SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 5 days ago • 267
Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models Paper • 2604.01404 • Published 13 days ago • 5
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper • 2603.17051 • Published 27 days ago • 109
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published Feb 13 • 216
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published 27 days ago • 248