Ruihan Yang

I'm currently a first second third-year PhD student at UC San Diego, advised by Prof Xiaolong Wang. Before coming to UC San Diego, I received my B.E. in Software Engineering from Nankai University in 2019

I'm interested in reinforcement learning, machine learning, robotics and some system stuff. Specifically, I'd like to build intelligent agent, which make decision with information coming from different sources

Email  /  CV  /  Google Scholar  /  Github  /  Linkedin

I'm open to discussion or collaboration. Feel free to drop me an email if you're interested in my research.

profile photo
Publication
Neural Volumetric Memory for Visual Locomotion Control
Ruihan Yang,   Ge Yang,   Xiaolong Wang,

CVPR, 2023 (Highlight)
arXiv / Project Page

Utilize 3D structure of the surrounding for visual locomotion over challenging terrain

Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Ruihan Yang*,   Minghao Zhang*,   Nicklas Hansen,   Huazhe Xu,   Xiaolong Wang,

ICLR, 2022 (Spotlight)
RSS VLRR Workshop, 2021 (Spotlight)
arXiv / Project Page / Code

Proposed LocoTransformer for Visual Locomotion with End2End RL

Multi-Task Reinforcement Learning with Soft Modularization
Ruihan Yang,   Huazhe Xu,   Yi Wu,   Xiaolong Wang,

NeurIPS, 2020
ICLR BeTR-RL workshop, 2020(Oral)
arXiv / Project Page / Code

Proposed Soft Modularization for Multi-Task RL to avoid gradient interference between tasks and knowledge Sharing across tasks.

Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization.
Chieko Sarah Imai*,   Minghao Zhang*,   Yuchen Zhang*,   Marcin Kierebiński, Ruihan Yang,   Yuzhe Qin,   Xiaolong Wang,

IROS, 2022
arXiv / Project Page / Code

We propose Multi-Modal Delay Randomization (MMDR) to address the latency from the control pipeline when training with RL agents.

DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Yuzhe Qin*,   Yueh-Hua Wu*,   Shaowei Liu,   Hanwen Jiang, Ruihan Yang,   Yang Fu,   Xiaolong Wang,

ECCV, 2022
arXiv / Project Page / Code

We propose a new platform and pipeline, DexMV (Dexterous Manipulation from Videos), for imitation learning to bridge the gap between computer vision and robot learning.

Preprint
Suphx: Mastering Mahjong with Deep Reinforcement Learning
Junjie Li,   Sotetsu Koyamada,   Qiwei Ye,   Guoqing Liu,   Chao Wang,   Ruihan Yang,  Li Zhao,   Tao Qin,   Tie-Yan Liu,   Hsiao-Wuen Hon

arXiv, 2020
arXiv

Built (Strongest Mahjong AI around the world), now well matched to the top professional human player.

Education
UC San Diego, San Diego, CA

• PhD in Machine Learning • 2021 to Present
• M.S in Computer Science • 2019 to 2021
Nankai University, Tianjin, China

• B.E in Software Engineering • 2015 to 2019
Experience
Allen Institute for AI, Seattle, WA

• Research Intern
• Jun. 2023 ~ Present
Adobe Research, San Jose, CA(Remote)

• Research Intern
• Jun. 2021 ~ Sep.2021
Microsoft Research Asia, Beijing, China

• Research Intern at Machine Learning group
• Mar. 2018 ~ Jun.2019
Professional Service

Conference Reviewer: AAAI-2021 / 2023 / 2024, ICRA-2022 / 2023, ECCV-2022, CVPR-2023, ICCV-2023, NeurIPS-2023, IROS 2023, ICLR 2024

Journal Reviewer: RAL

Teaching Experience

Math 155A, 3D Computer Graphics, UCSD
20Fall, Teaching Assistant

ECE 176, Introduction to Deep Learning & Applications, UCSD
21Winter / 23Winter, Teaching Assistant

Misc

Soccer: Man-United Fans
Gaming: League
Photograph: Novice
Swimming: Novice
Hiking
Driving: Learning Manual


Template from this handsome guy...