Embodied Red Teaming for Auditing Robotic Foundation Models Paper • 2411.18676 • Published Nov 27, 2024 • 1
Towards Data-Efficient Pretraining for Atomic Property Prediction Paper • 2502.11085 • Published 11 days ago • 3
Intuitive physics understanding emerges from self-supervised pretraining on natural videos Paper • 2502.11831 • Published 10 days ago • 14
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training Paper • 2502.11196 • Published 10 days ago • 21
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 11 days ago • 134
view article Article π0 and π0-FAST: Vision-Language-Action Models for General Robot Control 23 days ago • 109