Scholar
Siyi Chen
Google Scholar ID: j65QlFkAAAAJ
University of Michigan - Ann Arbor
Citations & Impact
Citations
111
H-index
4
i10-index
3
Publications
9
Co-authors
20
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published works on interpretable token embeddings for diffusion model unlearning, explaining and mitigating modality gap in contrastive multimodal learning, exploring low-dimensional subspaces in diffusion models for controllable image editing, unfolding video dynamics via Taylor expansion, and understanding how diffusion models learn low-dimensional distributions through subspace clustering; received Rackham Internship Fellowship and Rackham Predoctoral Fellowship.
Research Experience
- Research Intern at NVIDIA's Learning and Perception Research Group (05/2025 - Present); Research Intern at Sony AI America's Vision Foundation Model and Generative AI Team (03/2025 - 05/2025).
Education
- PhD student in Electrical and Computer Engineering at the University of Michigan-Ann Arbor (2022 - Present), advised by Prof. Qing Qu; B.S.E. in Computer Science from the University of Michigan-Ann Arbor, and a B.S.E. in Electrical and Computer Engineering from Shanghai Jiao Tong University. During undergraduate studies, worked with Prof. David Fouhey and Dr. Shengyi Qian on 3D computer vision.
Background
- Research interests encompass generative AI and multimodal foundation models, such as diffusion models, vision-language models, and representation learning. Interested in exploring their interpretability, controllability, and unification.
Miscellany
- Participated in the design of the game 'Asylum 7'; served as a Graduate Student Instructor for EECS 559 Optimization, Undergraduate Instructional Assistant for EECS 442 Computer Vision, Teaching Assistant for VE 401 Probabilistic Methods, and Teaching Assistant for VV 286 Honorable Mathematics.
