Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs Paper • 2608.12781 • Published 10 days ago • 33
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models Paper • 2606.02277 • Published Jun 1 • 7
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models Paper • 2606.02277 • Published Jun 1 • 7
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training Paper • 2605.13757 • Published May 13 • 21