VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published 13 days ago • 160
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published 11 days ago • 143
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents Paper • 2602.07274 • Published 17 days ago • 203
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published 13 days ago • 227
NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control Paper • 2602.09070 • Published 15 days ago • 43
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies Paper • 2602.09877 • Published 14 days ago • 191