MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models Paper • 2510.24794 • Published Oct 27, 2025 • 32
ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning Paper • 2602.11636 • Published Feb 12 • 2
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation Paper • 2605.14712 • Published May 14 • 16
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models Paper • 2606.02277 • Published Jun 1 • 8
SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models Paper • 2607.06442 • Published Jul 7 • 6
Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments Paper • 2606.32009 • Published Jun 30
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models Paper • 2606.02277 • Published Jun 1 • 8
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training Paper • 2605.13757 • Published May 13 • 21
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training Paper • 2605.13757 • Published May 13 • 21