Yiqi Wang

I am a master student in robotics (MSR) at Robotics Institute, Carnegie Mellon University (CMU), supervised by Prof. Jeff Schneider. Previously, I am an ECE master student (CMU) worked with Prof. Yuejie Chi and Prof. Chris Atkeson. I received my BS from University of Wisconsin-Madison in Computer Science, and worked as an undergraduate researcher at Informatics Skunkworks, under the supervision of Prof. Dane Morgan.

Email  /  Resume (Feb 2024)  /  Google Scholar  /  Github  / 

profile photo


Research Interests


I interested in developing sample-efficient algorithms for robot learning. This includes:

  1. How to learn priors (i.e., a model) from existing data that are unstructured (e.g., images, videos), and across embodiments (robots, human)?
  2. How to leverage the learned priors to improve downstream robot learning, and become more sample efficient?
Since robot data has to be explicitly collected in the real world, it can never match the size of the visual data online (in the wild), that contains useful information regarding common objects and live spaces. Capable of learning from these data could lead to prior with basic "understanding" on common objects/scenes, easily adaptable to a new task or robot. It will help the downstream robot to make better decisions (e.g., exploits or explores). The technique I'm looking at are World Models and Model-Based Control.



Projects

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
Yiqi Wang, Mrinal Verghese, Jeff Schneider,
Under Review, 2025
[paper]

Scalable Dynamic Resource Allocation via Domain Randomized Reinforcement Learning
Yiqi Wang, Laixi Shi, Martin Hyungwoo Lee, Jaroslaw Sydir, Zhu Zhou, Yuejie Chi, Bin Li,
IEEE GLOBECOM, 2024
[paper] [poster]

A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning
Yiqi Wang, Mengdi Xu, Laixi Shi, Yuejie Chi,
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, (UAI), 2023
[paper] [code] [presentation]

Automatic Speech Recognition Meets Language Modeling
Yiqi Wang, Jianyu Mao, Aditya Rathod, [code]

Website template from Jon Barron.