Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes Paper • 2603.25562 • Published 5 days ago • 6
PixelSmile: Toward Fine-Grained Facial Expression Editing Paper • 2603.25728 • Published 5 days ago • 114
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing Paper • 2603.19228 • Published 12 days ago • 66
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published 27 days ago • 210
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning Paper • 2602.23440 • Published Feb 26 • 3
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published Feb 11 • 220
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents Paper • 2602.07274 • Published Feb 6 • 208
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published Feb 11 • 244
NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control Paper • 2602.09070 • Published Feb 9 • 46
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies Paper • 2602.09877 • Published Feb 10 • 197