He Wang

AllDayNav achieves near-perfect navigation success rates by leveraging a self-evolving memory system that outperforms traditional mapping methods.

KPGrasp achieves a remarkable 76.3% grasp success rate, outpacing existing methods by a staggering 47.4% while simplifying the grasp generation process.

Training with just 3% of high-quality motion data can yield superior tracking performance compared to using the entire dataset.

Humanoid-GPT achieves unprecedented zero-shot generalization in motion tracking, outperforming traditional models by leveraging a billion-scale motion dataset.

Diffusion models can now plan effectively for long-horizon tasks by strategically generating subgoals that are then efficiently realized by rectified flow models.