Zuxuan Wu

Human demonstrations can yield over 10x the recovery data for robots, dramatically enhancing their ability to recover from failures in real-world tasks.

Fine-grained contact states can be distinguished through the dynamic correlation of tactile motion, transforming how we approach contact-rich manipulation in robotics.

Semantic visual-action tokenization in RepWAM significantly enhances robotic manipulation performance, outperforming traditional reconstruction-based approaches.

ActiveMimic reveals that leveraging active perception from egocentric videos can close the performance gap with robot-pretrained models, transforming how we approach robot learning.

Forget fine-tuning: VLA-Pro dynamically fuses task-specific LoRA adapters retrieved from memory to achieve state-of-the-art cross-task generalization in robotic manipulation.

BiDPO achieves a remarkable boost in compositional fidelity for text-to-image generation, outperforming previous methods through innovative preference optimization techniques.

Forget patch-based image tokenization: channel-wise quantization unlocks better codebook utilization and text-to-image generation by representing images as discrete levels of visual detail.

Freezing your vision foundation model doesn't have to mean sacrificing fine-grained detail: DecQ unlocks improved reconstruction and faster generative convergence with just 8 extra queries and minimal overhead.

VLA models can ace the task but still trigger unsafe outcomes, exposing a critical gap between action execution and semantic understanding.