| CARVIEW |
Haotian Xue
4th-year PhD (Machine Learning), Georgia Tech. Advised by Yongxin Chen.
About & Research Interests
I do research in machine learning and computer vision. Currently, I am interested in physics AI regarding multi-modal language models, video diffusion model and world models. I am also committed to safety problem in generative AI, focusing on adversarial protection of diffusion model.
I did research at
Adobe Firefly (2025),
NVIDIA DIR (2024), and
Microsoft Research Asia (2021).
I was also a visiting student at
MIT CSAIL (2021).
I earned my B.E. in Computer Science (Honors) from
Shanghai Jiao Tong University (Zhiyuan Honor Program) in 2022.
News
- 2025-10 We propose MoGAN, a novel post-training to improve motion quality for few-step video diffusion models.
- 2025-09 We propose PIO-Bench, a visual-grounding-centric benchmark for embodied reasoning of VLMs.
- 2025-04 Joining Adobe Firefly (Summer+Fall) to work on post-training for video diffusion.
- 2024-10 NeurIPS 2024 Scholar Award — see you in Vancouver!
- 2024-09 Three papers accepted to NeurIPS 2024: DP-Attacker, RefDrop, QueST.
- 2024-05 Started summer research intern at NVIDIA DIR Group.
- 2024-04 Released PDM-Pure, a universal purifier against diffusion models.
- 2024-03 ICLR 2024 Travel Award.
- 2024-01 SDS-Attack accepted to ICLR 2024.
- 2023-10 NeurIPS 2023 Scholar Award; invited reviewer for TPAMI.
- 2023-09 Diff-PGD and 3D-IntPhys accepted to NeurIPS 2023.
- 2023-08 Invited reviewer for ICLR 2024.
- 2023-05 Proposed Diff-PGD, a diffusion-based adversarial sample framework.
- 2022-12 Selected as a Top Reviewer of NeurIPS 2022.
- 2022-10 Distance-Transformer accepted to EMNLP 2022 Findings.
- 2022-08 Started PhD at ML@GT.
Selected Publications
More & older publications
See Google Scholar for the full, latest list.
Reviewer Experience
- NeurIPS ’22–’25
- ICLR ’24–’25
- ICML ’22–’25
- AISTATS ’25
- CVPRW ’25
- TPAMI
- TCSVT