Jiaxin Ge

About

I am a Ph.D. student in Computer Science at UC Berkeley, advised by Prof. Trevor Darrell. I am a member of Berkeley AI Research (BAIR). I also work closely with Prof. Sewon Min.

I received my Bachelor's Degree from Peking University, where I was advised by Prof. Shanghang Zhang. I have also worked closely with Prof. Graham Neubig, Prof. Jim Glass, and Prof. Guangyu Robert Yang.

I build generalizable unified models. If you are interested, please feel free to reach out!

Selected Publications (*: equal contribution)

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Zirui Wang*, Junyi Zhang*, Jiaxin Ge*, Long Lian, Letian Fu, Lisa Dunlap, Ken Goldberg, Xudong Wang, Ion Stoica, David M. Chan, Sewon Min, Joseph E. Gonzalez — 2026 Preprint

ICLR Workshop on Efficient Spatial Reasoning (Oral)

ICLR Workshop on Multimodal Intelligence (Oral)

pdf / website / code / dataset

Constantly Improving Image Models Need Constantly Improving Benchmarks

Jiaxin Ge*, Grace Luo*, Heekyung Lee, Nishant Malpani, Long Lian, XuDong Wang, Aleksander Holynski, Trevor Darrell, Sewon Min, David M. Chan — 2026 ICLR

pdf / website / code / dataset

AutoPresent: Designing Structured Visuals From Scratch

Jiaxin Ge*, Zora Zhiruo Wang*, Xuhui Zhou, Yi-Hao Peng, Sanjay Subramanian, Qinyue Tan, Maarten Sap, Alane Suhr, Daniel Fried, Graham Neubig, Trevor Darrell — 2025 CVPR

pdf / code

Enough Coin Flips Can Make LLMs Act Bayesian

Ritwik Gupta*, Rodolfo Corona*, Jiaxin Ge*, Eric Wang, Dan Klein, Trevor Darrell, David M. Chan — 2025 ACL

pdf / website / code

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning

Shaofeng Yin, Jiaxin Ge, Zora Zhiruo Wang, Chenyang Wang, Xiuyu Li, Michael J. Black, Trevor Darrell, Angjoo Kanazawa, Haiwen Feng — 2026 Preprint

pdf / website / code

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Yiming Qin, Bomin Wei, Jiaxin Ge, Konstantinos Kallidromitis, Stephanie Fu, Trevor Darrell, XuDong Wang — 2025 Preprint

pdf / website / code

Recursive Visual Programming

Jiaxin Ge, Sanjay Subramanian, Baifeng Shi, Roei Herzig, Trevor Darrell — 2024 ECCV

pdf / code

Teaching & Service

• Workshop Co-Organizer, What is Next in Multimodal Foundation Models? [CVPR 2026, ICCV 2025]
• Teaching Assistant: CS280 (Computer Vision), UC Berkeley
• Conference Reviewer: CVPR, NeurIPS, ICLR, ACL, EMNLP, NAACL