End-to-End Vision Tokenizer Tuning
Paper • 2505.10562 • Published • 22
Representation Learning
-
-
Global and Local Entailment Learning for Natural World Imagery
Paper • 2506.21476 • Published • 1 -
DINOv3
Paper • 2508.10104 • Published • 301 -
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
Paper • 2509.01363 • Published • 60 -
AToken: A Unified Tokenizer for Vision
Paper • 2509.14476 • Published • 37 -
Lost in Embeddings: Information Loss in Vision-Language Models
Paper • 2509.11986 • Published • 29 -
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Paper • 2509.15591 • Published • 45 -
SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Paper • 2510.12709 • Published • 13 -
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Paper • 2510.08492 • Published • 10 -
GRACE: Generative Representation Learning via Contrastive Policy Optimization
Paper • 2510.04506 • Published • 12 -
Latent Diffusion Model without Variational Autoencoder
Paper • 2510.15301 • Published • 50 -
Model Merging with Functional Dual Anchors
Paper • 2510.21223 • Published • 13 -
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
Paper • 2510.20479 • Published • 12 -
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Paper • 2510.25602 • Published • 79 -
Defeating the Training-Inference Mismatch via FP16
Paper • 2510.26788 • Published • 31 -
UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
Paper • 2511.00405 • Published • 6 -
Φeat: Physically-Grounded Feature Representation
Paper • 2511.11270 • Published • 11 -
Qwen3-VL Technical Report
Paper • 2511.21631 • Published • 161 -
Next-Embedding Prediction Makes Strong Vision Learners
Paper • 2512.16922 • Published • 88 -
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
Paper • 2601.04720 • Published • 57 -
Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 45 -
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Paper • 2602.08683 • Published • 52 -
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
Paper • 2602.02338 • Published • 42 -
Unified Vision-Language Modeling via Concept Space Alignment
Paper • 2603.01096 • Published • 6 -
InfoNCE Induces Gaussian Distribution
Paper • 2602.24012 • Published • 13 -
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
Paper • 2602.24264 • Published • 14