Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Paper • 2603.24472 • Published • 46
Sentinel
Sentinel7
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
Sentinel7/wan updated a model about 17 hours ago
Sentinel7/ltxv liked a dataset about 22 hours ago
open-index/open-libraryOrganizations
None yet
upvoted 20
papers 5 days ago
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
Paper • 2603.24533 • Published • 44
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models
Paper • 2603.25502 • Published • 55
Believe Your Model: Distribution-Guided Confidence Calibration
Paper • 2603.03872 • Published • 40
Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration
Paper • 2603.24800 • Published • 65
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
Paper • 2603.19466 • Published • 41
SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM
Paper • 2603.23386 • Published • 40
Repurposing Geometric Foundation Models for Multi-view Diffusion
Paper • 2603.22275 • Published • 45
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
Paper • 2603.19227 • Published • 42
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
Paper • 2603.22057 • Published • 45
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
Paper • 2603.23499 • Published • 50
VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
Paper • 2603.22285 • Published • 50
TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation
Paper • 2603.19039 • Published • 50
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Paper • 2603.22386 • Published • 54
Memento-Skills: Let Agents Design Agents
Paper • 2603.18743 • Published • 54
Online Experiential Learning for Language Models
Paper • 2603.16856 • Published • 57
FASTER: Rethinking Real-Time Flow VLAs
Paper • 2603.19199 • Published • 57
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Paper • 2603.23483 • Published • 59
3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
Paper • 2603.18524 • Published • 58
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Paper • 2603.16448 • Published • 58