EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper
• 2402.04252 • Published
• 29
VisionLM
-
-
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 44 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 23 -
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
Paper • 2402.05930 • Published • 39 -
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
Paper • 2402.05935 • Published • 17 -
ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling
Paper • 2402.06118 • Published • 15 -
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Paper • 2402.07456 • Published • 46 -
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
Paper • 2402.07872 • Published • 16 -
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
Paper • 2402.07865 • Published • 15 -
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 40 -
PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter
Paper • 2402.10896 • Published • 16 -
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models
Paper • 2402.10986 • Published • 81 -
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Paper • 2402.12226 • Published • 45 -
CoLLaVO: Crayon Large Language and Vision mOdel
Paper • 2402.11248 • Published • 22 -
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
Paper • 2402.11690 • Published • 9 -
VideoPrism: A Foundational Visual Encoder for Video Understanding
Paper • 2402.13217 • Published • 38 -
Video ReCap: Recursive Captioning of Hour-Long Videos
Paper • 2402.13250 • Published • 26 -
A Touch, Vision, and Language Dataset for Multimodal Alignment
Paper • 2402.13232 • Published • 16 -
How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
Paper • 2402.13220 • Published • 14 -
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Paper • 2402.13577 • Published • 9 -
PALO: A Polyglot Large Multimodal Model for 5B People
Paper • 2402.14818 • Published • 23 -
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Paper • 2402.14289 • Published • 20 -
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Paper • 2402.17177 • Published • 88 -
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Paper • 2402.19479 • Published • 35 -
MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies
Paper • 2403.01422 • Published • 30 -
InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
Paper • 2403.01487 • Published • 16 -
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
Paper • 2403.02677 • Published • 18 -
Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
Paper • 2403.02626 • Published • 11 -
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Paper • 2403.03194 • Published • 15 -
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
Paper • 2403.03003 • Published • 11 -
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Paper • 2403.09611 • Published • 129 -
MoAI: Mixture of All Intelligence for Large Language and Vision Models
Paper • 2403.07508 • Published • 77 -
Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
Paper • 2403.07750 • Published • 23 -
DragAnything: Motion Control for Anything using Entity Representation
Paper • 2403.07420 • Published • 14 -
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Paper • 2403.06764 • Published • 27 -
VideoMamba: State Space Model for Efficient Video Understanding
Paper • 2403.06977 • Published • 29 -
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Paper • 2403.05135 • Published • 45 -
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Paper • 2403.05530 • Published • 65 -
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper • 2403.05525 • Published • 49 -
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Paper • 2403.05438 • Published • 20 -
Uni-SMART: Universal Science Multimodal Analysis and Research Transformer
Paper • 2403.10301 • Published • 54 -
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
Paper • 2403.10517 • Published • 37 -
LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
Paper • 2403.11703 • Published • 17 -
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
Paper • 2403.11481 • Published • 13 -
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
Paper • 2403.12895 • Published • 32 -
Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs
Paper • 2403.12596 • Published • 11 -
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
Paper • 2403.14624 • Published • 53 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 33 -
InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding
Paper • 2403.15377 • Published • 28 -
SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Paper • 2403.15360 • Published • 13 -
VidLA: Video-Language Alignment at Scale
Paper • 2403.14870 • Published • 15 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 55 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 48 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 41 -
TextCraftor: Your Text Encoder Can be Image Quality Controller
Paper • 2403.18978 • Published • 15 -
Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
Paper • 2403.20331 • Published • 16 -
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
Paper • 2404.01197 • Published • 31 -
Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
Paper • 2404.01258 • Published • 12 -
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
Paper • 2404.03413 • Published • 27 -
LVLM-Intrepret: An Interpretability Tool for Large Vision-Language Models
Paper • 2404.03118 • Published • 25 -
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
Paper • 2404.03653 • Published • 35 -
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
Paper • 2404.05719 • Published • 83 -
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
Paper • 2404.05726 • Published • 23 -
MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation
Paper • 2404.05674 • Published • 15 -
Koala: Key frame-conditioned long video-LLM
Paper • 2404.04346 • Published • 7 -
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
Paper • 2404.06512 • Published • 30 -
Adapting LLaMA Decoder to Vision Transformer
Paper • 2404.06773 • Published • 18 -
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 19 -
Transferable and Principled Efficiency for Open-Vocabulary Segmentation
Paper • 2404.07448 • Published • 12 -
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models
Paper • 2404.07973 • Published • 32 -
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
Paper • 2404.09990 • Published • 14 -
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Paper • 2404.09204 • Published • 11 -
On Speculative Decoding for Multimodal Large Language Models
Paper • 2404.08856 • Published • 13 -
Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
Paper • 2404.12387 • Published • 39 -
BLINK: Multimodal Large Language Models Can See but Not Perceive
Paper • 2404.12390 • Published • 26 -
MultiBooth: Towards Generating All Your Concepts in an Image from Text
Paper • 2404.14239 • Published • 9 -
A Multimodal Automated Interpretability Agent
Paper • 2404.14394 • Published • 23 -
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Paper • 2404.12803 • Published • 30 -
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
Paper • 2404.13013 • Published • 31 -
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
Editable Image Elements for Controllable Synthesis
Paper • 2404.16029 • Published • 12 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension
Paper • 2404.16790 • Published • 10 -
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Paper • 2404.16821 • Published • 59 -
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
Paper • 2404.16375 • Published • 18 -
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Paper • 2404.16994 • Published • 37 -
HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections
Paper • 2404.16845 • Published • 7 -
BlenderAlchemy: Editing 3D Graphics with Vision-Language Models
Paper • 2404.17672 • Published • 19 -
Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations
Paper • 2404.17521 • Published • 13 -
Automatic Creative Selection with Cross-Modal Matching
Paper • 2405.00029 • Published • 9 -
What matters when building vision-language models?
Paper • 2405.02246 • Published • 103 -
Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots
Paper • 2405.07990 • Published • 20 -
No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Paper • 2405.08344 • Published • 15 -
Understanding the performance gap between online and offline alignment algorithms
Paper • 2405.08448 • Published • 18 -
SpeechVerse: A Large-scale Generalizable Audio Language Model
Paper • 2405.08295 • Published • 19 -
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Paper • 2405.08317 • Published • 12 -
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
Paper • 2405.09215 • Published • 22 -
LoRA Learns Less and Forgets Less
Paper • 2405.09673 • Published • 91 -
Many-Shot In-Context Learning in Multimodal Foundation Models
Paper • 2405.09798 • Published • 32 -
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper • 2405.09818 • Published • 132 -
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
Paper • 2405.10300 • Published • 30 -
Toon3D: Seeing Cartoons from a New Perspective
Paper • 2405.10320 • Published • 22 -
Octo: An Open-Source Generalist Robot Policy
Paper • 2405.12213 • Published • 29 -
Imp: Highly Capable Large Multimodal Models for Mobile Devices
Paper • 2405.12107 • Published • 29 -
Your Transformer is Secretly Linear
Paper • 2405.12250 • Published • 157 -
Diffusion for World Modeling: Visual Details Matter in Atari
Paper • 2405.12399 • Published • 30 -
AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability
Paper • 2405.14129 • Published • 14 -
CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers
Paper • 2405.13195 • Published • 12 -
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Paper • 2405.15574 • Published • 55 -
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition
Paper • 2405.15216 • Published • 15 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
Matryoshka Multimodal Models
Paper • 2405.17430 • Published • 34 -
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Paper • 2405.17428 • Published • 20 -
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
Paper • 2405.15738 • Published • 46 -
Dense Connector for MLLMs
Paper • 2405.13800 • Published • 24 -
Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation
Paper • 2405.14598 • Published • 13 -
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
Paper • 2405.20204 • Published • 37 -
Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities
Paper • 2405.18669 • Published • 12 -
MotionLLM: Understanding Human Behaviors from Human Motions and Videos
Paper • 2405.20340 • Published • 20 -
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Paper • 2405.21075 • Published • 26 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 33 -
Parrot: Multilingual Visual Instruction Tuning
Paper • 2406.02539 • Published • 36 -
PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM
Paper • 2406.02884 • Published • 18 -
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Paper • 2406.04325 • Published • 74 -
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Paper • 2406.04151 • Published • 24 -
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Paper • 2406.01014 • Published • 33 -
Vript: A Video Is Worth Thousands of Words
Paper • 2406.06040 • Published • 28 -
An Image is Worth 32 Tokens for Reconstruction and Generation
Paper • 2406.07550 • Published • 60 -
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Paper • 2406.06911 • Published • 12 -
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Paper • 2406.07476 • Published • 36 -
What If We Recaption Billions of Web Images with LLaMA-3?
Paper • 2406.08478 • Published • 43 -
MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
Paper • 2406.08407 • Published • 28 -
Needle In A Multimodal Haystack
Paper • 2406.07230 • Published • 54 -
mDPO: Conditional Preference Optimization for Multimodal Large Language Models
Paper • 2406.11839 • Published • 40 -
VideoLLM-online: Online Video Large Language Model for Streaming Video
Paper • 2406.11816 • Published • 26 -
TroL: Traversal of Layers for Large Language and Vision Models
Paper • 2406.12246 • Published • 36 -
VoCo-LLaMA: Towards Vision Compression with Large Language Models
Paper • 2406.12275 • Published • 31 -
Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning
Paper • 2406.12742 • Published • 15 -
Adversarial Attacks on Multimodal Agents
Paper • 2406.12814 • Published • 4 -
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models
Paper • 2406.11230 • Published • 33 -
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
Paper • 2406.12649 • Published • 16 -
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Paper • 2406.09358 • Published • 5 -
CMC-Bench: Towards a New Paradigm of Visual Signal Compression
Paper • 2406.09356 • Published • 6 -
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
Paper • 2406.09406 • Published • 15 -
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Paper • 2406.09403 • Published • 23 -
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Paper • 2406.09411 • Published • 19 -
mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus
Paper • 2406.08707 • Published • 17 -
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts
Paper • 2406.09162 • Published • 14 -
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
Paper • 2406.08418 • Published • 32 -
GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
Paper • 2406.08451 • Published • 26 -
Are We Done with MMLU?
Paper • 2406.04127 • Published • 39 -
NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
Paper • 2406.06523 • Published • 53 -
Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
Paper • 2406.08487 • Published • 14 -
VCR: Visual Caption Restoration
Paper • 2406.06462 • Published • 13 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 51 -
OpenVLA: An Open-Source Vision-Language-Action Model
Paper • 2406.09246 • Published • 43 -
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Paper • 2406.08552 • Published • 25 -
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Paper • 2406.04338 • Published • 39 -
Hibou: A Family of Foundational Vision Transformers for Pathology
Paper • 2406.05074 • Published • 10 -
Make It Count: Text-to-Image Generation with an Accurate Number of Objects
Paper • 2406.10210 • Published • 78 -
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Paper • 2406.08973 • Published • 89 -
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Paper • 2406.11833 • Published • 62 -
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
Paper • 2406.11831 • Published • 22 -
From Pixels to Prose: A Large Dataset of Dense Image Captions
Paper • 2406.10328 • Published • 18 -
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
Paper • 2406.14544 • Published • 35 -
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Paper • 2406.11069 • Published • 14 -
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
Paper • 2406.11271 • Published • 21 -
Task Me Anything
Paper • 2406.11775 • Published • 9 -
Unifying Multimodal Retrieval via Document Screenshot Embedding
Paper • 2406.11251 • Published • 11 -
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
Paper • 2406.10601 • Published • 70 -
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Paper • 2406.14515 • Published • 33 -
Two Giraffes in a Dirt Field: Using Game Play to Investigate Situation Modelling in Large Multimodal Models
Paper • 2406.14035 • Published • 13 -
ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights
Paper • 2406.14596 • Published • 5 -
Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report
Paper • 2406.11403 • Published • 4 -
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
Paper • 2406.16338 • Published • 26 -
Long Context Transfer from Language to Vision
Paper • 2406.16852 • Published • 33 -
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Paper • 2406.16860 • Published • 63 -
MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
Paper • 2406.17770 • Published • 19 -
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
Paper • 2406.15704 • Published • 6 -
Octo-planner: On-device Language Model for Planner-Action Agents
Paper • 2406.18082 • Published • 48 -
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
Paper • 2406.18521 • Published • 30 -
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
Paper • 2406.15334 • Published • 9 -
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
Paper • 2406.17294 • Published • 11 -
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Paper • 2406.19389 • Published • 54 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 42 -
MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data
Paper • 2406.18790 • Published • 34 -
Simulating Classroom Education with LLM-Empowered Agents
Paper • 2406.19226 • Published • 32 -
AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
Paper • 2406.10900 • Published • 11 -
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Paper • 2406.20095 • Published • 18 -
EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
Paper • 2406.20076 • Published • 10 -
Arboretum: A Large Multimodal Dataset Enabling AI for Biodiversity
Paper • 2406.17720 • Published • 8 -
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
Paper • 2407.01284 • Published • 81 -
ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
Paper • 2406.19741 • Published • 60 -
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation
Paper • 2407.00468 • Published • 35 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 51 -
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
Paper • 2407.00114 • Published • 13 -
Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Paper • 2407.02477 • Published • 24 -
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
Paper • 2407.03320 • Published • 94 -
TokenPacker: Efficient Visual Projector for Multimodal LLM
Paper • 2407.02392 • Published • 23 -
Unveiling Encoder-Free Vision-Language Models
Paper • 2406.11832 • Published • 54 -
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
Paper • 2406.08085 • Published • 17 -
Granular Privacy Control for Geolocation with Vision Language Models
Paper • 2407.04952 • Published • 7 -
ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
Paper • 2407.06135 • Published • 22 -
Multi-Object Hallucination in Vision-Language Models
Paper • 2407.06192 • Published • 12 -
Vision language models are blind
Paper • 2407.06581 • Published • 84 -
VIMI: Grounding Video Generation through Multi-modal Instruction
Paper • 2407.06304 • Published • 10 -
Video-to-Audio Generation with Hidden Alignment
Paper • 2407.07464 • Published • 17 -
Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge
Paper • 2407.03958 • Published • 21 -
Understanding Visual Feature Reliance through the Lens of Complexity
Paper • 2407.06076 • Published • 6 -
Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
Paper • 2407.06723 • Published • 11 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 72 -
LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models
Paper • 2407.07895 • Published • 42 -
Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
Paper • 2302.06555 • Published • 9 -
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
Paper • 2407.08303 • Published • 19 -
The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective
Paper • 2407.08583 • Published • 13 -
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model
Paper • 2407.07053 • Published • 47 -
E5-V: Universal Embeddings with Multimodal Large Language Models
Paper • 2407.12580 • Published • 42 -
Goldfish: Vision-Language Understanding of Arbitrarily Long Videos
Paper • 2407.12679 • Published • 8 -
AUITestAgent: Automatic Requirements Oriented GUI Function Testing
Paper • 2407.09018 • Published • 5 -
ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter
Paper • 2407.11298 • Published • 6 -
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
Paper • 2407.12366 • Published • 4 -
Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Paper • 2406.07057 • Published • 17 -
EVLM: An Efficient Vision-Language Model for Visual Understanding
Paper • 2407.14177 • Published • 45 -
VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding
Paper • 2407.12594 • Published • 19 -
SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
Paper • 2407.15841 • Published • 40 -
VideoGameBunny: Towards vision assistants for video games
Paper • 2407.15295 • Published • 23 -
CGB-DM: Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model
Paper • 2407.15233 • Published • 7 -
OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person
Paper • 2407.16224 • Published • 29 -
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
Paper • 2407.16655 • Published • 30 -
INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
Paper • 2407.16198 • Published • 13 -
VILA^2: VILA Augmented VILA
Paper • 2407.17453 • Published • 41 -
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
Paper • 2407.15815 • Published • 14 -
AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents
Paper • 2407.17490 • Published • 31 -
Efficient Inference of Vision Instruction-Following Models with Elastic Cache
Paper • 2407.18121 • Published • 17 -
VSSD: Vision Mamba with Non-Casual State Space Duality
Paper • 2407.18559 • Published • 20 -
Wolf: Captioning Everything with a World Summarization Framework
Paper • 2407.18908 • Published • 32 -
Diffusion Feedback Helps CLIP See Better
Paper • 2407.20171 • Published • 36 -
VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
Paper • 2407.19795 • Published • 11 -
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Paper • 2407.19985 • Published • 37 -
MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
Paper • 2407.21770 • Published • 22 -
Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent
Paper • 2407.21646 • Published • 18 -
ShieldGemma: Generative AI Content Moderation Based on Gemma
Paper • 2407.21772 • Published • 14 -
Open-Vocabulary Audio-Visual Semantic Segmentation
Paper • 2407.21721 • Published • 9 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 120 -
OmniParser for Pure Vision Based GUI Agent
Paper • 2408.00203 • Published • 24 -
Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
Paper • 2407.21794 • Published • 6 -
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
Paper • 2408.01800 • Published • 92 -
Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
Paper • 2408.02657 • Published • 35 -
Language Model Can Listen While Speaking
Paper • 2408.02622 • Published • 40 -
ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning
Paper • 2408.02210 • Published • 9 -
Operationalizing Contextual Integrity in Privacy-Conscious Assistants
Paper • 2408.02373 • Published • 5 -
LLaVA-OneVision: Easy Visual Task Transfer
Paper • 2408.03326 • Published • 61 -
Diffusion Models as Data Mining Tools
Paper • 2408.02752 • Published • 15 -
AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation
Paper • 2408.01708 • Published • 4 -
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
Paper • 2408.03615 • Published • 31 -
Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
Paper • 2408.03695 • Published • 13 -
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond
Paper • 2408.03900 • Published • 10 -
Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches
Paper • 2408.04567 • Published • 26 -
Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models
Paper • 2408.04594 • Published • 14 -
Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics
Paper • 2408.04631 • Published • 9 -
VITA: Towards Open-Source Interactive Omni Multimodal LLM
Paper • 2408.05211 • Published • 50 -
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
Paper • 2408.04840 • Published • 33 -
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
Paper • 2408.04810 • Published • 24 -
ControlNeXt: Powerful and Efficient Control for Image and Video Generation
Paper • 2408.06070 • Published • 55 -
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
Paper • 2408.06327 • Published • 17 -
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
Paper • 2408.05939 • Published • 14 -
Imagen 3
Paper • 2408.07009 • Published • 62 -
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
Paper • 2408.06663 • Published • 16 -
DeepSpeak Dataset v1.0
Paper • 2408.05366 • Published • 14 -
Towards flexible perception with visual memory
Paper • 2408.08172 • Published • 23 -
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Paper • 2408.08872 • Published • 101 -
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
Paper • 2408.08459 • Published • 45 -
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
Paper • 2408.08441 • Published • 8 -
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Paper • 2408.10188 • Published • 52 -
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
Paper • 2408.11001 • Published • 13 -
Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data
Paper • 2408.10119 • Published • 17 -
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 63 -
NeCo: Improving DINOv2's spatial representations in 19 GPU hours with Patch Neighbor Consistency
Paper • 2408.11054 • Published • 14 -
Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
Paper • 2408.10764 • Published • 9 -
Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos
Paper • 2408.10998 • Published • 9 -
MambaEVT: Event Stream based Visual Object Tracking using State Space Model
Paper • 2408.10487 • Published • 7 -
FocusLLM: Scaling LLM's Context by Parallel Decoding
Paper • 2408.11745 • Published • 25 -
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
Paper • 2408.11318 • Published • 56 -
GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models
Paper • 2408.11817 • Published • 9 -
FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting
Paper • 2408.11706 • Published • 7 -
TrackGo: A Flexible and Efficient Method for Controllable Video Generation
Paper • 2408.11475 • Published • 18 -
Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
Paper • 2408.11237 • Published • 6 -
Iterative Object Count Optimization for Text-to-image Diffusion Models
Paper • 2408.11721 • Published • 6 -
Sapiens: Foundation for Human Vision Models
Paper • 2408.12569 • Published • 94 -
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
Paper • 2408.12528 • Published • 51 -
Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
Paper • 2408.11878 • Published • 63 -
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
Paper • 2408.12590 • Published • 35 -
Scalable Autoregressive Image Generation with Mamba
Paper • 2408.12245 • Published • 26 -
Real-Time Video Generation with Pyramid Attention Broadcast
Paper • 2408.12588 • Published • 17 -
SPARK: Multi-Vision Sensor Perception and Reasoning Benchmark for Large-scale Vision-Language Models
Paper • 2408.12114 • Published • 15 -
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Paper • 2408.09787 • Published • 10 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 133 -
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Paper • 2408.13257 • Published • 26 -
CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Paper • 2408.13239 • Published • 11 -
Foundation Models for Music: A Survey
Paper • 2408.14340 • Published • 44 -
LLaVaOLMoBitnet1B: Ternary LLM goes Multimodal!
Paper • 2408.13402 • Published • 18 -
TVG: A Training-free Transition Video Generation Method with Diffusion Models
Paper • 2408.13413 • Published • 14 -
BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline
Paper • 2408.15079 • Published • 54 -
Law of Vision Representation in MLLMs
Paper • 2408.16357 • Published • 95 -
CogVLM2: Visual Language Models for Image and Video Understanding
Paper • 2408.16500 • Published • 57 -
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Paper • 2408.16532 • Published • 50 -
Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming
Paper • 2408.16725 • Published • 53 -
VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
Paper • 2408.17253 • Published • 39 -
TableBench: A Comprehensive and Complex Benchmark for Table Question Answering
Paper • 2408.09174 • Published • 52 -
VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges
Paper • 2409.01071 • Published • 27 -
DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Paper • 2409.02095 • Published • 37 -
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 34 -
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
Paper • 2409.02889 • Published • 54 -
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 92 -
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
Paper • 2409.04410 • Published • 25 -
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
Paper • 2409.05840 • Published • 49 -
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Paper • 2409.02795 • Published • 72 -
POINTS: Improving Your Vision-language Model with Affordable Strategies
Paper • 2409.04828 • Published • 24 -
Benchmarking Chinese Knowledge Rectification in Large Language Models
Paper • 2409.05806 • Published • 15 -
LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Paper • 2409.06666 • Published • 60 -
Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis
Paper • 2409.06135 • Published • 16 -
PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation
Paper • 2409.06820 • Published • 68 -
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Paper • 2409.07129 • Published • 8 -
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
Paper • 2409.07239 • Published • 15 -
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
Paper • 2409.06277 • Published • 15 -
Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
Paper • 2409.09269 • Published • 8 -
One missing piece in Vision and Language: A Survey on Comics Understanding
Paper • 2409.09502 • Published • 24 -
NVLM: Open Frontier-Class Multimodal LLMs
Paper • 2409.11402 • Published • 74 -
OmniGen: Unified Image Generation
Paper • 2409.11340 • Published • 115 -
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Paper • 2409.11355 • Published • 30 -
OSV: One Step is Enough for High-Quality Image to Video Generation
Paper • 2409.11367 • Published • 14 -
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding
Paper • 2409.03420 • Published • 26 -
InstantDrag: Improving Interactivity in Drag-based Image Editing
Paper • 2409.08857 • Published • 34 -
AudioBERT: Audio Knowledge Augmented Language Model
Paper • 2409.08199 • Published • 5 -
LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study
Paper • 2409.08554 • Published • 3 -
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Paper • 2409.12191 • Published • 78 -
Qwen2.5-Coder Technical Report
Paper • 2409.12186 • Published • 153 -
Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
Paper • 2409.11564 • Published • 20 -
Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models
Paper • 2409.12139 • Published • 12 -
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
Paper • 2409.12961 • Published • 25 -
StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation
Paper • 2409.12576 • Published • 16 -
Imagine yourself: Tuning-Free Personalized Image Generation
Paper • 2409.13346 • Published • 69 -
YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models
Paper • 2409.13592 • Published • 50 -
Portrait Video Editing Empowered by Multimodal Generative Priors
Paper • 2409.13591 • Published • 16 -
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
Paper • 2409.15278 • Published • 24 -
Phantom of Latent for Large Language and Vision Models
Paper • 2409.14713 • Published • 29 -
Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections
Paper • 2409.14677 • Published • 15 -
MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling
Paper • 2409.16160 • Published • 34 -
MonoFormer: One Transformer for Both Diffusion and Autoregression
Paper • 2409.16280 • Published • 18 -
Seeing Faces in Things: A Model and Dataset for Pareidolia
Paper • 2409.16143 • Published • 17 -
Attention Prompting on Image for Large Vision-Language Models
Paper • 2409.17143 • Published • 7 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121 -
MIO: A Foundation Model on Multimodal Tokens
Paper • 2409.17692 • Published • 53 -
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
Paper • 2409.20566 • Published • 55 -
Visual Question Decomposition on Multimodal Large Language Models
Paper • 2409.19339 • Published • 8 -
Loong: Generating Minute-level Long Videos with Autoregressive Language Models
Paper • 2410.02757 • Published • 36 -
Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models
Paper • 2410.02740 • Published • 54 -
LLaVA-Critic: Learning to Evaluate Multimodal Models
Paper • 2410.02712 • Published • 37 -
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
Paper • 2410.02762 • Published • 9 -
Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos
Paper • 2410.02763 • Published • 7 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 151 -
VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
Paper • 2410.04364 • Published • 29 -
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
Paper • 2410.05243 • Published • 20 -
UniMuMo: Unified Text, Music and Motion Generation
Paper • 2410.04534 • Published • 19 -
TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Paper • 2410.04734 • Published • 18 -
OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction
Paper • 2410.04932 • Published • 9 -
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Paper • 2410.01912 • Published • 14 -
ControlAR: Controllable Image Generation with Autoregressive Models
Paper • 2410.02705 • Published • 11 -
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Paper • 2410.03290 • Published • 7 -
Aria: An Open Multimodal Native Mixture-of-Experts Model
Paper • 2410.05993 • Published • 111 -
Personalized Visual Instruction Tuning
Paper • 2410.07113 • Published • 70 -
Pixtral 12B
Paper • 2410.07073 • Published • 69 -
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
Paper • 2410.07171 • Published • 43 -
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
Paper • 2410.07167 • Published • 39 -
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Paper • 2410.06373 • Published • 36 -
Pyramidal Flow Matching for Efficient Video Generative Modeling
Paper • 2410.05954 • Published • 40 -
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
Paper • 2410.05363 • Published • 45 -
Story-Adapter: A Training-free Iterative Framework for Long Story Visualization
Paper • 2410.06244 • Published • 20 -
MM-Ego: Towards Building Egocentric Multimodal LLMs
Paper • 2410.07177 • Published • 22 -
TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
Paper • 2410.05591 • Published • 13 -
Temporal Reasoning Transfer from Text to Video
Paper • 2410.06166 • Published • 13 -
MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
Paper • 2410.03450 • Published • 36 -
Intriguing Properties of Large Language and Vision Models
Paper • 2410.04751 • Published • 16 -
Progressive Autoregressive Video Diffusion Models
Paper • 2410.08151 • Published • 16 -
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
Paper • 2410.05210 • Published • 11 -
Self-Boosting Large Language Models with Synthetic Preference Data
Paper • 2410.06961 • Published • 16 -
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Paper • 2410.07484 • Published • 51 -
Agent S: An Open Agentic Framework that Uses Computers Like a Human
Paper • 2410.08164 • Published • 26 -
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
Paper • 2410.06154 • Published • 16 -
Baichuan-Omni Technical Report
Paper • 2410.08565 • Published • 87 -
From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning
Paper • 2410.06456 • Published • 37 -
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Paper • 2410.07133 • Published • 19 -
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Paper • 2410.10139 • Published • 51 -
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Paper • 2410.10594 • Published • 29 -
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Paper • 2410.11779 • Published • 26 -
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
Paper • 2410.10816 • Published • 21 -
Improving Long-Text Alignment for Text-to-Image Diffusion Models
Paper • 2410.11817 • Published • 15 -
OMCAT: Omni Context Aware Transformer
Paper • 2410.12109 • Published • 4 -
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
Paper • 2410.11623 • Published • 49 -
HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks
Paper • 2410.12381 • Published • 43 -
The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
Paper • 2410.12787 • Published • 30 -
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Paper • 2410.13848 • Published • 35 -
Harnessing Webpage UIs for Text-Rich Visual Understanding
Paper • 2410.13824 • Published • 30 -
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
Paper • 2410.12705 • Published • 32 -
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
Paper • 2410.13863 • Published • 37 -
MobA: A Two-Level Agent System for Efficient Mobile Task Automation
Paper • 2410.13757 • Published • 32 -
Roadmap towards Superhuman Speech Understanding using Large Language Models
Paper • 2410.13268 • Published • 33 -
Movie Gen: A Cast of Media Foundation Models
Paper • 2410.13720 • Published • 100 -
DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
Paper • 2410.13830 • Published • 26 -
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Paper • 2410.13085 • Published • 24 -
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Paper • 2410.13639 • Published • 19 -
VidPanos: Generative Panoramic Videos from Casual Panning Videos
Paper • 2410.13832 • Published • 13 -
Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant
Paper • 2410.13360 • Published • 9 -
γ-MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
Paper • 2410.13859 • Published • 8 -
Can MLLMs Understand the Deep Implication Behind Chinese Images?
Paper • 2410.13854 • Published • 12 -
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
Paper • 2410.13925 • Published • 24 -
Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities
Paper • 2410.11190 • Published • 22 -
SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation
Paper • 2410.14745 • Published • 47 -
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
Paper • 2410.16268 • Published • 69 -
Baichuan Alignment Technical Report
Paper • 2410.14940 • Published • 51 -
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
Paper • 2410.13861 • Published • 56 -
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
Paper • 2410.09347 • Published • 5 -
AutoTrain: No-code training for state-of-the-art models
Paper • 2410.15735 • Published • 59 -
RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
Paper • 2410.16184 • Published • 25 -
Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant
Paper • 2410.15316 • Published • 12 -
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Paper • 2410.17247 • Published • 47 -
Aligning Large Language Models via Self-Steering Optimization
Paper • 2410.17131 • Published • 24 -
Improve Vision Language Model Chain-of-thought Reasoning
Paper • 2410.16198 • Published • 26 -
xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
Paper • 2410.16267 • Published • 18 -
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
Paper • 2410.17637 • Published • 35 -
Can Knowledge Editing Really Correct Hallucinations?
Paper • 2410.16251 • Published • 55 -
LOGO -- Long cOntext aliGnment via efficient preference Optimization
Paper • 2410.18533 • Published • 43 -
Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Paper • 2410.18798 • Published • 21 -
Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data
Paper • 2410.18558 • Published • 18 -
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
Paper • 2410.17779 • Published • 8 -
ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting
Paper • 2410.17856 • Published • 52 -
Continuous Speech Synthesis using per-token Latent Diffusion
Paper • 2410.16048 • Published • 29 -
GPT-4o System Card
Paper • 2410.21276 • Published • 87 -
Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines
Paper • 2410.21220 • Published • 11 -
CLEAR: Character Unlearning in Textual and Visual Modalities
Paper • 2410.18057 • Published • 209 -
Toxicity of the Commons: Curating Open-Source Pre-Training Data
Paper • 2410.22587 • Published • 10 -
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
Paper • 2410.23287 • Published • 19 -
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
Paper • 2410.23218 • Published • 49 -
Personalization of Large Language Models: A Survey
Paper • 2411.00027 • Published • 33 -
Randomized Autoregressive Visual Generation
Paper • 2411.00776 • Published • 18 -
Face Anonymization Made Simple
Paper • 2411.00762 • Published • 9 -
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents
Paper • 2410.24024 • Published • 49 -
WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
Paper • 2411.02337 • Published • 36 -
How Far is Video Generation from World Model: A Physical Law Perspective
Paper • 2411.02385 • Published • 34 -
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Paper • 2411.02265 • Published • 25 -
Adaptive Caching for Faster Video Generation with Diffusion Transformers
Paper • 2411.02397 • Published • 23 -
AutoVFX: Physically Realistic Video Editing from Natural Language Instructions
Paper • 2411.02394 • Published • 16 -
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Paper • 2411.02359 • Published • 14 -
Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination
Paper • 2411.03823 • Published • 49 -
Adaptive Length Image Tokenization via Recurrent Allocation
Paper • 2411.02393 • Published • 13 -
ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning
Paper • 2411.05003 • Published • 71 -
TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation
Paper • 2411.04709 • Published • 26 -
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Paper • 2411.04952 • Published • 29 -
Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?
Paper • 2411.05000 • Published • 22 -
VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
Paper • 2411.04923 • Published • 23 -
Analyzing The Language of Visual Tokens
Paper • 2411.05001 • Published • 24 -
LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation
Paper • 2411.04997 • Published • 39 -
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Paper • 2411.04097 • Published • 5 -
OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision
Paper • 2411.07199 • Published • 50 -
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Paper • 2411.07140 • Published • 35 -
Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models
Paper • 2411.07126 • Published • 30 -
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
Paper • 2411.07232 • Published • 68 -
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
Paper • 2411.07975 • Published • 31 -
Autoregressive Models in Vision: A Survey
Paper • 2411.05902 • Published • 19 -
MagicQuill: An Intelligent Interactive Image Editing System
Paper • 2411.09703 • Published • 80 -
Sharingan: Extract User Action Sequence from Desktop Recordings
Paper • 2411.08768 • Published • 9 -
LLaVA-o1: Let Vision Language Models Reason Step-by-Step
Paper • 2411.10440 • Published • 129 -
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
Paper • 2411.06558 • Published • 36 -
The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
Paper • 2411.10323 • Published • 34 -
Number it: Temporal Grounding Videos like Flipping Manga
Paper • 2411.10332 • Published • 14 -
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
Paper • 2411.10640 • Published • 46 -
Generative World Explorer
Paper • 2411.11844 • Published • 77 -
AnimateAnything: Consistent and Controllable Animation for Video Generation
Paper • 2411.10836 • Published • 24 -
SlimLM: An Efficient Small Language Model for On-Device Document Assistance
Paper • 2411.09944 • Published • 12 -
Adaptive Decoding via Latent Preference Optimization
Paper • 2411.09661 • Published • 10 -
StableV2V: Stablizing Shape Consistency in Video-to-Video Editing
Paper • 2411.11045 • Published • 11 -
RedPajama: an Open Dataset for Training Large Language Models
Paper • 2411.12372 • Published • 56 -
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
Paper • 2411.11909 • Published • 22 -
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
Paper • 2411.10818 • Published • 26 -
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
Paper • 2411.12044 • Published • 14 -
Continuous Speculative Decoding for Autoregressive Image Generation
Paper • 2411.11925 • Published • 16 -
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper • 2411.10442 • Published • 87 -
Multimodal Autoregressive Pre-training of Large Vision Encoders
Paper • 2411.14402 • Published • 47 -
Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
Paper • 2411.14432 • Published • 25 -
Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
Paper • 2411.14982 • Published • 19 -
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Paper • 2411.16489 • Published • 45 -
One Diffusion to Generate Them All
Paper • 2411.16318 • Published • 28 -
DreamRunner: Fine-Grained Storytelling Video Generation with Retrieval-Augmented Motion Adaptation
Paper • 2411.16657 • Published • 19 -
Factorized Visual Tokenization and Generation
Paper • 2411.16681 • Published • 19 -
TEXGen: a Generative Diffusion Model for Mesh Textures
Paper • 2411.14740 • Published • 17 -
ROICtrl: Boosting Instance Control for Visual Generation
Paper • 2411.17949 • Published • 87 -
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Paper • 2411.17465 • Published • 89 -
SketchAgent: Language-Driven Sequential Sketch Generation
Paper • 2411.17673 • Published • 18 -
Rethinking Token Reduction in MLLMs: Towards a Unified Paradigm for Training-Free Acceleration
Paper • 2411.17686 • Published • 19 -
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
Paper • 2411.15296 • Published • 21 -
Large Language Model-Brained GUI Agents: A Survey
Paper • 2411.18279 • Published • 30 -
VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
Paper • 2411.17991 • Published • 5 -
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Paper • 2411.18203 • Published • 40 -
On Domain-Specific Post-Training for Multimodal Large Language Models
Paper • 2411.19930 • Published • 31 -
Yi-Lightning Technical Report
Paper • 2412.01253 • Published • 28 -
X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models
Paper • 2412.01824 • Published • 64 -
VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation
Paper • 2412.00927 • Published • 29 -
Open-Sora Plan: Open-Source Large Video Generation Model
Paper • 2412.00131 • Published • 33 -
SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters
Paper • 2412.00174 • Published • 23 -
VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
Paper • 2412.00947 • Published • 8 -
AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?
Paper • 2412.02611 • Published • 25 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 133 -
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
Paper • 2412.03069 • Published • 34 -
Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
Paper • 2412.00493 • Published • 17 -
Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
Paper • 2412.03565 • Published • 10 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 117 -
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 62 -
NVILA: Efficient Frontier Visual Language Models
Paper • 2412.04468 • Published • 60 -
Negative Token Merging: Image-based Adversarial Feature Guidance
Paper • 2412.01339 • Published • 22 -
Personalized Multimodal Large Language Models: A Survey
Paper • 2412.02142 • Published • 13 -
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
Paper • 2412.01169 • Published • 13 -
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
Paper • 2412.04449 • Published • 7 -
Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
Paper • 2412.03704 • Published • 6 -
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 160 -
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Paper • 2412.05237 • Published • 46 -
LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
Paper • 2412.04814 • Published • 46 -
SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
Paper • 2412.04301 • Published • 40 -
CompCap: Improving Multimodal Large Language Models with Composite Captions
Paper • 2412.05243 • Published • 20 -
Mind the Time: Temporally-Controlled Multi-Event Video Generation
Paper • 2412.05263 • Published • 10 -
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Paper • 2412.04626 • Published • 13 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 94 -
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
Paper • 2412.06781 • Published • 23 -
Maya: An Instruction Finetuned Multilingual Multimodal Model
Paper • 2412.07112 • Published • 28 -
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
Paper • 2412.04432 • Published • 16 -
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models
Paper • 2412.05939 • Published • 15 -
DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation
Paper • 2412.07589 • Published • 48 -
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
Paper • 2412.03548 • Published • 17 -
POINTS1.5: Building a Vision-Language Model towards Real World Applications
Paper • 2412.08443 • Published • 38 -
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations
Paper • 2412.08580 • Published • 45 -
MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation
Paper • 2412.07147 • Published • 5 -
StreamChat: Chatting with Streaming Video
Paper • 2412.08646 • Published • 18 -
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Paper • 2412.09596 • Published • 97 -
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions
Paper • 2412.08737 • Published • 54 -
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
Paper • 2412.09501 • Published • 48 -
Multimodal Latent Language Modeling with Next-Token Diffusion
Paper • 2412.08635 • Published • 49 -
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
Paper • 2412.09618 • Published • 21 -
VisionArena: 230K Real World User-VLM Conversations with Preference Labels
Paper • 2412.08687 • Published • 13 -
Arbitrary-steps Image Super-resolution via Diffusion Inversion
Paper • 2412.09013 • Published • 13 -
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Paper • 2412.10360 • Published • 147 -
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 98 -
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
Paper • 2412.09283 • Published • 19 -
Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation
Paper • 2412.09428 • Published • 7 -
SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
Paper • 2412.09604 • Published • 38 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
BrushEdit: All-In-One Image Inpainting and Editing
Paper • 2412.10316 • Published • 36 -
VidTok: A Versatile and Open-Source Video Tokenizer
Paper • 2412.13061 • Published • 8 -
GUI Agents: A Survey
Paper • 2412.13501 • Published • 29 -
Progressive Multimodal Reasoning via Active Retrieval
Paper • 2412.14835 • Published • 73 -
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
Paper • 2412.14475 • Published • 57 -
Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception
Paper • 2412.14233 • Published • 6 -
Large Motion Video Autoencoding with Cross-modal Video VAE
Paper • 2412.17805 • Published • 24 -
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding
Paper • 2412.17295 • Published • 9 -
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
Paper • 2412.15213 • Published • 28 -
Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion
Paper • 2412.14462 • Published • 15 -
AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation
Paper • 2412.15191 • Published • 5 -
Parallelized Autoregressive Visual Generation
Paper • 2412.15119 • Published • 53 -
Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
Paper • 2412.15322 • Published • 20 -
Sequence Matters: Harnessing Video Models in 3D Super-Resolution
Paper • 2412.11525 • Published • 11 -
Diving into Self-Evolving Training for Multimodal Reasoning
Paper • 2412.17451 • Published • 42 -
Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
Paper • 2412.17153 • Published • 39 -
NILE: Internal Consistency Alignment in Large Language Models
Paper • 2412.16686 • Published • 8 -
DepthLab: From Partial to Complete
Paper • 2412.18153 • Published • 36 -
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
Paper • 2412.18450 • Published • 36 -
Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
Paper • 2412.17739 • Published • 41 -
DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
Paper • 2412.18597 • Published • 20 -
How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
Paper • 2412.18495 • Published • 9 -
Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
Paper • 2412.18609 • Published • 17 -
Bridging the Data Provenance Gap Across Text, Speech and Video
Paper • 2412.17847 • Published • 10 -
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Paper • 2412.18319 • Published • 39 -
YuLan-Mini: An Open Data-efficient Language Model
Paper • 2412.17743 • Published • 66 -
MMFactory: A Universal Solution Search Engine for Vision-Language Tasks
Paper • 2412.18072 • Published • 18 -
Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation
Paper • 2412.18176 • Published • 16 -
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
Paper • 2412.18619 • Published • 60 -
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Paper • 2412.19326 • Published • 18 -
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Paper • 2412.19512 • Published • 9 -
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
Paper • 2412.18525 • Published • 74 -
Edicho: Consistent Image Editing in the Wild
Paper • 2412.21079 • Published • 22 -
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
Paper • 2412.21037 • Published • 24 -
Are Vision-Language Models Truly Understanding Multi-vision Sensor?
Paper • 2412.20750 • Published • 20 -
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 109 -
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
Paper • 2501.01427 • Published • 53 -
LTX-Video: Realtime Video Latent Diffusion
Paper • 2501.00103 • Published • 50 -
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper • 2501.00599 • Published • 46 -
MLLM-as-a-Judge for Image Safety without Human Labeling
Paper • 2501.00192 • Published • 31 -
A3: Android Agent Arena for Mobile GUI Agents
Paper • 2501.01149 • Published • 22 -
Unifying Specialized Visual Encoders for Video Language Models
Paper • 2501.01426 • Published • 20 -
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
Paper • 2501.01957 • Published • 47 -
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 52 -
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Paper • 2501.02955 • Published • 44 -
Cosmos World Foundation Model Platform for Physical AI
Paper • 2501.03575 • Published • 82 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 104 -
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Paper • 2501.04001 • Published • 47 -
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis
Paper • 2501.04561 • Published • 17 -
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
Paper • 2501.04575 • Published • 25 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 102 -
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
Paper • 2501.03271 • Published • 10 -
The GAN is dead; long live the GAN! A Modern GAN Baseline
Paper • 2501.05441 • Published • 95 -
Enhancing Human-Like Responses in Large Language Models
Paper • 2501.05032 • Published • 61 -
An Empirical Study of Autoregressive Pre-training from Videos
Paper • 2501.05453 • Published • 41 -
Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Paper • 2501.05122 • Published • 19 -
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
Paper • 2501.04377 • Published • 14 -
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Paper • 2501.05874 • Published • 75 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 65 -
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
Paper • 2501.05767 • Published • 29 -
OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
Paper • 2501.05510 • Published • 44 -
MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
Paper • 2501.06282 • Published • 53 -
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
Paper • 2501.08326 • Published • 34 -
MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
Paper • 2501.07556 • Published • 7 -
MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents
Paper • 2501.08828 • Published • 30 -
RepVideo: Rethinking Cross-Layer Representation for Video Generation
Paper • 2501.08994 • Published • 15 -
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Paper • 2501.05452 • Published • 15 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
VideoAuteur: Towards Long Narrative Video Generation
Paper • 2501.06173 • Published • 31 -
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Paper • 2501.06842 • Published • 16 -
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
Paper • 2501.06708 • Published • 5 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 300 -
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
Paper • 2501.07730 • Published • 18 -
HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
Paper • 2501.08292 • Published • 17 -
Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding
Paper • 2501.07888 • Published • 15 -
OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training
Paper • 2501.08197 • Published • 9 -
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding
Paper • 2501.07783 • Published • 8 -
MINIMA: Modality Invariant Image Matching
Paper • 2412.19412 • Published • 4 -
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 46 -
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
Paper • 2501.09755 • Published • 35 -
Do generative video models learn physical principles from watching videos?
Paper • 2501.09038 • Published • 34 -
FAST: Efficient Action Tokenization for Vision-Language-Action Models
Paper • 2501.09747 • Published • 28 -
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Paper • 2501.09781 • Published • 27 -
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Paper • 2501.12380 • Published • 84 -
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
Paper • 2501.11733 • Published • 28 -
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
Paper • 2501.13926 • Published • 43 -
Baichuan-Omni-1.5 Technical Report
Paper • 2501.15368 • Published • 60 -
Qwen2.5-1M Technical Report
Paper • 2501.15383 • Published • 72 -
Towards General-Purpose Model-Free Reinforcement Learning
Paper • 2501.16142 • Published • 31 -
Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
Paper • 2501.15907 • Published • 17 -
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
Paper • 2403.09193 • Published • 9 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 124 -
PixelWorld: Towards Perceiving Everything as Pixels
Paper • 2501.19339 • Published • 17 -
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper • 2502.01061 • Published • 223 -
Process Reinforcement through Implicit Rewards
Paper • 2502.01456 • Published • 62 -
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Paper • 2502.01341 • Published • 39 -
Humanity's Last Exam
Paper • 2501.14249 • Published • 77 -
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Paper • 2501.13106 • Published • 90 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 126 -
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Paper • 2501.12895 • Published • 61 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 440 -
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
Paper • 2502.03275 • Published • 18 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 60 -
Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment
Paper • 2502.04328 • Published • 29 -
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Paper • 2502.05173 • Published • 64 -
Fast Video Generation with Sliding Tile Attention
Paper • 2502.04507 • Published • 51 -
Goku: Flow Based Video Generative Foundation Models
Paper • 2502.04896 • Published • 106 -
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 152 -
QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
Paper • 2502.05178 • Published • 10 -
On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices
Paper • 2502.04363 • Published • 12 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 152 -
Scaling Pre-training to One Hundred Billion Data for Vision Language Models
Paper • 2502.07617 • Published • 29 -
Expect the Unexpected: FailSafe Long Context QA for Finance
Paper • 2502.06329 • Published • 133 -
Magic 1-For-1: Generating One Minute Video Clips within One Minute
Paper • 2502.07701 • Published • 36 -
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Paper • 2502.08590 • Published • 42 -
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
Paper • 2502.07870 • Published • 45 -
WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation
Paper • 2502.08047 • Published • 28 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 57 -
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data
Paper • 2502.08468 • Published • 16 -
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
Paper • 2502.08946 • Published • 191 -
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Paper • 2502.08690 • Published • 43 -
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Paper • 2502.09560 • Published • 35 -
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Paper • 2502.09696 • Published • 43 -
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Paper • 2502.10248 • Published • 57 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 34 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 126 -
Learning Getting-Up Policies for Real-World Humanoid Robots
Paper • 2502.12152 • Published • 42 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 167 -
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Paper • 2502.11196 • Published • 23 -
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
Paper • 2502.10458 • Published • 38 -
HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
Paper • 2502.12148 • Published • 17 -
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Paper • 2502.11831 • Published • 20 -
video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
Paper • 2502.11775 • Published • 9 -
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Paper • 2502.08826 • Published • 17 -
ILIAS: Instance-Level Image retrieval At Scale
Paper • 2502.11748 • Published • 4 -
Soundwave: Less is More for Speech-Text Alignment in LLMs
Paper • 2502.12900 • Published • 86 -
Continuous Diffusion Model for Language Modeling
Paper • 2502.11564 • Published • 53 -
Phantom: Subject-consistent video generation via cross-modal alignment
Paper • 2502.11079 • Published • 59 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 58 -
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Paper • 2502.12115 • Published • 46 -
Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation
Paper • 2502.13145 • Published • 38 -
RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
Paper • 2502.12513 • Published • 16 -
Harnessing Vision Models for Time Series Analysis: A Survey
Paper • 2502.08869 • Published • 2 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 214 -
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
Paper • 2502.14296 • Published • 45 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 158 -
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper • 2502.14502 • Published • 91 -
LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models
Paper • 2502.14834 • Published • 24 -
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information
Paper • 2502.14258 • Published • 26 -
PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC
Paper • 2502.14282 • Published • 29 -
How to Get Your LLM to Generate Challenging Problems for Evaluation
Paper • 2502.14678 • Published • 18 -
Dynamic Concepts Personalization from Single Videos
Paper • 2502.14844 • Published • 16 -
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
Paper • 2502.14846 • Published • 14 -
NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization
Paper • 2502.14638 • Published • 11 -
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper • 2502.14802 • Published • 13 -
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
Paper • 2502.13063 • Published • 74 -
VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
Paper • 2502.12084 • Published • 34 -
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Paper • 2502.15007 • Published • 174 -
SurveyX: Academic Survey Automation via Large Language Models
Paper • 2502.14776 • Published • 100 -
PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data
Paper • 2502.14397 • Published • 41 -
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Paper • 2502.17157 • Published • 52 -
Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models
Paper • 2502.16033 • Published • 18 -
Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
Paper • 2502.16707 • Published • 13 -
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Paper • 2502.18411 • Published • 74 -
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60 -
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Paper • 2502.18449 • Published • 75 -
KV-Edit: Training-Free Image Editing for Precise Background Preservation
Paper • 2502.17363 • Published • 37 -
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
Paper • 2502.18364 • Published • 36 -
K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
Paper • 2502.18461 • Published • 17 -
Introducing Visual Perception Token into Multimodal Large Language Model
Paper • 2502.17425 • Published • 16 -
MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Paper • 2502.17422 • Published • 7 -
LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation
Paper • 2502.18302 • Published • 5 -
Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI
Paper • 2502.17092 • Published • 3 -
TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding
Paper • 2502.19400 • Published • 47 -
Towards an AI co-scientist
Paper • 2502.18864 • Published • 52 -
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Paper • 2502.19634 • Published • 63 -
UniTok: A Unified Tokenizer for Visual Generation and Understanding
Paper • 2502.20321 • Published • 30 -
Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
Paper • 2502.20172 • Published • 29 -
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models
Paper • 2502.20811 • Published • 3 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50 -
Tell me why: Visual foundation models as self-explainable classifiers
Paper • 2502.19577 • Published • 11 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22 -
MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing
Paper • 2502.21291 • Published • 5 -
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Paper • 2503.00808 • Published • 56 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 86 -
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Paper • 2503.01743 • Published • 89 -
Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions
Paper • 2503.00501 • Published • 12 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 140 -
DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles
Paper • 2503.03651 • Published • 16 -
UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface
Paper • 2503.01342 • Published • 8 -
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens
Paper • 2502.18890 • Published • 30 -
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Paper • 2503.02003 • Published • 48 -
Process-based Self-Rewarding Language Models
Paper • 2503.03746 • Published • 39 -
CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs
Paper • 2503.01378 • Published • 5 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 96 -
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
Paper • 2503.04724 • Published • 72 -
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
Paper • 2503.03983 • Published • 27 -
How to Steer LLM Latents for Hallucination Detection?
Paper • 2503.01917 • Published • 11 -
The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation
Paper • 2503.04606 • Published • 9 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 123 -
R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
Paper • 2503.05132 • Published • 57 -
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Paper • 2503.05179 • Published • 46 -
S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information
Paper • 2503.05085 • Published • 47 -
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning
Paper • 2503.05379 • Published • 38 -
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Paper • 2503.05639 • Published • 26 -
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
Paper • 2503.05638 • Published • 20 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 61 -
Automated Movie Generation via Multi-Agent CoT Planning
Paper • 2503.07314 • Published • 44 -
Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning
Paper • 2503.07002 • Published • 39 -
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Paper • 2503.06749 • Published • 31 -
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Paper • 2503.07920 • Published • 101 -
MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
Paper • 2503.05978 • Published • 36 -
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Paper • 2503.07536 • Published • 88 -
Video Action Differencing
Paper • 2503.07860 • Published • 33 -
UniF^2ace: Fine-grained Face Understanding and Generation with Unified Multimodal Models
Paper • 2503.08120 • Published • 32 -
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Paper • 2503.08625 • Published • 27 -
Implicit Reasoning in Transformers is Reasoning through Shortcuts
Paper • 2503.07604 • Published • 23 -
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
Paper • 2503.08619 • Published • 20 -
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Paper • 2503.07027 • Published • 29 -
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
Paper • 2503.04812 • Published • 17 -
Words or Vision: Do Vision-Language Models Have Blind Faith in Text?
Paper • 2503.02199 • Published • 8 -
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Paper • 2503.07703 • Published • 37 -
Gemini Embedding: Generalizable Embeddings from Gemini
Paper • 2503.07891 • Published • 45 -
OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models
Paper • 2503.08686 • Published • 19 -
CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing
Paper • 2503.06940 • Published • 11 -
Transformers without Normalization
Paper • 2503.10622 • Published • 170 -
Charting and Navigating Hugging Face's Model Atlas
Paper • 2503.10633 • Published • 93 -
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
Paper • 2503.10480 • Published • 56 -
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
Paper • 2503.10639 • Published • 53 -
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
Paper • 2503.10291 • Published • 36 -
4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models
Paper • 2503.10437 • Published • 34 -
CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
Paper • 2503.09662 • Published • 33 -
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
Paper • 2503.08677 • Published • 29 -
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Paper • 2503.10460 • Published • 30 -
GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
Paper • 2503.10596 • Published • 18 -
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Paper • 2503.10615 • Published • 17 -
Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
Paper • 2503.09642 • Published • 20 -
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Paper • 2503.07677 • Published • 86 -
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Paper • 2503.11647 • Published • 146 -
GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving
Paper • 2503.05689 • Published • 3 -
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 147 -
Large-scale Pre-training for Grounded Video Caption Generation
Paper • 2503.10781 • Published • 16 -
ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy
Paper • 2503.06542 • Published • 7 -
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
Paper • 2503.06053 • Published • 138 -
Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills
Paper • 2503.12533 • Published • 68 -
DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models
Paper • 2503.12885 • Published • 43 -
Edit Transfer: Learning Image Editing via Vision In-Context Relations
Paper • 2503.13327 • Published • 29 -
BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing
Paper • 2503.13434 • Published • 27 -
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
Paper • 2503.12937 • Published • 30 -
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
Paper • 2503.12605 • Published • 35 -
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 32 -
Aligning Multimodal LLM with Human Preference: A Survey
Paper • 2503.14504 • Published • 26 -
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
Paper • 2503.14492 • Published • 20 -
TULIP: Towards Unified Language-Image Pretraining
Paper • 2503.15485 • Published • 49 -
φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
Paper • 2503.13288 • Published • 51 -
Temporal Regularization Makes Your Video Generator Stronger
Paper • 2503.15417 • Published • 22 -
VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity
Paper • 2503.11557 • Published • 22 -
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Paper • 2503.16419 • Published • 77 -
Unleashing Vecset Diffusion Model for Fast Shape Generation
Paper • 2503.16302 • Published • 43 -
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
Paper • 2503.14487 • Published • 28 -
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
Paper • 2503.16365 • Published • 41 -
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Paper • 2503.16418 • Published • 36 -
Ultra-Resolution Adaptation with Ease
Paper • 2503.16322 • Published • 13 -
M3: 3D-Spatial MultiModal Memory
Paper • 2503.16413 • Published • 15 -
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
Paper • 2503.13834 • Published • 5 -
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
Paper • 2503.16057 • Published • 14 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 144 -
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 153 -
Impossible Videos
Paper • 2503.14378 • Published • 61 -
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Paper • 2503.16219 • Published • 52 -
Inside-Out: Hidden Factual Knowledge in LLMs
Paper • 2503.15299 • Published • 56 -
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper • 2503.15558 • Published • 50 -
Where do Large Vision-Language Models Look at when Answering Questions?
Paper • 2503.13891 • Published • 8 -
MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving
Paper • 2503.16905 • Published • 54 -
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Paper • 2503.17352 • Published • 24 -
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
Paper • 2503.16430 • Published • 34 -
When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO
Paper • 2503.16921 • Published • 6 -
From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
Paper • 2503.12821 • Published • 10 -
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
Paper • 2503.16549 • Published • 15 -
Why Do Multi-Agent LLM Systems Fail?
Paper • 2503.13657 • Published • 48 -
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Paper • 2503.16660 • Published • 72 -
Can Large Vision Language Models Read Maps Like a Human?
Paper • 2503.14607 • Published • 10 -
GAEA: A Geolocation Aware Conversational Model
Paper • 2503.16423 • Published • 6 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 119 -
Video-T1: Test-Time Scaling for Video Generation
Paper • 2503.18942 • Published • 90 -
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Paper • 2503.18892 • Published • 31 -
Aether: Geometric-Aware Unified World Modeling
Paper • 2503.18945 • Published • 28 -
Judge Anything: MLLM as a Judge Across Any Modality
Paper • 2503.17489 • Published • 23 -
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
Paper • 2503.18013 • Published • 20 -
Mind with Eyes: from Language Reasoning to Multimodal Reasoning
Paper • 2503.18071 • Published • 3 -
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 31 -
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
Paper • 2503.18931 • Published • 30 -
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
Paper • 2503.19325 • Published • 73 -
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
Paper • 2503.14905 • Published • 20 -
When Words Outperform Vision: VLMs Can Self-Improve Via Text-Only Training For Human-Centered Decision Making
Paper • 2503.16965 • Published • 4 -
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
Paper • 2503.19990 • Published • 35 -
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
Paper • 2503.19757 • Published • 51 -
GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
Paper • 2503.19480 • Published • 16 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 170 -
Wan: Open and Advanced Large-Scale Video Generative Models
Paper • 2503.20314 • Published • 59 -
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
Paper • 2503.20201 • Published • 48 -
Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
Paper • 2503.20198 • Published • 4 -
Video-R1: Reinforcing Video Reasoning in MLLMs
Paper • 2503.21776 • Published • 79 -
UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning
Paper • 2503.21620 • Published • 62 -
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Paper • 2503.21696 • Published • 23 -
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
Paper • 2503.21614 • Published • 43 -
OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning
Paper • 2503.16081 • Published • 28 -
Your ViT is Secretly an Image Segmentation Model
Paper • 2503.19108 • Published • 25 -
On Large Multimodal Models as Open-World Image Classifiers
Paper • 2503.21851 • Published • 5 -
TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes
Paper • 2503.23461 • Published • 94 -
Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation
Paper • 2503.24379 • Published • 76 -
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
Paper • 2503.24376 • Published • 38 -
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
Paper • 2504.00595 • Published • 37 -
Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?
Paper • 2504.00509 • Published • 24 -
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 139 -
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Paper • 2503.24290 • Published • 62 -
Unicorn: Text-Only Data Synthesis for Vision Language Model Training
Paper • 2503.22655 • Published • 39 -
TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
Paper • 2503.19901 • Published • 41 -
Expanding RL with Verifiable Rewards Across Diverse Domains
Paper • 2503.23829 • Published • 24 -
Multi-Token Attention
Paper • 2504.00927 • Published • 56 -
OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
Paper • 2503.22952 • Published • 17 -
Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
Paper • 2504.00557 • Published • 15 -
Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
Paper • 2504.00072 • Published • 6 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
Improved Visual-Spatial Reasoning via R1-Zero-Like Training
Paper • 2504.00883 • Published • 67 -
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance
Paper • 2504.01724 • Published • 68 -
AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
Paper • 2504.01014 • Published • 70 -
Towards Physically Plausible Video Generation via VLM Planning
Paper • 2503.23368 • Published • 40 -
Understanding R1-Zero-Like Training: A Critical Perspective
Paper • 2503.20783 • Published • 59 -
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
Paper • 2504.01934 • Published • 22 -
Articulated Kinematics Distillation from Video Diffusion Models
Paper • 2504.01204 • Published • 23 -
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
Paper • 2504.01308 • Published • 14 -
DASH: Detection and Assessment of Systematic Hallucinations of VLMs
Paper • 2503.23573 • Published • 12 -
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
Paper • 2503.18817 • Published • 3 -
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Paper • 2504.02826 • Published • 68 -
WikiVideo: Article Generation from Multiple Videos
Paper • 2504.00939 • Published • 37 -
GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
Paper • 2504.02782 • Published • 57 -
Inference-Time Scaling for Generalist Reward Modeling
Paper • 2504.02495 • Published • 58 -
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Paper • 2504.02587 • Published • 32 -
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
Paper • 2504.00502 • Published • 26 -
VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning
Paper • 2504.02949 • Published • 21 -
MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models
Paper • 2504.03641 • Published • 14 -
Slow-Fast Architecture for Video Multi-Modal Large Language Models
Paper • 2504.01328 • Published • 7 -
URECA: Unique Region Caption Anything
Paper • 2504.05305 • Published • 35 -
Concept Lancet: Image Editing with Compositional Representation Transplant
Paper • 2504.02828 • Published • 16 -
LiveVQA: Live Visual Knowledge Seeking
Paper • 2504.05288 • Published • 15 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 205 -
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
Paper • 2504.03151 • Published • 15 -
Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
Paper • 2504.05594 • Published • 11 -
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Paper • 2504.05599 • Published • 85 -
Rethinking Reflection in Pre-Training
Paper • 2504.04022 • Published • 80 -
Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
Paper • 2504.03193 • Published • 4 -
OmniSVG: A Unified Scalable Vector Graphics Generation Model
Paper • 2504.06263 • Published • 183 -
V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models
Paper • 2504.06148 • Published • 13 -
OmniCaptioner: One Captioner to Rule Them All
Paper • 2504.07089 • Published • 20 -
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
Paper • 2504.05541 • Published • 15 -
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Paper • 2504.06958 • Published • 13 -
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 137 -
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper • 2504.07128 • Published • 87 -
VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
Paper • 2504.07956 • Published • 46 -
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Paper • 2504.07960 • Published • 50 -
MM-IFEngine: Towards Multimodal Instruction Following
Paper • 2504.07957 • Published • 35 -
Scaling Laws for Native Multimodal Models Scaling Laws for Native Multimodal Models
Paper • 2504.07951 • Published • 30 -
Towards Visual Text Grounding of Multimodal Large Language Model
Paper • 2504.04974 • Published • 17 -
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Paper • 2504.08685 • Published • 130 -
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Paper • 2504.08736 • Published • 46 -
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
Paper • 2504.08388 • Published • 42 -
VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model
Paper • 2504.07615 • Published • 35 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 43 -
FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
Paper • 2504.09925 • Published • 39 -
Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability
Paper • 2504.08003 • Published • 49 -
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 306 -
Mavors: Multi-granularity Video Representation for Multimodal Large Language Model
Paper • 2504.10068 • Published • 30 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16 -
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Paper • 2504.09130 • Published • 12 -
Reasoning Models Can Be Effective Without Thinking
Paper • 2504.09858 • Published • 12 -
The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
Paper • 2504.10462 • Published • 15 -
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
Paper • 2504.10465 • Published • 27 -
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
Paper • 2504.13169 • Published • 39 -
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
Paper • 2504.13122 • Published • 20 -
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Paper • 2504.11468 • Published • 30 -
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
Paper • 2504.10342 • Published • 11 -
Multimodal Long Video Modeling Based on Temporal Dynamic Context
Paper • 2504.10443 • Published • 3 -
Summarization of Multimodal Presentations with Vision-Language Models: Study of the Effect of Modalities and Structure
Paper • 2504.10049 • Published • 2 -
ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
Paper • 2504.10514 • Published • 48 -
Perception Encoder: The best visual embeddings are not at the output of the network
Paper • 2504.13181 • Published • 35 -
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
Paper • 2504.13055 • Published • 19 -
DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
Paper • 2504.12364 • Published • 22 -
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Paper • 2504.13180 • Published • 20 -
Could Thinking Multilingually Empower LLM Reasoning?
Paper • 2504.11833 • Published • 29 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 139 -
UFO2: The Desktop AgentOS
Paper • 2504.14603 • Published • 29 -
LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark
Paper • 2504.13805 • Published • 11 -
Vidi: Large Multimodal Models for Video Understanding and Editing
Paper • 2504.15681 • Published • 14 -
LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
Paper • 2504.16030 • Published • 36 -
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
Paper • 2504.15280 • Published • 25 -
InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners
Paper • 2504.14239 • Published • 14 -
IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
Paper • 2504.15415 • Published • 23 -
Describe Anything: Detailed Localized Image and Video Captioning
Paper • 2504.16072 • Published • 64 -
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
Paper • 2504.15271 • Published • 67 -
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Paper • 2504.13157 • Published • 20 -
Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
Paper • 2504.14899 • Published • 20 -
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
Paper • 2504.15270 • Published • 9 -
BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation
Paper • 2504.14538 • Published • 30 -
Personalized Text-to-Image Generation with Auto-Regressive Models
Paper • 2504.13162 • Published • 18 -
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Paper • 2504.16080 • Published • 15 -
MR. Video: "MapReduce" is the Principle for Long Video Understanding
Paper • 2504.16082 • Published • 5 -
VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
Paper • 2504.15279 • Published • 78 -
DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning
Paper • 2504.14509 • Published • 53 -
Trillion 7B Technical Report
Paper • 2504.15431 • Published • 38 -
I-Con: A Unifying Framework for Representation Learning
Paper • 2504.16929 • Published • 30 -
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Paper • 2504.16074 • Published • 36 -
DreamO: A Unified Framework for Image Customization
Paper • 2504.16915 • Published • 24 -
Progressive Language-guided Visual Learning for Multi-Task Visual Grounding
Paper • 2504.16145 • Published • 2 -
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper • 2504.17192 • Published • 123 -
Step1X-Edit: A Practical Framework for General Image Editing
Paper • 2504.17761 • Published • 92 -
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
Paper • 2504.17502 • Published • 55 -
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
Paper • 2504.17432 • Published • 40 -
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation
Paper • 2504.17207 • Published • 30 -
Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models
Paper • 2504.17789 • Published • 23 -
DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
Paper • 2504.17040 • Published • 13 -
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Paper • 2504.16064 • Published • 14 -
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Paper • 2504.17343 • Published • 13 -
ViSMaP: Unsupervised Hour-long Video Summarisation by Meta-Prompting
Paper • 2504.15921 • Published • 7 -
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Paper • 2504.16656 • Published • 57 -
Towards Understanding Camera Motions in Any Video
Paper • 2504.15376 • Published • 155 -
Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark
Paper • 2504.16427 • Published • 18 -
DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
Paper • 2504.12080 • Published • 8 -
Contrastive Localized Language-Image Pre-Training
Paper • 2410.02746 • Published • 37 -
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
Paper • 2409.19291 • Published • 21 -
GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs
Paper • 2410.03645 • Published • 3 -
LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
Paper • 2504.19838 • Published • 23 -
RepText: Rendering Visual Text via Replicating
Paper • 2504.19724 • Published • 31 -
Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
Paper • 2504.18589 • Published • 13 -
Clinical knowledge in LLMs does not translate to human interactions
Paper • 2504.18919 • Published • 26 -
SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
Paper • 2504.19162 • Published • 18 -
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
Paper • 2504.16083 • Published • 8 -
NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
Paper • 2504.19854 • Published • 7 -
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Paper • 2504.20571 • Published • 98 -
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 -
UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities
Paper • 2504.20734 • Published • 62 -
YoChameleon: Personalized Vision and Language Generation
Paper • 2504.20998 • Published • 12 -
X-Fusion: Introducing New Modality to Frozen Large Language Models
Paper • 2504.20996 • Published • 13 -
A Review of 3D Object Detection with Vision-Language Models
Paper • 2504.18738 • Published • 2 -
Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math
Paper • 2504.21233 • Published • 49 -
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
Paper • 2505.00551 • Published • 36 -
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning
Paper • 2504.21850 • Published • 27 -
ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction
Paper • 2504.21855 • Published • 13 -
A Survey of Interactive Generative Video
Paper • 2504.21853 • Published • 46 -
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
Paper • 2505.00703 • Published • 44 -
PixelHacker: Image Inpainting with Structural and Semantic Consistency
Paper • 2504.20438 • Published • 44 -
Improving Editability in Image Generation with Layer-wise Memory
Paper • 2505.01079 • Published • 29 -
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
Paper • 2505.02707 • Published • 85 -
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 81 -
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
Paper • 2505.02835 • Published • 28 -
Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction
Paper • 2505.02471 • Published • 15 -
SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing
Paper • 2505.02370 • Published • 14 -
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Paper • 2505.01441 • Published • 39 -
LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Paper • 2505.02625 • Published • 23 -
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
Paper • 2504.21650 • Published • 16 -
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper • 2505.03318 • Published • 92 -
OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents
Paper • 2505.03570 • Published • 8 -
OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution
Paper • 2505.04606 • Published • 9 -
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
Paper • 2505.04601 • Published • 29 -
Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models
Paper • 2505.03821 • Published • 24 -
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Paper • 2505.04512 • Published • 36 -
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Paper • 2505.04588 • Published • 65 -
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
Paper • 2505.02567 • Published • 80 -
Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation
Paper • 2505.02836 • Published • 8 -
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Paper • 2505.03739 • Published • 9 -
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Paper • 2505.04921 • Published • 186 -
On Path to Multimodal Generalist: General-Level and General-Bench
Paper • 2505.04620 • Published • 82 -
Flow-GRPO: Training Flow Matching Models via Online RL
Paper • 2505.05470 • Published • 88 -
FG-CLIP: Fine-Grained Visual and Textual Alignment
Paper • 2505.05071 • Published • 18 -
X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
Paper • 2505.03981 • Published • 15 -
Vision-Language-Action Models: Concepts, Progress, Applications and Challenges
Paper • 2505.04769 • Published • 10 -
Bielik v3 Small: Technical Report
Paper • 2505.02550 • Published • 68 -
Bielik 11B v2 Technical Report
Paper • 2505.02410 • Published • 54 -
Seed1.5-VL Technical Report
Paper • 2505.07062 • Published • 155 -
Unified Continuous Generative Models
Paper • 2505.07447 • Published • 42 -
DanceGRPO: Unleashing GRPO on Visual Generation
Paper • 2505.07818 • Published • 32 -
Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
Paper • 2505.07263 • Published • 30 -
H^{3}DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning
Paper • 2505.07819 • Published • 5 -
MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
Paper • 2505.06176 • Published • 12 -
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
Paper • 2505.07233 • Published • 8 -
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
Paper • 2505.07916 • Published • 134 -
Fast Text-to-Audio Generation with Adversarial Post-Training
Paper • 2505.08175 • Published • 25 -
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
Paper • 2505.05464 • Published • 11 -
Aya Vision: Advancing the Frontier of Multilingual Multimodality
Paper • 2505.08751 • Published • 13 -
SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation
Paper • 2505.08665 • Published • 5 -
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Paper • 2505.09568 • Published • 99 -
Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures
Paper • 2505.09343 • Published • 76 -
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning
Paper • 2505.10557 • Published • 47 -
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
Paper • 2505.04410 • Published • 44 -
WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
Paper • 2505.09558 • Published • 10 -
Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?
Paper • 2505.09439 • Published • 10 -
VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models
Paper • 2505.08455 • Published • 5 -
Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA
Paper • 2505.06356 • Published • 3 -
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 120 -
OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning
Paper • 2505.08617 • Published • 42 -
WorldPM: Scaling Human Preference Modeling
Paper • 2505.10527 • Published • 34 -
End-to-End Vision Tokenizer Tuning
Paper • 2505.10562 • Published • 22 -
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
Paper • 2505.10046 • Published • 9 -
AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
Paper • 2505.09926 • Published • 6 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 334 -
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
Paper • 2505.10610 • Published • 55 -
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
Paper • 2505.11049 • Published • 61 -
Visual Planning: Let's Think Only with Images
Paper • 2505.11409 • Published • 57 -
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via texttt{D}ual-texttt{H}ead texttt{O}ptimization
Paper • 2505.07675 • Published • 21 -
Chain-of-Model Learning for Language Model
Paper • 2505.11820 • Published • 121 -
AdaptThink: Reasoning Models Can Learn When to Think
Paper • 2505.13417 • Published • 83 -
Model Merging in Pre-training of Large Language Models
Paper • 2505.12082 • Published • 40 -
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images
Paper • 2505.07704 • Published • 29 -
Faster Video Diffusion with Trainable Sparse Attention
Paper • 2505.13389 • Published • 38 -
ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models
Paper • 2505.13180 • Published • 13 -
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
Paper • 2505.12081 • Published • 18 -
R3: Robust Rubric-Agnostic Reward Models
Paper • 2505.13388 • Published • 11 -
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
Paper • 2505.13181 • Published • 9 -
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
Paper • 2505.12781 • Published • 2 -
Emerging Properties in Unified Multimodal Pretraining
Paper • 2505.14683 • Published • 133 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 37 -
Visual Agentic Reinforcement Fine-Tuning
Paper • 2505.14246 • Published • 32 -
VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
Paper • 2505.14460 • Published • 33 -
Think Only When You Need with Large Hybrid-Reasoning Models
Paper • 2505.14631 • Published • 20 -
Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
Paper • 2505.14677 • Published • 15 -
Hunyuan-Game: Industrial-grade Intelligent Game Creation Model
Paper • 2505.14135 • Published • 16 -
VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation
Paper • 2505.14640 • Published • 16 -
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Paper • 2505.14681 • Published • 10 -
Visual Instruction Bottleneck Tuning
Paper • 2505.13946 • Published • 10 -
Not All Correct Answers Are Equal: Why Your Distillation Source Matters
Paper • 2505.14464 • Published • 10 -
Lessons from Defending Gemini Against Indirect Prompt Injections
Paper • 2505.14534 • Published • 8 -
The Hallucination Tax of Reinforcement Finetuning
Paper • 2505.13988 • Published • 8 -
Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence
Paper • 2505.10176 • Published • 3 -
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Paper • 2505.15277 • Published • 104 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 98 -
UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
Paper • 2505.14231 • Published • 53 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 55 -
Vid2World: Crafting Video Diffusion Models to Interactive World Models
Paper • 2505.14357 • Published • 27 -
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
Paper • 2505.15400 • Published • 23 -
lmgame-Bench: How Good are LLMs at Playing Games?
Paper • 2505.15146 • Published • 20 -
IA-T2I: Internet-Augmented Text-to-Image Generation
Paper • 2505.15779 • Published • 14 -
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
Paper • 2505.15210 • Published • 18 -
RLVR-World: Training World Models with Reinforcement Learning
Paper • 2505.13934 • Published • 16 -
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
Paper • 2505.15776 • Published • 11 -
HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation
Paper • 2505.11454 • Published • 5 -
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
Paper • 2505.16175 • Published • 42 -
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
Paper • 2505.16933 • Published • 34 -
GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
Paper • 2505.17022 • Published • 27 -
Risk-Averse Reinforcement Learning with Itakura-Saito Loss
Paper • 2505.16925 • Published • 26 -
Understanding Generative AI Capabilities in Everyday Image Editing Tasks
Paper • 2505.16181 • Published • 24 -
Training-Free Efficient Video Generation via Dynamic Token Carving
Paper • 2505.16864 • Published • 24 -
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding
Paper • 2505.16990 • Published • 22 -
VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
Paper • 2505.15952 • Published • 20 -
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
Paper • 2505.17018 • Published • 15 -
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Paper • 2505.16916 • Published • 17 -
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
Paper • 2505.16421 • Published • 19 -
LaViDa: A Large Diffusion Language Model for Multimodal Understanding
Paper • 2505.16839 • Published • 13 -
GRIT: Teaching MLLMs to Think with Images
Paper • 2505.15879 • Published • 13 -
Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
Paper • 2505.16854 • Published • 11 -
OViP: Online Vision-Language Preference Learning
Paper • 2505.15963 • Published • 9 -
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
Paper • 2505.17015 • Published • 9 -
VLM-R^3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
Paper • 2505.16192 • Published • 12 -
Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets
Paper • 2505.15517 • Published • 4 -
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
Paper • 2505.15865 • Published • 5 -
RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
Paper • 2505.14462 • Published • 4 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
Paper • 2505.17558 • Published • 15 -
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
Paper • 2505.16211 • Published • 18 -
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
Paper • 2505.15389 • Published • 8 -
Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
Paper • 2505.18536 • Published • 18 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88 -
Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models
Paper • 2505.17225 • Published • 64 -
QwenLong-CPRS: Towards infty-LLMs with Dynamic Context Optimization
Paper • 2505.18092 • Published • 43 -
RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs
Paper • 2505.16770 • Published • 12 -
Interactive Post-Training for Vision-Language-Action Models
Paper • 2505.17016 • Published • 6 -
G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
Paper • 2505.13426 • Published • 13 -
Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
Paper • 2505.19706 • Published • 3 -
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
Paper • 2505.17540 • Published • 7 -
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Paper • 2505.19147 • Published • 145 -
Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps
Paper • 2505.18675 • Published • 26 -
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
Paper • 2505.20256 • Published • 19 -
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
Paper • 2505.20046 • Published • 18 -
Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models
Paper • 2505.20152 • Published • 11 -
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Paper • 2505.19640 • Published • 15 -
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
Paper • 2505.10887 • Published • 10 -
STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs
Paper • 2505.15804 • Published • 10 -
Jodi: Unification of Visual Generation and Understanding via Joint Modeling
Paper • 2505.19084 • Published • 20 -
Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey
Paper • 2505.15957 • Published • 3 -
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
Paper • 2505.20236 • Published • 3 -
Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
Paper • 2505.14071 • Published • 1 -
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Paper • 2505.21497 • Published • 109 -
Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
Paper • 2505.21374 • Published • 28 -
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
Paper • 2505.21333 • Published • 38 -
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Paper • 2505.21327 • Published • 83 -
MMMR: Benchmarking Massive Multi-Modal Reasoning Tasks
Paper • 2505.16459 • Published • 45 -
SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning
Paper • 2505.19099 • Published • 7 -
Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
Paper • 2505.21457 • Published • 16 -
UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents
Paper • 2505.21496 • Published • 38 -
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
Paper • 2505.21500 • Published • 13 -
ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
Paper • 2505.19897 • Published • 104 -
MLLMs are Deeply Affected by Modality Bias
Paper • 2505.18657 • Published • 5 -
Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO
Paper • 2505.22453 • Published • 46 -
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
Paper • 2505.22334 • Published • 36 -
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Paper • 2505.22617 • Published • 131 -
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
Paper • 2505.21600 • Published • 71 -
Skywork Open Reasoner 1 Technical Report
Paper • 2505.22312 • Published • 54 -
Sherlock: Self-Correcting Reasoning in Vision-Language Models
Paper • 2505.22651 • Published • 48 -
Fostering Video Reasoning via Next-Event Prediction
Paper • 2505.22457 • Published • 29 -
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
Paper • 2505.22019 • Published • 11 -
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
Paper • 2505.22613 • Published • 9 -
Zero-Shot Vision Encoder Grafting via LLM Surrogates
Paper • 2505.22664 • Published • 7 -
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
Paper • 2505.20298 • Published • 9 -
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Paper • 2505.23747 • Published • 69 -
ZeroGUI: Automating Online GUI Learning at Zero Human Cost
Paper • 2505.23762 • Published • 45 -
The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason
Paper • 2505.22653 • Published • 43 -
VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
Paper • 2505.23693 • Published • 53 -
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Paper • 2505.23359 • Published • 38 -
To Trust Or Not To Trust Your Vision-Language Model's Prediction
Paper • 2505.23745 • Published • 4 -
Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
Paper • 2505.22943 • Published • 3 -
FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding
Paper • 2505.17330 • Published • 22 -
HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models
Paper • 2505.20444 • Published • 5 -
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
Paper • 2505.22914 • Published • 37 -
Are Reasoning Models More Prone to Hallucination?
Paper • 2505.23646 • Published • 24 -
Multi-Domain Explainability of Preferences
Paper • 2505.20088 • Published • 20 -
REOrdering Patches Improves Vision Models
Paper • 2505.23751 • Published • 15 -
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape
Paper • 2505.22918 • Published • 6 -
Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint
Paper • 2505.23759 • Published • 5 -
A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models
Paper • 2505.19286 • Published • 3 -
Grounded Reinforcement Learning for Visual Reasoning
Paper • 2505.23678 • Published • 2 -
Time Blindness: Why Video-Language Models Can't See What Humans Can?
Paper • 2505.24867 • Published • 82 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 143 -
Large Language Models for Data Synthesis
Paper • 2505.14752 • Published • 49 -
Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation
Paper • 2505.18842 • Published • 36 -
ViStoryBench: Comprehensive Benchmark Suite for Story Visualization
Paper • 2505.24862 • Published • 30 -
DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models
Paper • 2505.24025 • Published • 27 -
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Paper • 2505.24871 • Published • 23 -
Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
Paper • 2505.24878 • Published • 23 -
Vision Language Models are Biased
Paper • 2505.23941 • Published • 23 -
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Paper • 2505.21523 • Published • 13 -
Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models
Paper • 2505.20873 • Published • 9 -
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
Paper • 2505.24875 • Published • 10 -
un^2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
Paper • 2505.24517 • Published • 5 -
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper • 2506.01844 • Published • 151 -
Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models
Paper • 2506.00996 • Published • 40 -
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles
Paper • 2505.23590 • Published • 25 -
LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks
Paper • 2506.00411 • Published • 31 -
SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
Paper • 2506.01713 • Published • 48 -
EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models
Paper • 2506.01667 • Published • 21 -
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
Paper • 2505.23977 • Published • 10 -
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
Paper • 2505.24625 • Published • 9 -
OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
Paper • 2505.21724 • Published • 5 -
Aligning VLM Assistants with Personalized Situated Cognition
Paper • 2506.00930 • Published • 2 -
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
Paper • 2506.01674 • Published • 28 -
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
Paper • 2506.02096 • Published • 52 -
VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments
Paper • 2506.02387 • Published • 58 -
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Paper • 2506.03147 • Published • 58 -
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs
Paper • 2505.24120 • Published • 49 -
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
Paper • 2506.03135 • Published • 40 -
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
Paper • 2506.00123 • Published • 35 -
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Paper • 2506.03143 • Published • 53 -
FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens
Paper • 2506.03096 • Published • 4 -
TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
Paper • 2505.24500 • Published • 12 -
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Paper • 2506.04207 • Published • 48 -
MiMo-VL Technical Report
Paper • 2506.03569 • Published • 80 -
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
Paper • 2506.04141 • Published • 29 -
Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
Paper • 2506.03525 • Published • 6 -
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
Paper • 2506.04308 • Published • 43 -
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Paper • 2506.05176 • Published • 79 -
EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
Paper • 2506.05287 • Published • 14 -
SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
Paper • 2506.05344 • Published • 17 -
FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion
Paper • 2506.01111 • Published • 31 -
Is Extending Modality The Right Path Towards Omni-Modality?
Paper • 2506.01872 • Published • 24 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 263 -
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Paper • 2506.06205 • Published • 30 -
Image Reconstruction as a Tool for Feature Analysis
Paper • 2506.07803 • Published • 29 -
Bootstrapping World Models from Dynamics Models in Multimodal Foundation Models
Paper • 2506.06006 • Published • 14 -
Vision Transformers Don't Need Trained Registers
Paper • 2506.08010 • Published • 22 -
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 113 -
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Paper • 2506.08887 • Published • 4 -
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Paper • 2506.09040 • Published • 34 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 107 -
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models
Paper • 2506.04688 • Published • 3 -
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 133 -
Hidden in plain sight: VLMs overlook their visual representations
Paper • 2506.08008 • Published • 7 -
Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
Paper • 2506.09736 • Published • 9 -
VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos
Paper • 2506.10857 • Published • 30 -
Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts
Paper • 2506.10357 • Published • 21 -
SAFE: Multitask Failure Detection for Vision-Language-Action Models
Paper • 2506.09937 • Published • 9 -
Magistral
Paper • 2506.10910 • Published • 66 -
Ming-Omni: A Unified Multimodal Model for Perception and Generation
Paper • 2506.09344 • Published • 31 -
VideoDeepResearch: Long Video Understanding With Agentic Tool Using
Paper • 2506.10821 • Published • 19 -
UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
Paper • 2506.09952 • Published • 6 -
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Paper • 2506.11924 • Published • 34 -
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Paper • 2506.10128 • Published • 22 -
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 273 -
BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
Paper • 2506.07961 • Published • 11 -
Discrete Diffusion in Large Language and Multimodal Models: A Survey
Paper • 2506.13759 • Published • 43 -
Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
Paper • 2506.13642 • Published • 27 -
VGR: Visual Grounded Reasoning
Paper • 2506.11991 • Published • 20 -
AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
Paper • 2506.06962 • Published • 28 -
DoTA-RAG: Dynamic of Thought Aggregation RAG
Paper • 2506.12571 • Published • 50 -
Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning
Paper • 2506.13654 • Published • 43 -
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
Paper • 2506.10521 • Published • 73 -
LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
Paper • 2506.14429 • Published • 44 -
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
Paper • 2506.10100 • Published • 10 -
VideoMolmo: Spatio-Temporal Grounding Meets Pointing
Paper • 2506.05336 • Published • 9 -
MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation
Paper • 2506.14028 • Published • 93 -
Sekai: A Video Dataset towards World Exploration
Paper • 2506.15675 • Published • 66 -
ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs
Paper • 2506.15211 • Published • 39 -
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models
Paper • 2506.15681 • Published • 42 -
SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification
Paper • 2506.15569 • Published • 12 -
FedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models
Paper • 2506.14824 • Published • 8 -
CoMemo: LVLMs Need Image Context with Image Memory
Paper • 2506.06279 • Published • 8 -
Show-o2: Improved Native Unified Multimodal Models
Paper • 2506.15564 • Published • 29 -
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Paper • 2506.16035 • Published • 89 -
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
Paper • 2506.16054 • Published • 60 -
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
Paper • 2506.17201 • Published • 57 -
Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
Paper • 2506.17218 • Published • 29 -
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Paper • 2506.17202 • Published • 10 -
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Paper • 2506.15442 • Published • 15 -
InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Paper • 2506.15745 • Published • 14 -
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation
Paper • 2506.17113 • Published • 5 -
OmniGen2: Exploration to Advanced Multimodal Generation
Paper • 2506.18871 • Published • 78 -
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
Paper • 2506.18898 • Published • 34 -
From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models
Paper • 2506.09930 • Published • 8 -
USAD: Universal Speech and Audio Representation via Distillation
Paper • 2506.18843 • Published • 12 -
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
Paper • 2506.19848 • Published • 26 -
Unified Vision-Language-Action Model
Paper • 2506.19850 • Published • 27 -
GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
Paper • 2506.16141 • Published • 27 -
Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset
Paper • 2506.18851 • Published • 30 -
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
Paper • 2506.18095 • Published • 66 -
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Paper • 2506.20512 • Published • 47 -
MMSearch-R1: Incentivizing LMMs to Search
Paper • 2506.20670 • Published • 64 -
WorldVLA: Towards Autoregressive Action World Model
Paper • 2506.21539 • Published • 40 -
FaSTA^*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
Paper • 2506.20911 • Published • 41 -
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
Paper • 2506.21862 • Published • 36 -
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
Paper • 2506.21656 • Published • 16 -
MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
Paper • 2506.22434 • Published • 10 -
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
Paper • 2506.17450 • Published • 64 -
ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
Paper • 2506.21356 • Published • 22 -
Audio-FLAN: A Preliminary Release
Paper • 2502.16584 • Published • 36 -
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
Paper • 2506.21876 • Published • 28 -
Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?
Paper • 2506.17417 • Published • 11 -
Ovis-U1 Technical Report
Paper • 2506.23044 • Published • 61 -
Listener-Rewarded Thinking in VLMs for Image Preferences
Paper • 2506.22832 • Published • 23 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 251 -
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
Paper • 2506.23115 • Published • 36 -
MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models
Paper • 2506.23009 • Published • 11 -
Kwai Keye-VL Technical Report
Paper • 2507.01949 • Published • 131 -
A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
Paper • 2507.01925 • Published • 39 -
LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
Paper • 2507.01945 • Published • 76 -
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
Paper • 2506.23918 • Published • 90 -
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Paper • 2507.01955 • Published • 36 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 159 -
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
Paper • 2507.04447 • Published • 45 -
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
Paper • 2507.03483 • Published • 24 -
ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation
Paper • 2507.04952 • Published • 11 -
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Paper • 2507.04590 • Published • 17 -
Perception-Aware Policy Optimization for Multimodal Reasoning
Paper • 2507.06448 • Published • 48 -
4KAgent: Agentic Any Image to 4K Super-Resolution
Paper • 2507.07105 • Published • 106 -
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
Paper • 2507.07095 • Published • 56 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 160 -
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
Paper • 2507.07999 • Published • 50 -
PyVision: Agentic Vision with Dynamic Tooling
Paper • 2507.07998 • Published • 33 -
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Paper • 2507.07990 • Published • 46 -
A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality
Paper • 2507.07202 • Published • 25 -
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Paper • 2507.05255 • Published • 75 -
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
Paper • 2507.08441 • Published • 62 -
Robust Multimodal Large Language Models Against Modality Conflict
Paper • 2507.07151 • Published • 6 -
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Paper • 2507.06261 • Published • 67 -
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
Paper • 2507.08128 • Published • 13 -
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
Paper • 2507.09862 • Published • 51 -
Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
Paper • 2507.07104 • Published • 46 -
Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers
Paper • 2507.10787 • Published • 13 -
UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks
Paper • 2507.11336 • Published • 7 -
MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding
Paper • 2507.12463 • Published • 27 -
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Paper • 2507.13348 • Published • 79 -
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
Paper • 2507.13344 • Published • 59 -
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
Paper • 2507.12841 • Published • 42 -
π^3: Scalable Permutation-Equivariant Visual Geometry Learning
Paper • 2507.13347 • Published • 66 -
Automating Steering for Safe Multimodal Large Language Models
Paper • 2507.13255 • Published • 4 -
Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models
Paper • 2507.12566 • Published • 15 -
Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Paper • 2507.14137 • Published • 35 -
GUI-G^2: Gaussian Reward Modeling for GUI Grounding
Paper • 2507.15846 • Published • 133 -
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
Paper • 2507.15597 • Published • 34 -
Latent Denoising Makes Good Visual Tokenizers
Paper • 2507.15856 • Published • 12 -
Step-Audio 2 Technical Report
Paper • 2507.16632 • Published • 74 -
Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
Paper • 2507.16746 • Published • 34 -
Semi-off-Policy Reinforcement Learning for Vision-Language Slow-thinking Reasoning
Paper • 2507.16814 • Published • 21 -
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
Paper • 2507.16815 • Published • 42 -
Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory
Paper • 2507.16713 • Published • 21 -
Pixels, Patterns, but No Poetry: To See The World like Humans
Paper • 2507.16863 • Published • 69 -
Yume: An Interactive World Generation Model
Paper • 2507.17744 • Published • 91 -
Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed
Paper • 2507.16880 • Published • 7 -
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Paper • 2507.18537 • Published • 18 -
Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows
Paper • 2507.18405 • Published • 5 -
Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI
Paper • 2507.10510 • Published • 5 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 68 -
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios
Paper • 2507.20198 • Published • 28 -
ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts
Paper • 2507.20939 • Published • 57 -
Region-based Cluster Discrimination for Visual Representation Learning
Paper • 2507.20025 • Published • 19 -
Reconstructing 4D Spatial Intelligence: A Survey
Paper • 2507.21045 • Published • 38 -
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Paper • 2507.21033 • Published • 23 -
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
Paper • 2507.22058 • Published • 40 -
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Paper • 2507.21183 • Published • 15 -
ForCenNet: Foreground-Centric Network for Document Image Rectification
Paper • 2507.19804 • Published • 12 -
Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
Paper • 2507.22886 • Published • 10 -
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
Paper • 2507.21809 • Published • 140 -
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Paper • 2507.22607 • Published • 47 -
Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents
Paper • 2507.23698 • Published • 11 -
Phi-Ground Tech Report: Advancing Perception in GUI Grounding
Paper • 2507.23779 • Published • 45 -
C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations
Paper • 2507.22968 • Published • 25 -
villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
Paper • 2507.23682 • Published • 24 -
Multimodal Referring Segmentation: A Survey
Paper • 2508.00265 • Published • 9 -
PixNerd: Pixel Neural Field Diffusion
Paper • 2507.23268 • Published • 52 -
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 272 -
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Paper • 2508.02317 • Published • 22 -
InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation
Paper • 2507.17520 • Published • 15 -
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Paper • 2508.01548 • Published • 14 -
Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation
Paper • 2508.03320 • Published • 63 -
LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
Paper • 2508.03694 • Published • 52 -
Representation Shift: Unifying Token Compression with FlashAttention
Paper • 2508.00367 • Published • 16 -
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Paper • 2508.03686 • Published • 39 -
The Promise of RL for Autoregressive Image Editing
Paper • 2508.01119 • Published • 11 -
HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
Paper • 2508.02629 • Published • 6 -
LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
Paper • 2508.00477 • Published • 11 -
ChartCap: Mitigating Hallucination of Dense Chart Captioning
Paper • 2508.03164 • Published • 7 -
Sotopia-RL: Reward Design for Social Intelligence
Paper • 2508.03905 • Published • 23 -
HPSv3: Towards Wide-Spectrum Human Preference Score
Paper • 2508.03789 • Published • 20 -
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Paper • 2508.05629 • Published • 184 -
Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
Paper • 2508.04280 • Published • 35 -
CM^3: Calibrating Multimodal Recommendation
Paper • 2508.01226 • Published • 1 -
DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
Paper • 2508.05405 • Published • 64 -
Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability
Paper • 2508.04017 • Published • 11 -
Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Paper • 2508.05547 • Published • 11 -
Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
Paper • 2508.04825 • Published • 60 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 30 -
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
Paper • 2508.05748 • Published • 141 -
Adversarial Video Promotion Against Text-to-Video Retrieval
Paper • 2508.06964 • Published • 9 -
MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models
Paper • 2508.06009 • Published • 16 -
Story2Board: A Training-Free Approach for Expressive Storyboard Generation
Paper • 2508.09983 • Published • 70 -
Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation
Paper • 2508.07901 • Published • 40 -
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Paper • 2508.09736 • Published • 58 -
IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding
Paper • 2508.09456 • Published • 8 -
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
Paper • 2508.10711 • Published • 145 -
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning
Paper • 2508.10433 • Published • 144 -
HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
Paper • 2508.10576 • Published • 8 -
Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
Paper • 2508.10637 • Published • 8 -
Thyme: Think Beyond Images
Paper • 2508.11630 • Published • 81 -
DINOv3
Paper • 2508.10104 • Published • 298 -
Controlling Multimodal LLMs via Reward-guided Decoding
Paper • 2508.11616 • Published • 7 -
Ovis2.5 Technical Report
Paper • 2508.11737 • Published • 112 -
Next Visual Granularity Generation
Paper • 2508.12811 • Published • 49 -
OmniTry: Virtual Try-On Anything without Masks
Paper • 2508.13632 • Published • 15 -
MultiRef: Controllable Image Generation with Multiple Visual References
Paper • 2508.06905 • Published • 21 -
Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer
Paper • 2508.09131 • Published • 16 -
RynnEC: Bringing MLLMs into Embodied World
Paper • 2508.14160 • Published • 20 -
Intern-S1: A Scientific Multimodal Foundation Model
Paper • 2508.15763 • Published • 269 -
Waver: Wave Your Way to Lifelike Video Generation
Paper • 2508.15761 • Published • 36 -
Visual Autoregressive Modeling for Instruction-Guided Image Editing
Paper • 2508.15772 • Published • 9 -
When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Paper • 2508.15641 • Published • 4 -
LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model
Paper • 2508.15418 • Published • 8 -
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 160 -
PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
Paper • 2508.17188 • Published • 17 -
OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation
Paper • 2508.19209 • Published • 42 -
Autoregressive Universal Video Segmentation Model
Paper • 2508.19242 • Published • 29 -
MovieCORE: COgnitive REasoning in Movies
Paper • 2508.19026 • Published • 7 -
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 214 -
MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
Paper • 2508.18264 • Published • 25 -
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Paper • 2508.17298 • Published • 4 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 90 -
Self-Rewarding Vision-Language Model via Reasoning Decomposition
Paper • 2508.19652 • Published • 84 -
Mixture of Contexts for Long Video Generation
Paper • 2508.21058 • Published • 35 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
Beyond Transcription: Mechanistic Interpretability in ASR
Paper • 2508.15882 • Published • 87 -
MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation
Paper • 2508.19320 • Published • 29 -
SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
Paper • 2508.18179 • Published • 9 -
CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
Paper • 2508.21046 • Published • 9 -
OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
Paper • 2508.21066 • Published • 13 -
Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
Paper • 2508.17502 • Published • 1 -
AudioStory: Generating Long-Form Narrative Audio with Large Language Models
Paper • 2508.20088 • Published • 21 -
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Paper • 2508.21113 • Published • 110 -
EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper • 2508.21112 • Published • 77 -
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
Paper • 2509.02544 • Published • 125 -
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion
Paper • 2509.01215 • Published • 51 -
ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
Paper • 2508.21496 • Published • 55 -
Kwai Keye-VL 1.5 Technical Report
Paper • 2509.01563 • Published • 38 -
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
Paper • 2509.01644 • Published • 34 -
Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
Paper • 2508.20470 • Published • 75 -
Planning with Reasoning using Vision Language World Model
Paper • 2509.02722 • Published • 24 -
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Paper • 2509.03403 • Published • 23 -
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth
Paper • 2509.03867 • Published • 211 -
Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
Paper • 2508.20478 • Published • 18 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 196 -
WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
Paper • 2509.04744 • Published • 12 -
LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation
Paper • 2509.05263 • Published • 11 -
Reinforced Visual Perception with Tools
Paper • 2509.01656 • Published • 32 -
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
Paper • 2509.06461 • Published • 20 -
UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
Paper • 2509.06155 • Published • 14 -
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
Paper • 2509.03516 • Published • 12 -
D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning
Paper • 2509.06771 • Published • 6 -
Visual Representation Alignment for Multimodal Large Language Models
Paper • 2509.07979 • Published • 84 -
Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
Paper • 2509.07969 • Published • 59 -
Reconstruction Alignment Improves Unified Multimodal Models
Paper • 2509.07295 • Published • 40 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 190 -
RewardDance: Reward Scaling in Visual Generation
Paper • 2509.08826 • Published • 73 -
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Paper • 2509.09372 • Published • 246 -
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Paper • 2509.08519 • Published • 128 -
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
Paper • 2509.09674 • Published • 80 -
Can Understanding and Generation Truly Benefit Together -- or Just Coexist?
Paper • 2509.09666 • Published • 34 -
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
Paper • 2509.09595 • Published • 48 -
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Paper • 2509.09676 • Published • 35 -
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
Paper • 2509.09677 • Published • 35 -
Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
Paper • 2509.11452 • Published • 14 -
PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits
Paper • 2509.11362 • Published • 5 -
Lost in Embeddings: Information Loss in Vision-Language Models
Paper • 2509.11986 • Published • 29 -
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Paper • 2509.12201 • Published • 106 -
UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning
Paper • 2509.11543 • Published • 49 -
LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
Paper • 2509.12203 • Published • 20 -
Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
Paper • 2509.06079 • Published • 6 -
3D Aware Region Prompted Vision Language Model
Paper • 2509.13317 • Published • 14 -
Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation
Paper • 2509.12815 • Published • 40 -
Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
Paper • 2509.12132 • Published • 7 -
Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding
Paper • 2509.11866 • Published • 2 -
Scaling Agents via Continual Pre-training
Paper • 2509.13310 • Published • 117 -
SAIL-VL2 Technical Report
Paper • 2509.14033 • Published • 44 -
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 116 -
WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
Paper • 2509.15130 • Published • 30 -
MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
Paper • 2509.14638 • Published • 13 -
AToken: A Unified Tokenizer for Vision
Paper • 2509.14476 • Published • 36 -
Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
Paper • 2509.15178 • Published • 6 -
PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
Paper • 2509.12989 • Published • 28 -
LLM-I: LLMs are Naturally Interleaved Multimodal Creators
Paper • 2509.13642 • Published • 9 -
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper • 2509.16197 • Published • 58 -
Lynx: Towards High-Fidelity Personalized Video Generation
Paper • 2509.15496 • Published • 13 -
BaseReward: A Strong Baseline for Multimodal Reward Model
Paper • 2509.16127 • Published • 21 -
BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
Paper • 2509.15566 • Published • 14 -
Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents
Paper • 2509.15233 • Published • 2 -
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Paper • 2509.15937 • Published • 20 -
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Paper • 2509.17627 • Published • 66 -
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
Paper • 2509.18056 • Published • 27 -
Qwen3-Omni Technical Report
Paper • 2509.17765 • Published • 149 -
GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning
Paper • 2509.17437 • Published • 17 -
VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
Paper • 2509.17985 • Published • 26 -
ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
Paper • 2509.17818 • Published • 8 -
MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
Paper • 2509.18095 • Published • 9 -
When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
Paper • 2509.16633 • Published • 2 -
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
Paper • 2509.18154 • Published • 55 -
Reinforcement Learning on Pre-Training Data
Paper • 2509.19249 • Published • 67 -
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Paper • 2509.19296 • Published • 25 -
Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
Paper • 2509.18824 • Published • 23 -
UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
Paper • 2509.18094 • Published • 4 -
MAPO: Mixed Advantage Policy Optimization
Paper • 2509.18849 • Published • 27 -
EmbeddingGemma: Powerful and Lightweight Text Representations
Paper • 2509.20354 • Published • 47 -
Advancing Speech Understanding in Speech-Aware Language Models with GRPO
Paper • 2509.16990 • Published • 21 -
Video models are zero-shot learners and reasoners
Paper • 2509.20328 • Published • 100 -
EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Paper • 2509.20360 • Published • 18 -
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Paper • 2509.20427 • Published • 82 -
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Paper • 2509.21268 • Published • 104 -
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Paper • 2509.21245 • Published • 39 -
How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective
Paper • 2509.18905 • Published • 30 -
Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
Paper • 2509.19244 • Published • 12 -
AutoIntent: AutoML for Text Classification
Paper • 2509.21138 • Published • 36 -
CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling
Paper • 2509.21114 • Published • 16 -
V-GameGym: Visual Game Generation for Code Large Language Models
Paper • 2509.20136 • Published • 9 -
Interactive Recommendation Agent with Active User Commands
Paper • 2509.21317 • Published • 7 -
MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Paper • 2509.21113 • Published • 6 -
LongLive: Real-time Interactive Long Video Generation
Paper • 2509.22622 • Published • 188 -
VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing
Paper • 2509.22651 • Published • 23 -
CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Paper • 2509.22647 • Published • 33 -
UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models
Paper • 2509.21760 • Published • 15 -
Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
Paper • 2509.21710 • Published • 19 -
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 146 -
Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
Paper • 2509.22496 • Published • 4 -
X-Streamer: Unified Human World Modeling with Audiovisual Interaction
Paper • 2509.21574 • Published • 8 -
Visual Jigsaw Post-Training Improves MLLMs
Paper • 2509.25190 • Published • 37 -
LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning
Paper • 2509.24786 • Published • 7 -
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
Paper • 2509.25131 • Published • 16 -
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
Paper • 2509.22220 • Published • 65 -
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
Paper • 2509.24900 • Published • 53 -
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
Paper • 2509.25160 • Published • 32 -
EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
Paper • 2509.23909 • Published • 33 -
HunyuanImage 3.0 Technical Report
Paper • 2509.23951 • Published • 25 -
MMPB: It's Time for Multi-Modal Personalization
Paper • 2509.22820 • Published • 15 -
BRIDGE - Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation
Paper • 2509.25077 • Published • 15 -
Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Paper • 2509.23050 • Published • 15 -
UniMIC: Token-Based Multimodal Interactive Coding for Human-AI Collaboration
Paper • 2509.22570 • Published • 4 -
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 140 -
LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models
Paper • 2510.03232 • Published • 1 -
Efficient Test-Time Scaling for Small Vision-Language Models
Paper • 2510.03574 • Published • 10 -
Self-Improvement in Multimodal Large Language Models: A Survey
Paper • 2510.02665 • Published • 21 -
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Paper • 2510.00515 • Published • 42 -
Apriel-1.5-15b-Thinker
Paper • 2510.01141 • Published • 121 -
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models
Paper • 2510.01623 • Published • 12 -
VideoNSA: Native Sparse Attention Scales Video Understanding
Paper • 2510.02295 • Published • 10 -
Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
Paper • 2509.21789 • Published • 9 -
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Paper • 2510.02240 • Published • 18 -
Learning to Reason for Hallucination Span Detection
Paper • 2510.02173 • Published • 19 -
VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning
Paper • 2510.01444 • Published • 20 -
Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
Paper • 2510.01284 • Published • 37 -
ModernVBERT: Towards Smaller Visual Document Retrievers
Paper • 2510.01149 • Published • 32 -
StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions
Paper • 2510.02314 • Published • 60 -
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Paper • 2510.02283 • Published • 96 -
VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs
Paper • 2509.25916 • Published • 6 -
Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Paper • 2509.23250 • Published • 6 -
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Paper • 2509.26346 • Published • 19 -
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
Paper • 2510.00406 • Published • 66 -
IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
Paper • 2509.26231 • Published • 18 -
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
Paper • 2509.26391 • Published • 22 -
DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
Paper • 2509.25182 • Published • 39 -
Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
Paper • 2509.26625 • Published • 43 -
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Paper • 2509.26507 • Published • 547 -
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
Paper • 2509.25848 • Published • 80 -
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
Paper • 2509.23873 • Published • 67 -
Heptapod: Language Modeling on Visual Signals
Paper • 2510.06673 • Published • 5 -
Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
Paper • 2510.01954 • Published • 14 -
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
Paper • 2510.07143 • Published • 13 -
TTRV: Test-Time Reinforcement Learning for Vision Language Models
Paper • 2510.06783 • Published • 12 -
MATRIX: Mask Track Alignment for Interaction-aware Video Generation
Paper • 2510.07310 • Published • 36 -
Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
Paper • 2510.06308 • Published • 55 -
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Paper • 2510.06590 • Published • 77 -
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 98 -
SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
Paper • 2510.05081 • Published • 5 -
MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
Paper • 2510.04136 • Published • 4 -
Character Mixing for Video Generation
Paper • 2510.05093 • Published • 7 -
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
Paper • 2510.04290 • Published • 20 -
Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Paper • 2510.05091 • Published • 20 -
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation
Paper • 2510.05094 • Published • 38 -
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Paper • 2510.05034 • Published • 51 -
Paper2Video: Automatic Video Generation from Scientific Papers
Paper • 2510.05096 • Published • 119 -
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper • 2510.08540 • Published • 109 -
DreamOmni2: Multimodal Instruction-based Editing and Generation
Paper • 2510.06679 • Published • 73 -
UniVideo: Unified Understanding, Generation, and Editing for Videos
Paper • 2510.08377 • Published • 81 -
VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
Paper • 2510.08555 • Published • 64 -
ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation
Paper • 2510.08551 • Published • 34 -
PickStyle: Video-to-Video Style Transfer with Context-Style Adapters
Paper • 2510.07546 • Published • 22 -
UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution
Paper • 2510.08143 • Published • 20 -
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Paper • 2510.08565 • Published • 21 -
InstructX: Towards Unified Visual Editing with MLLM Guidance
Paper • 2510.08485 • Published • 18 -
Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
Paper • 2510.08673 • Published • 126 -
D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI
Paper • 2510.05684 • Published • 143 -
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Paper • 2510.09201 • Published • 50 -
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Paper • 2510.09608 • Published • 51 -
BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities
Paper • 2510.08759 • Published • 46 -
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
Paper • 2510.09606 • Published • 18 -
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
Paper • 2510.08457 • Published • 13 -
OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
Paper • 2510.10689 • Published • 47 -
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
Paper • 2510.10395 • Published • 31 -
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
Paper • 2510.11712 • Published • 31 -
Spotlight on Token Perception for Multimodal Reinforcement Learning
Paper • 2510.09285 • Published • 37 -
On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
Paper • 2510.09008 • Published • 16 -
Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
Paper • 2510.11027 • Published • 23 -
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Paper • 2510.12747 • Published • 39 -
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Paper • 2510.12693 • Published • 28 -
DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Paper • 2510.12801 • Published • 13 -
UniFusion: Vision-Language Model as Unified Encoder in Image Generation
Paper • 2510.12789 • Published • 19 -
SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Paper • 2510.12709 • Published • 13 -
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Paper • 2510.12784 • Published • 20 -
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Paper • 2510.12276 • Published • 147 -
Scaling Language-Centric Omnimodal Representation Learning
Paper • 2510.11693 • Published • 104 -
HoneyBee: Data Recipes for Vision-Language Reasoners
Paper • 2510.12225 • Published • 11 -
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE
Paper • 2510.13344 • Published • 63 -
FlashWorld: High-quality 3D Scene Generation within Seconds
Paper • 2510.13678 • Published • 73 -
InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
Paper • 2510.13747 • Published • 30 -
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
Paper • 2510.13795 • Published • 59 -
Generative Universal Verifier as Multimodal Meta-Reasoner
Paper • 2510.13804 • Published • 27 -
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 12 -
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Paper • 2510.13778 • Published • 17 -
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Paper • 2510.10921 • Published • 11 -
X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
Paper • 2510.10274 • Published • 16 -
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
Paper • 2510.13626 • Published • 46 -
PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
Paper • 2510.13809 • Published • 38 -
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Paper • 2510.13802 • Published • 31 -
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
Paper • 2510.13759 • Published • 11 -
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
Paper • 2510.04849 • Published • 115 -
WithAnyone: Towards Controllable and ID Consistent Image Generation
Paper • 2510.14975 • Published • 85 -
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
Paper • 2510.14979 • Published • 67 -
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 118 -
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
Paper • 2510.14958 • Published • 23 -
VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
Paper • 2510.10518 • Published • 19 -
VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
Paper • 2510.14902 • Published • 17 -
Qwen3Guard Technical Report
Paper • 2510.14276 • Published • 15 -
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
Paper • 2510.15870 • Published • 91 -
Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Paper • 2510.15742 • Published • 51 -
PICABench: How Far Are We from Physically Realistic Image Editing?
Paper • 2510.17681 • Published • 64 -
Glyph: Scaling Context Windows via Visual-Text Compression
Paper • 2510.17800 • Published • 68 -
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation
Paper • 2510.17354 • Published • 35 -
FineVision: Open Data Is All You Need
Paper • 2510.17269 • Published • 75 -
RL makes MLLMs see better than SFT
Paper • 2510.16333 • Published • 49 -
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
Paper • 2510.16888 • Published • 22 -
Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling
Paper • 2510.16751 • Published • 21 -
ConsistEdit: Highly Consistent and Precise Training-free Visual Editing
Paper • 2510.17803 • Published • 14 -
Executable Knowledge Graphs for Replicating AI Research
Paper • 2510.17795 • Published • 15 -
Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
Paper • 2510.14605 • Published • 5 -
MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models
Paper • 2510.16641 • Published • 5 -
Paper2Web: Let's Make Your Paper Alive!
Paper • 2510.15842 • Published • 27 -
Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
Paper • 2510.18849 • Published • 21 -
World-in-World: World Models in a Closed-Loop World
Paper • 2510.18135 • Published • 77 -
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
Paper • 2510.18876 • Published • 37 -
ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
Paper • 2510.18795 • Published • 11 -
IF-VidCap: Can Video Caption Models Follow Instructions?
Paper • 2510.18726 • Published • 26 -
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues
Paper • 2510.17722 • Published • 20 -
olmOCR 2: Unit Test Rewards for Document OCR
Paper • 2510.19817 • Published • 16 -
DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents
Paper • 2510.19336 • Published • 17 -
Unified Reinforcement and Imitation Learning for Vision-Language Models
Paper • 2510.19307 • Published • 32 -
OmniNWM: Omniscient Driving Navigation World Models
Paper • 2510.18313 • Published • 14 -
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models
Paper • 2510.19457 • Published • 9 -
Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
Paper • 2510.19808 • Published • 30 -
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints
Paper • 2510.19316 • Published • 12 -
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos
Paper • 2510.19488 • Published • 20 -
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
Paper • 2510.19430 • Published • 52 -
From Charts to Code: A Hierarchical Benchmark for Multimodal Models
Paper • 2510.17932 • Published • 8 -
Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Paper • 2510.20579 • Published • 56 -
HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
Paper • 2510.20822 • Published • 41 -
ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
Paper • 2510.20803 • Published • 12 -
Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence
Paper • 2510.20470 • Published • 12 -
LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas
Paper • 2510.20820 • Published • 11 -
Directional Reasoning Injection for Fine-Tuning MLLMs
Paper • 2510.15050 • Published • 12 -
See the Text: From Tokenization to Visual Reading
Paper • 2510.18840 • Published • 4 -
Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
Paper • 2510.18279 • Published • 6 -
Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
Paper • 2510.20187 • Published • 19 -
SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models
Paper • 2510.16917 • Published • 20 -
UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning
Paper • 2510.20286 • Published • 24 -
Video-As-Prompt: Unified Semantic Control for Video Generation
Paper • 2510.20888 • Published • 50 -
From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
Paper • 2510.19871 • Published • 30 -
Model Merging with Functional Dual Anchors
Paper • 2510.21223 • Published • 13 -
Visual Diffusion Models are Geometric Solvers
Paper • 2510.21697 • Published • 20 -
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
Paper • 2510.21583 • Published • 31 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Paper • 2510.20479 • Published • 12 -
Taming Modality Entanglement in Continual Audio-Visual Segmentation
Paper • 2510.17234 • Published • 5 -
PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
Paper • 2510.21111 • Published • 3 -
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Paper • 2510.23451 • Published • 28 -
LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
Paper • 2510.22946 • Published • 18 -
LongCat-Video Technical Report
Paper • 2510.22200 • Published • 33 -
Tongyi DeepResearch Technical Report
Paper • 2510.24701 • Published • 101 -
Generalization or Memorization: Dynamic Decoding for Mode Steering
Paper • 2510.22099 • Published • 4 -
VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
Paper • 2510.21323 • Published • 4 -
Rethinking Visual Intelligence: Insights from Video Pretraining
Paper • 2510.24448 • Published • 6 -
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation
Paper • 2510.23581 • Published • 42 -
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
Paper • 2510.21817 • Published • 42 -
Open Multimodal Retrieval-Augmented Factual Image Generation
Paper • 2510.22521 • Published • 31 -
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
Paper • 2510.23479 • Published • 16 -
Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
Paper • 2510.24514 • Published • 22 -
Emu3.5: Native Multimodal Models are World Learners
Paper • 2510.26583 • Published • 111 -
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 117 -
Kimi Linear: An Expressive, Efficient Attention Architecture
Paper • 2510.26692 • Published • 125 -
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
Paper • 2510.26802 • Published • 34 -
OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
Paper • 2510.26800 • Published • 22 -
OmniLayout: Enabling Coarse-to-Fine Learning with LLMs for Universal Document Layout Generation
Paper • 2510.26213 • Published • 10 -
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
Paper • 2510.27492 • Published • 86 -
π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Paper • 2510.25889 • Published • 66 -
Continuous Autoregressive Language Models
Paper • 2510.27688 • Published • 73 -
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Paper • 2510.27606 • Published • 31 -
Revisiting Multimodal Positional Encoding in Vision-Language Models
Paper • 2510.23095 • Published • 22 -
SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
Paper • 2510.24940 • Published • 18 -
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning
Paper • 2510.27623 • Published • 13 -
The Underappreciated Power of Vision Models for Graph Structural Understanding
Paper • 2510.24788 • Published • 36 -
LongCat-Flash-Omni Technical Report
Paper • 2511.00279 • Published • 26 -
Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench
Paper • 2510.26865 • Published • 12 -
left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles
Paper • 2511.01340 • Published • 13 -
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Paper • 2510.25616 • Published • 105 -
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
Paper • 2511.02778 • Published • 102 -
When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
Paper • 2511.02779 • Published • 59 -
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
Paper • 2511.02243 • Published • 25 -
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
Paper • 2511.02650 • Published • 10 -
MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity
Paper • 2511.03146 • Published • 8 -
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
Paper • 2511.04570 • Published • 240 -
V-Thinker: Interactive Thinking with Images
Paper • 2511.04460 • Published • 97 -
Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts
Paper • 2511.04655 • Published • 8 -
NVIDIA Nemotron Nano V2 VL
Paper • 2511.03929 • Published • 30 -
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
Paper • 2511.03334 • Published • 53 -
Cambrian-S: Towards Spatial Supersensing in Video
Paper • 2511.04670 • Published • 38 -
Contamination Detection for VLMs using Multi-Modal Semantic Perturbation
Paper • 2511.03774 • Published • 13 -
Visual Spatial Tuning
Paper • 2511.05491 • Published • 52 -
Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
Paper • 2511.04962 • Published • 57 -
Dense Motion Captioning
Paper • 2511.05369 • Published • 10 -
DeepEyesV2: Toward Agentic Multimodal Model
Paper • 2511.05271 • Published • 45 -
HaluMem: Evaluating Hallucinations in Memory Systems of Agents
Paper • 2511.03506 • Published • 94 -
MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
Paper • 2511.07250 • Published • 18 -
Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale
Paper • 2511.05705 • Published • 8 -
Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs
Paper • 2511.05933 • Published • 9 -
MPJudge: Towards Perceptual Assessment of Music-Induced Paintings
Paper • 2511.07137 • Published • 6 -
VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models
Paper • 2511.07299 • Published • 8 -
Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora
Paper • 2511.07080 • Published • 32 -
VideoSSR: Video Self-Supervised Reinforcement Learning
Paper • 2511.06281 • Published • 25 -
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Paper • 2511.05489 • Published • 3 -
WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
Paper • 2511.09515 • Published • 20 -
MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
Paper • 2511.06805 • Published • 13 -
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
Paper • 2511.08892 • Published • 210 -
TiDAR: Think in Diffusion, Talk in Autoregression
Paper • 2511.08923 • Published • 128 -
Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising
Paper • 2511.08633 • Published • 55 -
GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
Paper • 2511.11134 • Published • 32 -
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 97 -
WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
Paper • 2511.11434 • Published • 45 -
UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation
Paper • 2511.08195 • Published • 34 -
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Paper • 2511.07403 • Published • 14 -
Simulating the Visual World with Artificial Intelligence: A Roadmap
Paper • 2511.08585 • Published • 30 -
EmoVid: A Multimodal Emotion Video Dataset for Emotion-Centric Video Understanding and Generation
Paper • 2511.11002 • Published • 4 -
Depth Anything 3: Recovering the Visual Space from Any Views
Paper • 2511.10647 • Published • 99 -
Music Flamingo: Scaling Music Understanding in Audio Language Models
Paper • 2511.10289 • Published • 17 -
AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
Paper • 2511.10017 • Published • 7 -
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Paper • 2511.11793 • Published • 187 -
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 70 -
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
Paper • 2511.13647 • Published • 71 -
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
Paper • 2511.13704 • Published • 43 -
Back to Basics: Let Denoising Generative Models Denoise
Paper • 2511.13720 • Published • 69 -
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Paper • 2511.14659 • Published • 13 -
VIDEOP2R: Video Understanding from Perception to Reasoning
Paper • 2511.11113 • Published • 111 -
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Paper • 2511.10555 • Published • 62 -
Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark
Paper • 2511.13853 • Published • 36 -
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
Paper • 2511.14159 • Published • 25 -
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Paper • 2511.14582 • Published • 19 -
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
Paper • 2511.13026 • Published • 26 -
General Agentic Memory Via Deep Research
Paper • 2511.18423 • Published • 167 -
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 129 -
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 93 -
Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
Paper • 2511.19418 • Published • 29 -
HunyuanVideo 1.5 Technical Report
Paper • 2511.18870 • Published • 28 -
HunyuanOCR Technical Report
Paper • 2511.19575 • Published • 22 -
RynnVLA-002: A Unified Vision-Language-Action and World Model
Paper • 2511.17502 • Published • 28 -
O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
Paper • 2511.13593 • Published • 27 -
Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
Paper • 2511.17490 • Published • 22 -
Loomis Painter: Reconstructing the Painting Process
Paper • 2511.17344 • Published • 15 -
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Paper • 2511.16175 • Published • 12 -
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Paper • 2511.11007 • Published • 15 -
Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models
Paper • 2511.17487 • Published • 12 -
VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation
Paper • 2511.17199 • Published • 8 -
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 64 -
In-Video Instructions: Visual Signals as Generative Control
Paper • 2511.19401 • Published • 32 -
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
Paper • 2511.20256 • Published • 28 -
AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser
Paper • 2511.16397 • Published • 10 -
Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward
Paper • 2511.20561 • Published • 32 -
Soft Adaptive Policy Optimization
Paper • 2511.20347 • Published • 42 -
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flow
Paper • 2511.20462 • Published • 32 -
MagicWorld: Interactive Geometry-driven Video World Exploration
Paper • 2511.18886 • Published • 19 -
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
Paper • 2511.19413 • Published • 20 -
Monet: Reasoning in Latent Visual Space Beyond Images and Language
Paper • 2511.21395 • Published • 18 -
G^2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Paper • 2511.21688 • Published • 8 -
Video Generation Models Are Good Latent Reward Models
Paper • 2511.21541 • Published • 45 -
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
Paper • 2511.21691 • Published • 36 -
REASONEDIT: Towards Reasoning-Enhanced Image Editing Models
Paper • 2511.22625 • Published • 47 -
InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
Paper • 2512.01342 • Published • 18 -
TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
Paper • 2511.16595 • Published • 10 -
Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
Paper • 2511.16669 • Published • 32 -
MiMo-Embodied: X-Embodied Foundation Model Technical Report
Paper • 2511.16518 • Published • 26 -
SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
Paper • 2511.15605 • Published • 24 -
Scaling Spatial Intelligence with Multimodal Foundation Models
Paper • 2511.13719 • Published • 47 -
Step-Audio-R1 Technical Report
Paper • 2511.15848 • Published • 58 -
V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models
Paper • 2511.16668 • Published • 55 -
ARC-Chapter: Structuring Hour-Long Videos into Navigable Chapters and Hierarchical Summaries
Paper • 2511.14349 • Published • 18 -
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 43 -
Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks
Paper • 2511.15065 • Published • 77 -
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Paper • 2511.14993 • Published • 231 -
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
Paper • 2512.03041 • Published • 66 -
TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
Paper • 2512.01248 • Published • 12 -
OneThinker: All-in-one Reasoning Model for Image and Video
Paper • 2512.03043 • Published • 33 -
ViDiC: Video Difference Captioning
Paper • 2512.03405 • Published • 28 -
Thinking with Programming Vision: Towards a Unified View for Thinking with Images
Paper • 2512.03746 • Published • 17 -
Qwen3-VL Technical Report
Paper • 2511.21631 • Published • 158 -
AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
Paper • 2512.03794 • Published • 5 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 171 -
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
Paper • 2512.05081 • Published • 31 -
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
Paper • 2511.22826 • Published • 8 -
Guided Self-Evolving LLMs with Minimal Human Supervision
Paper • 2512.02472 • Published • 55 -
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 49 -
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
Paper • 2512.02425 • Published • 25 -
Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation
Paper • 2512.02457 • Published • 14 -
MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues
Paper • 2512.03046 • Published • 12 -
Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization
Paper • 2511.22586 • Published • 7 -
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Paper • 2512.04678 • Published • 42 -
Relational Visual Similarity
Paper • 2512.07833 • Published • 25 -
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
Paper • 2512.07829 • Published • 23 -
LongCat-Image Technical Report
Paper • 2512.07584 • Published • 23 -
OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
Paper • 2512.08294 • Published • 18 -
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
Paper • 2512.07831 • Published • 17 -
Visual Generation Tuning
Paper • 2511.23469 • Published • 16 -
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Paper • 2512.08765 • Published • 132 -
Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality
Paper • 2512.07951 • Published • 50 -
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Paper • 2512.07802 • Published • 46 -
DeepCode: Open Agentic Coding
Paper • 2512.07921 • Published • 33 -
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Paper • 2512.02231 • Published • 9 -
InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
Paper • 2512.08829 • Published • 21 -
Rethinking Chain-of-Thought Reasoning for Videos
Paper • 2512.09616 • Published • 19 -
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Paper • 2511.23386 • Published • 16 -
LongVie 2: Multimodal Controllable Ultra-Long Video World Model
Paper • 2512.13604 • Published • 74 -
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
Paper • 2512.12967 • Published • 108 -
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
Paper • 2512.13080 • Published • 17 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 119 -
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Paper • 2512.12675 • Published • 41 -
Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure
Paper • 2512.14336 • Published • 31 -
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
Paper • 2512.14051 • Published • 46 -
ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
Paper • 2512.13303 • Published • 17 -
Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in
Paper • 2512.14273 • Published • 10 -
Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
Paper • 2512.15603 • Published • 66 -
DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models
Paper • 2512.15713 • Published • 17 -
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Paper • 2512.14614 • Published • 71 -
Video Reality Test: Can AI-Generated ASMR Videos fool VLMs and Humans?
Paper • 2512.13281 • Published • 64 -
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
Paper • 2512.14699 • Published • 28 -
TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
Paper • 2512.14698 • Published • 21 -
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
Paper • 2512.14052 • Published • 42 -
Puzzle Curriculum GRPO for Vision-Centric Reasoning
Paper • 2512.14944 • Published • 36 -
In Pursuit of Pixel Supervision for Visual Pre-training
Paper • 2512.15715 • Published • 11 -
Kling-Omni Technical Report
Paper • 2512.16776 • Published • 170 -
Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model
Paper • 2512.13507 • Published • 40 -
Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image
Paper • 2512.16899 • Published • 14 -
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
Paper • 2512.17495 • Published • 20 -
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
Paper • 2512.17532 • Published • 67 -
PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence
Paper • 2512.16793 • Published • 75 -
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Paper • 2512.17909 • Published • 37 -
MMFormalizer: Multimodal Autoformalization in the Wild
Paper • 2601.03017 • Published • 105 -
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Paper • 2601.04720 • Published • 55 -
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Paper • 2601.05175 • Published • 36 -
Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
Paper • 2512.21815 • Published • 22 -
JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
Paper • 2512.22905 • Published • 20 -
InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
Paper • 2512.18745 • Published • 12 -
Latent Implicit Visual Reasoning
Paper • 2512.21218 • Published • 69 -
How Much 3D Do Video Foundation Models Encode?
Paper • 2512.19949 • Published • 10 -
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Paper • 2512.20557 • Published • 50 -
Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
Paper • 2512.21337 • Published • 31 -
LongVideoAgent: Multi-Agent Reasoning with Long Videos
Paper • 2512.20618 • Published • 55 -
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 154 -
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
Paper • 2601.03193 • Published • 47 -
MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
Paper • 2512.23412 • Published • 41 -
MiMo-V2-Flash Technical Report
Paper • 2601.02780 • Published • 35 -
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
Paper • 2601.02204 • Published • 62 -
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Paper • 2512.24271 • Published • 63