Assistant Professor, ShanghaiTech University
4 papers at NeurIPS 2025
Introduce the first Open-World Hand-Object Interaction (HOI) Synthesis framework that can generate Long-horizon HOI sequences of Unseen Objects from Open-vocabulary instruction with 3D Multimodal Large Language Model.
We propose GenPO, which effectively incorporates invertible diffusion model into on-policy RL, and deals with the challenge of log-likehood computation in diffusion policies.
LithoSim introduces lithography simulation benchmark with >4 million rigorously curated input-output pairs, integrating optical variations, mask corrections, and process dynamics to establish a unified evaluation flow for ML-based simulation.