VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published 15 days ago • 183
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published 13 days ago • 145
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published 16 days ago • 230
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies Paper • 2602.09877 • Published 16 days ago • 196
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger Paper • 2602.08222 • Published 17 days ago • 269