|
Junwei Yu Hi! I'm a member of technical staff at Voio Inc, and a researcher at Berkeley AI Research (BAIR) lab. I'm fortunate to work closely with Prof. XuDong Wang, Prof. Trevor Darrell, and Prof. Adam Yala. I received Bachelor's degree in Computer Science (Honors) and Applied Mathematics from UC Berkeley. My research focuses on self-supervised learning, vision foundation models, and multimodality. I also have experience in learning theory and optimization. |
|
Publications |
|
Open-Ended CT Volume Segmentation with Weak Supervision from Language
Sanjay Subramanian, Junwei Yu, Zirui Wang, Rohil Malpani, Maggie Chung, Adam Yala, Dan Klein, Trevor Darrell arXiv, 2026 Paper |
|
Stateful Visual Encoders for Vision-Language Models
Zirui Wang, Junwei Yu, Adam Yala, David M. Chan, Joseph E. Gonzalez, Trevor Darrell arXiv 2026 Paper | Project page | Code |
|
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
Junwei Yu, Trevor Darrell, XuDong Wang arXiv 2025 Paper | Project page | Code |
|
Fast John Ellipsoid Computation with Differential Privacy Optimization
(Alphabetical Order) Xiaoyu Li*, Yingyu Liang*, Zhenmei Shi*, Zhao Song*, Junwei Yu* CPAL 2025, Oral Paper |
|
|
Quantum Speedups for Approximating the John Ellipsoid
(Alphabetical Order) Xiaoyu Li*, Zhao Song*, Junwei Yu* QIP 2025 Paper |
Experience |
|
Voio: Member of Technical Staff
Jan 2026 - Present: Research Team |
|
Amazon: Software Engineering Intern
Summer 2025: Member of Global Payment Tech |
|
DATA C140: Probability for Data Science
Fall 2024: Tutor Supervised by Prof. Ani Adhikari |