๐ผ About
I am a researcher at Microsoft GenAI, working on OpenAI and Microsoft model training. I completed a Ph.D. in Computer Science at the University of California, Santa Cruz with Xin Eric Wang. My PhD research work mainly revolved around generative AI, agentic AI, and multimodal learning. I was at the University of California, San Diego working with Pengtao Xie on machine learning and AI for healthcare. Before that, I began my research and undergraduate at the University of Electronic Science and Technology of China.
๐ฐ News
- ๐งโ๐ป 2025.07: One paper accepted to ICCV, three papers accepted to NeurIPs 2025, and one paper accepted to WACV.
- ๐ ๏ธ 2025.02: Co-organize the CVPR 2025 Workshop โ Computer Vision in the Wild.๐ Host our MMWorld benchmark there.๐ฅ
- ๐ 2025.02: One paper accepted to CVPR 2025.
- ๐ฅ 2025.01: Two papers accepted to ICLR 2025.๐
- ๐ฅ 2024.08: One paper accepted to TMLR 2024.
๐ Selected Publications
The symbol * indicates equal contribution

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
Xuehai He, Weixi Feng*, Kaizhi Zheng*, Yujie Lu*, Wanrong Zhu*, Jiachen Li*, Yue Fan*, Jianfeng Wang, Linjie Li, Zhengyuan Yang, Kevin Lin, William Yang Wang, Lijuan Wang, Xin Eric Wang.
ICLR, 2025. [Project Website]

Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners
Xuehai He, Weixi Feng, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang.
TMLR, 2024. [Project Website]

Parameter-efficient Model Adaptation for Vision Transformers
Xuehai He, Chunyuan Li, Pengchuan Zhang, Jianwei Yang, Xin Eric Wang.
AAAI, 2023. [Project Website]
๐ Selected Preprints
Mojito: Motion Trajectory and Intensity Control for Video Generation
Xuehai He, Shuohang Wang, Jianwei Yang, Xiaoxia Wu, Yiping Wang, Kuan Wang, Zheng Zhan, Olatunji Ruwase, Yelong Shen, Xin Eric Wang.
[PDF]
MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens
Kaizhi Zheng*, Xuehai He*, Xin Eric Wang.
[PDF]
Soft thinking: Unlocking the reasoning potential of llms in continuous concept space
Zhen Zhang*, Xuehai He*, Weixiang Yan, Ao Shen, Chenyang Zhao, Shuohang Wang, Yelong Shen, Xin Eric Wang.
[PDF]
๐ Publications
See Google Scholar for fully updated one.
Click to expand publications
๐ฒ Service
-
๐๏ธ Conference Reviewer: ICASSPโ19, IJCAIโ21, AAAIโ21, CVPRโ21-โ24, ICCVโ21-โ23, ECCVโ22, NeurIPSโ22-โ23, EMNLPโ22-โ23, ACLโ23-โ24, ICMLโ23-โ24.
- โ๏ธ Journal Reviewer:
- IEEE Accessโ19โ20
- Transactions on Pattern Analysis and Machine Intelligence (TPAMI)โ24
- ๐ฅ Program Committee Member:
- NeurIPS 2021 Workshop: Self-Supervised Learning โ Theory and Practice [Link]
- ๐ค Workshop Co-organizer:
- ๐ Workshop Reviewer: