LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models Paper • 2603.28301 • Published 12 days ago • 77
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published 21 days ago • 330
Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models Paper • 2603.17051 • Published 24 days ago • 108
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published 24 days ago • 248