Ge Yan

Ge Yan 严格

CS PhD student, University of Washington

I am a 3rd-year CS PhD student at University of Washington, advised by Prof. Dieter Fox. I am currently a research intern with the Large Behavior Models team at Toyota Research Institute, and have also spent time at the Allen Institute for AI. Previously, I received my MS degree from UC San Diego, advised by Prof. Xiaolong Wang.

I am building generally capable robot foundation models for open-world dexterous manipulation. My most recent work is Flex-π, a multi-stream world-action model.

Research highlights

Click a video to open its project page.

Flex-π — a multi-stream world-action model: any observed inputs, any generated futures, and a speed–accuracy trade-off you pick at deployment, all from one checkpoint.

DNAct & GNFactor — 3D manipulation policies that distill a neural feature field from a vision foundation model, learning multi-task real-robot skills from few demonstrations.

News

Publications

Sorted by recency. Selected papers are highlighted.

Flex-π: A Multi-Stream World-Action Model with Compute Flexibility
Ge Yan*, Jinghao Liu*, Yuzhi Fan*, Lei Cai, Minwen Liao, Jesse Zhang†, Dieter Fox†
arXiv preprint, 2026
project page / arXiv / code / video / bibtex

Ge Yan, Shun Iwase, Yuzhi Fan, Dieter Fox, Sergey Zakharov, Katherine Liu
Conference on Robot Learning (CoRL), 2026
/ / /
ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
Ge Yan, Jiyue Zhu*, Yuquan Deng*, Shiqi Yang, Ri-Zhao Qiu, Xuxin Cheng, Marius Memmel, Ranjay Krishna†, Ankit Goyal†, Xiaolong Wang†, Dieter Fox†
Conference on Robot Learning (CoRL), 2025
project page / arXiv / code / bibtex
Humanoid Policy ~ Human Policy
Ri-Zhao Qiu*, Shiqi Yang*, Xuxin Cheng*, Chaitanya Chawla*, Jialong Li, Tairan He, Ge Yan, David J. Yoon, Ryan Hoque, Lars Paulsen, Ge Yang, Jian Zhang, Sha Yi, Guanya Shi, Xiaolong Wang
Conference on Robot Learning (CoRL), 2025
project page / arXiv / code / bibtex
DNAct: Diffusion Guided Multi-Task 3D Policy Learning
Ge Yan*, Yueh-Hua Wu*, Xiaolong Wang
International Conference on Intelligent Robots and Systems (IROS), 2025 (Oral)
project page / arXiv / bibtex
LMM-3DP: Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation
Yuelei Li*, Ge Yan*, Annabella Macaluso, Mazeyu Ji, Xueyan Zou, Xiaolong Wang
ICCV Human-Robot-Scene Interaction and Collaboration Workshop, 2025 (Oral)
project page / arXiv / bibtex
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment, [...], Ge Yan, [...] (200+ authors)
International Conference on Robotics and Automation (ICRA), 2024 (Best Paper Award)
project page / code / dataset / bibtex
GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
Yanjie Ze*, Ge Yan*, Yueh-Hua Wu*, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, Xiaolong Wang
Conference on Robot Learning (CoRL), 2023 (Oral)
project page / arXiv / code / bibtex
Image
DMRA: Depth-induced Multi-scale Recurrent Attention Network for RGB-D Saliency Detection
Wei Ji*, Ge Yan*, Jingjing Li, Yongri Piao, Shunyu Yao, Miao Zhang, Li Cheng, Huchuan Lu
IEEE Transactions on Image Processing (TIP), 2022
paper / code / bibtex

Misc

我是天空里的一片云,
偶尔投影在你的波心——
你不必讶异,
更无须欢喜——
在转瞬间消灭了踪影。

你我相逢在黑夜的海上,
你有你的,我有我的,方向;
你记得也好,
最好你忘掉,
在这交会时互放的光亮!
I am a cloud in the sky,
casting random shadow in your mind;
you need not startle,
nor take delight
for I’d forthwith vanish out of your sight.

You and I met at sea in the darkness of night,
You have your destination, I have mine;
You may remember,
though it’d be best if you could forget,
we glowed as our paths crossed and brightly shined.
—— 徐志摩 《偶然》 · Xu Zhimo, «By Chance»