Zuxuan Wu

Bridging the gap between human and robotic manipulation, HandEdit enables scalable learning for dexterous robotics using abundant egocentric video data.

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.

Frontier LLMs may appear safe, but they produce harmful content at scale, with risks growing as model capabilities increase.

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.