|
[2026.06] Our work RATs is on arXiv!
[2026.03] Our work LoGeR is on arXiv! Check out the project page and code.
[2026.01] VisGym is on arXiv! Code, dataset, models, and benchmarks can be found on the webpage!
[2025.10] VideoMimic is accepted to CoRL 2025 as Oral, Best Student Paper Award!
[2025.05] Our work VideoMimic is released, check out the project page we made: VideoMimic.net!
[2025.04] Our work St4RTrack is on arXiv!
[2025.01] Both MonST3R and DenseMatcher are accepted by ICLR 2025 as Spotlight!
[2024.12] Our work DenseMatcher is on arXiv!
[2024.10] Very excited to share our latest work, MonST3R, check out the interactive 4D results 🔥!
[2024.06] I graduated from SJTU with Honor Degree, Outstanding Graduates of Shanghai, and Best Bachelor Thesis! 🥳
[2024.03] Code for Telling Left from Right is released on GitHub.
[2024.02] 🎉 Our work Telling Left from Right is accepted by CVPR 2024! 🎉
[2023.11] Our work Telling Left from Right is on arXiv!
[2023.09] 🎉 Our work A Tale of Two Features is accepted to NeurIPS 2023! 🎉
[2023.08] Code for LayoutDiffusion is released on GitHub.
[2023.07] 🎉 Our work LayoutDiffusion is accepted to ICCV 2023! 🎉
[2023.06] Code for A Tale of Two Features is released on GitHub.
[2023.05] Our work A Tale of Two Features is on arXiv!
[2023.04] Our work Pangea is on arXiv!
[2023.03] Our work LayoutDiffusion is on arXiv!
|
|
Playful Agentic Robot Learning
Junyi Zhang*†,
Jiaxin Ge*†,
Hanjun Yoo†,
Letian Fu‡,
Zihan Yang‡,
Yaowei Liu‡,
Raj Saravanan‡,
Shaofeng Yin,
Justin Yu,
Dantong Niu,
Zirui Wang,
Roei Herzig,
Ken Goldberg,
Yutong Bai,
David M. Chan,
Ion Stoica,
Angjoo Kanazawa,
Jiahui Lei§,
Haiwen Feng§,
Trevor Darrell
arXiv, 2026
code
/
project page
/
arXiv
|
|
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
Junyi Zhang,
Charles Herrmann*,
Junhwa Hur*,
Chen Sun,
Ming-Hsuan Yang,
Forrester Cole,
Trevor Darrell,
Deqing Sunâ€
ECCV, 2026
code
/
project page
/
arXiv
|
|
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
arXiv, 2026
code
/
project page
/
arXiv
/
dataset & models
|
|
Visual Imitation Enables Contextual Humanoid Control
Arthur Allshire*,
Hongsuk Choi*,
Junyi Zhang*,
David McAllister*,
Anthony Zhang,
Chung Min Kim,
Trevor Darrell,
Pieter Abbeel,
Jitendra Malik,
Angjoo Kanazawa
CoRL, 2025 (Oral, Best Student Paper Award)
code
/
project page
/
arXiv
|
|
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng*,
Junyi Zhang*,
Qianqian Wang,
Yufei Ye,
Pengcheng Yu,
Michael J. Black,
Trevor Darrell,
Angjoo Kanazawa
ICCV, 2025
code
/
project page
/
arXiv
|
|
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
Junyi Zhang,
Charles Herrmann+,
Junhwa Hur,
Varun Jampani,
Trevor Darrell,
Forrester Cole,
Deqing Sun*,
Ming-Hsuan Yang*
ICLR, 2025 (Spotlight)
code
/
project page
/
arXiv
/
poster
|
|
DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo
Junzhe Zhu*,
Yuanchen Ju*,
Junyi Zhang,
Muhan Wang,
Zhecheng Yuan,
Kaizhe Hu,
Huazhe Xu
ICLR, 2025 (Spotlight)
code
/
project page
/
arXiv
|
|
Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
Junyi Zhang,
Charles Herrmann,
Junhwa Hur,
Eric Chen,
Varun Jampani,
Deqing Sun*,
Ming-Hsuan Yang*
CVPR, 2024
code
/ project page
/ arXiv
/ poster
|
|
A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
Junyi Zhang,
Charles Herrmann,
Junhwa Hur,
Luisa F. PolanÃa,
Varun Jampani,
Deqing Sun,
Ming-Hsuan Yang
NeurIPS, 2023
code
/ project page
/ arXiv
/ poster
|
|
LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models
Junyi Zhang,
Jiaqi Guo,
Shizhao Sun,
Jian-Guang Lou,
Dongmei Zhang
ICCV, 2023
code & project page
/ arXiv
/ poster
|
|
InteractFusion: Synthesizing Interactive Motions with Noise-Decoupled Diffusion Models
Junyi Zhang and Hongchi Xia (course report only)
Advisor: Dr. Xinpeng Liu and Prof. Yong-Lu Li
CS3327: Virtual Reality and Augmented Display
SJTU, March 2023
Course Report
|
|
DiffStyle: Leverage Diffusion Prior to One-for-All Style Transfer
Junyi Zhang
CS3310: Computer Graphics
SJTU, Dec. 2022
Github / bilibili (in Chinese)
|
|
Physical Intelligence
2026.05 ~ present
San Francisco, CA, USA
Research Intern
Host: XuDong Wang
|
|
Google DeepMind
|
|
University of California, Merced
|
|
Google Research
|
|
Microsoft Research Asia
|
|
Shanghai Jiao Tong University
|
|
Qualcomm Innovation Fellowship, Qualcomm, 2025
|
|
Best Bachelor Thesis (top 1%, ranked 1/200+ in CS department), SJTU, 2024
|
|
Outstanding Graduates of Shanghai (top 3%), SJTU, 2024
|
|
Zhiyuan Outstanding Scholarship (top 5% in honors program), SJTU, 2024
|
|
SenseTime Scholarship (30 undergraduate AI researchers nationwide), SenseTime, 2023
|
Chandler-Chi Family Scholarship (top 5%), SJTU, 2023
|
|
Microsoft Research "Stars of Tomorrow" Certificate (top 10% interns), MSRA, 2022
|
|
Huawei Fellowship (top 1% in honors program), SJTU, 2022
|
|
Fujian Young Talent Merit Scholarship (50 winners in the whole province), Communist Youth League Fujian Committee, 2022
|
|
National Scholarship (top 0.2% nationwide), Ministry of Education of the People's Republic of China, 2021
|
|
Merit Scholarship, A Level (top 1%), SJTU, 2021
|
|
Merit Student Award (top 5%), SJTU, 2021
|
|
Zhiyuan Honors Scholarship (top 5%), SJTU, 2021, 2022, 2023
|
|
Meritorious Winner (top 7%), ICM, 2021
|
|
I am a cinephile. My favorite directors include
Martin Scorsese,
Theodoros Angelopoulos,
Leos Carax,
Jean-Luc Godard,
Paul Thomas Anderson,
and many more. You can find a list of some of my favorite films here.
I was the VP of the student group 'No. 800 Film Society' and hosted several film salons and curated several screening series. I also write reviews on films, books, and games (in Chinese) on Douban.
|
|