Yuheng joined Adobe Research in 2024, where he works on computer vision and deep learning.

He received his Ph.D. in Computer Science from the University of Wisconsin–Madison, advised by Prof. Yong Jae Lee. His doctoral research focused on controllable image generation.

His recent work centers on multimodal learning, including unified training strategies for MLLMs, model architectures, and dataset design. He is also broadly interested in general computer vision problems.

Publications

X-Fusion: Introducing New Modality to Frozen Large Language Models

Mo, Sicheng., Nguyen, Thao., Huang, Xun., Iyer, Siddharth., Li, Yijun., Liu, Yuchen., Tandon, Abhishek., Shechtman, Eli., Singh, Krishna., Lee, Yong., Zhou, Bolei., Li, Yuheng. (Apr. 29, 2025)

Best Paper award at T4V workshop CVPR'25

arxiv