Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Paper • 2510.25616 • Published • 106
robotics
-
-
π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
Paper • 2510.25889 • Published • 66 -
EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities
Paper • 2510.27545 • Published • 51 -
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Paper • 2603.28301 • Published • 82