Chaoqi Liu
I am currently a student researcher at Stanford and 1X World Model Lab. I got BS from UIUC (2026). I have worked with Yilun Du, Kris Hauser, Yunzhu Li, and Maxim Likhachev. I love robots. I want to do strong science, and help people feel able to do it, too.
I write notes on robotics and AI, and I like building tools that can benefit the community. Feel free to reach out about research ideas, collaborations, or robotics in general.
News
- I'm glad to share that OAT was named The Best/Outstanding Paper Finalist at RSS 2026. Over the past few months, we have been refining and extending OAT; please check out our latest full paper, Ordered Action Tokens for Visuomotor Policy Learning.
- I wrote a new blog post on making scientific figures and slides in the AI era.
- Ordered Action Tokenization (OAT) is accepted. I will present it at RSS 2026 in Sydney.
- Factorized Diffusion Policy (FDP) is accepted to RA-L.
- Hybrid Diffusion Policy (HDP) is accepted to RA-L.
- Multi-Modal Policy Consensus (MMPC) is accepted to ICRA 2026. MMPC explicitly decomposes action space by sensory modality for flexible multimodal fusion. Also check out FDP, which does implicit factorization.
- Localized Graph-Based Neural Dynamics (L-GBND) is accepted. I will present it at ICRA 2026 in Vienna.
- Attend RSS 2025 in Los Angeles.
- Attend ICRA 2025 in Atlanta.
- Check out Heterogeneous Masked Autoregression (HMA), our new real-time action-conditioned robotic video simulator.
- Attend WAFR 2024 in Chicago.
- Present INSATxGCS (IxG) at RSS 2024 in Delft.
Publications
* indicates equal contribution. Representative papers are highlighted.
OAT: Ordered Action Tokenization
Robotics Science and Systems (RSS), 2026
The Best/Outstanding Paper Finalist
Talk at: RoboPapers
Flexible Multitask Learning with Factorized Diffusion Policy
IEEE Robotics and Automation Letters (RA-L), 2026
Spotlight at RSS 2025 2nd Workshop on Semantic Reasoning and Goal Understanding in Robotics [Link]
Multi-Modal Manipulation via Multi-Modal Policy Consensus
IEEE International Conference on Robotics and Automation (ICRA), 2026
Best paper at CVPR 2026 Sense of Space Workshop [Link]
Featured by: Video Friday
Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning
IEEE Robotics and Automation Letters (RA-L), 2026
Localized Graph-Based Neural Dynamics Models for Terrain Manipulation
IEEE International Conference on Robotics and Automation (ICRA), 2026
Implicit Graph Search for Planning on Graphs of Convex Sets
Robotics Science and Systems (RSS), 2024
Open-source Software
praxis-vla
A controlled laboratory for vision-language-action policy research, with environments, policy interfaces, and evaluation utilities for reproducible VLA experiments.
praxis-eval
A simple, efficient, and extensible evaluation framework for robot policies across diverse benchmarks, supporting both local and remote execution.
Blog
How to make scientific figures and slides in the AI era
A proposal to make final research artifacts source-native: explore figures in Python, finish them in TikZ; sketch slides anywhere, ship them as HTML.
How to design action tokens?
How should we design action tokens for autoregressive robot policies? OAT is an ordered, prefix-decodable action representation built to be compact, totally decodable, and easy to model.
Awards and Honors
Bronze Tablet
Highest undergraduate honor at UIUC.
James N. Snyder Award for Scholastic Achievement
Awarded to 2 recipients annually.
I maintained a 4.0 GPA at UIUC; if interested, a complete coursework list is available here.
Professional Service
Reviewer for
- T-ROIEEE Transactions on Robotics
- RA-LIEEE Robotics and Automation Letters
- ICRAIEEE International Conference on Robotics and Automation