Research Interest

Currently, I am interested at improving physical understanding and physical alignment of Generative AI models, e.g. Vision-Language Models and Video Diffusion Models.
I am also committed to developing safe GenAI, in my early Ph.D., I worked on adversarial attacks and defenses in GenAI, and developed several important algorithms across Image Diffusion Model and Robot Diffusion Policy: e.g. Diff-PGD, SDS-Attack, Diff-Pure and DP-Attacker.

News 📢

• [2025.04] I will be at Adobe Firefly this summer and fall, working on post-training of video diffusion models.
• [2024.10] I was awarded the NeurIPS'2024 scholar award, thanks! See you in Vancouver, CA.
• [2024.09] 3 Papers (DP-Attacker, RefDrop, QueST) are accepted to NeurIPS 2024 !
• [2024.05] I started as a summer research intern at Nvidia DIR Group !
• [2024.05] We propose DP-Attacker, a framework to attack Diffusion-based policy generator.
• [2024.04] We release PDM-Pure, a universal purifier for protection against diffusion models
• [2024.03] I received the ICLR'2024 travel award, thanks!
• [2024.01] Our SDS-Attack is accepted by ICLR'2024!
• [2023.10] I was awarded the NeurIPS'2023 scholar award, thanks!
• [2023.10] I was invited as a reviewer for TPAMI.
• [2023.09] Diff-PGD and 3D-IntPhys are accepted by NeurIPS'2023!
• [2023.08] I was invited as a reviewer for ICLR'2024.
• [2023.05] We propose Diff-PGD, a diffusion-based adv-sample generation framework.
• [2022.12] I am selected as the Top Reviewer of NeurIPS 2022.
• [2022.10] Our Distance-Transformer is accepted to EMNLP2022 Findings.
• [2022.08] I will start as a PhD student at (ML@GT) starting from 2022Fall.

Reviewer Experience

Conference:

• NeurIPS@22/23/24/25
• ICLR@24/25
• AISTATS@25
• ICML@22/23/24/25
• CVPRW@25

Journals:

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)