Anqi Li  

 



  ![](/sites/default/files/person/Anqi_Li_Badge.jpg)

  

 Anqi Li completed her Ph.D. in Computer Science & Engineering from the University of Washington in 2023. Before that, she received her Master's degree from Carnegie Mellon University and her Bachelor's degree from Zhejiang University. Her research focuses on bringing sample efficiency and formal performance guarantees to robot learning. Specific research topics include offline reinforcement learning, safe reinforcement learning, learning from human demonstrations, and planning & control with guarantees.



   Research Area(s)

[Robotics](/research-area/robotics)

 

 

  

 Main Field of Interest

[Robotics](/research-area/robotics)

 

  

 Google Scholar

[https://scholar.google.com/citations?user=HG08FCMAAAAJ&hl=en](https://scholar.google.com/citations?user=HG08FCMAAAAJ&hl=en)

 

  

 

 

 



 ### Publications

 

### 2025 

[Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification](/publication/2025-11_do-what-you-say-steering-vision-language-action-models-runtime-reasoning-action)

Yilin Wu, [Anqi Li](/person/anqi-li), [Tucker Hermans](/person/tucker-hermans), [Fabio Ramos](/person/fabio-ramos), Andrea Bajcs, [Claudia Pérez D’Arpino ](/person/cdarpino)



<https://arxiv.org/abs/2510.16281>









### 2024 

[HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation](/publication/2024-11_hamster-hierarchical-action-models-open-world-robot-manipulation)

Yi Li, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, [Caelan Garrett](/person/caelan-garrett), [Fabio Ramos](/person/fabio-ramos), Dieter Fox, [Anqi Li](/person/anqi-li), Abhishek Gupta, [Ankit Goyal](/person/ankit-goyal)



[International Conference on Learning Representations (ICLR)](https://openreview.net/forum?id=xZ6ZrbpBRp)