Yixuan Huang

I am a Postdoctoral Research Associate at Princeton University, working with Professor Tom Silver. I completed my Ph.D. in the Kahlert School of Computing at the University of Utah, where I was advised by Professor Tucker Hermans. During my Ph.D., I was a Visiting Student Researcher (VSR) at Stanford University, working with Professor Jeannette Bohg. I got my bachelor's degree in Computer Science and Engineering from Northeastern University in 2020. During my undergraduate years, I worked with Professor Sicun Gao at UC San Diego.

Yixuan Huang
Yixuan Huang
Postdoctoral Researcher
Princeton University

Research

I aim to build robots that continually expand their physical capabilities through experience: solving unfamiliar tasks, acquiring reusable skills, and adapting to new environments, embodiments, and users. My research bridges slow reasoning and real-time execution: robots reason to solve novel physical problems, distill solutions into reusable visuomotor policies, and learn from deployment failures to expand their capabilities over time. My past work has explored three key components of this reasoning-to-capability cycle:

  1. Enabling reasoning from raw sensor data: Learn models and skills to enable hierarchical planning directly from partial-view point clouds.
  2. Turning reasoning into real-time, reusable capabilities: Leverage planning to supervise and improve robot foundation models.
  3. Learning from failures during deployment: Develop robot systems that can continuously learn and adapt during their deployment.

News

Publications

*Equal contribution. †Student mentored by me.

TAMP learning survey figure
Learning By and For Task and Motion Planning: A Survey

Yixuan Huang*, Benned Hedegaard*, Naman Shah, Siddharth Srivastava, George Konidaris, Tom Silver
In Submission, 2026

TANDEM: Task and Motion Planning with As-Needed Demonstrations for Efficient Vision-Language-Action Model Fine-tuning

Samrat Sahoo*†, Liang Ji*†, Tom Silver, Yixuan Huang
In Submission, 2026
project page / arXiv / code

DATAFARM: Distribution-Aligned Task and Motion Planning for Fine-Tuning Vision-Language-Action Models

Samrat Sahoo†, Yixuan Huang, Tom Silver
In Submission, 2026
project page / arXiv / code

Coding Agents for Generalized Task and Motion Planning Problems

Matteo Merler, Bowen Li, Josh Roy, Yichao Liang, Qianwei Wang, Yixuan Huang, Tom Silver
In Submission, 2026
project page / arXiv

Chaining visuomotor skills figure
Chaining Visuomotor Skills for Constrained Manipulation Through Perceptual Manipulation

Hao Wang†, Yixuan Huang, Somil Bansal, Tom Silver
In Submission, 2026
project page

SPECTRE: Skeleton Priority Estimation Conditioned on TAMP Refinement Evidence

Jiacheng Xu†, Yixuan Huang, Tom Silver
In Submission, 2026
project page

Skeleton-conditioned base placement figure
Skeleton-Conditioned Base Placement Evaluation for Long-Horizon Mobile Manipulation

Qihang Li†, Yixuan Huang, Tom Silver, Peng Gao
In Submission, 2026

KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning

Yixuan Huang*, Bowen Li*, Vaibhav Saxena*, Yichao Liang, Utkarsh Aashu Mishra, Liang Ji†, Lihan Zha, Jimmy Wu, Nishanth Kumar, Sebastian Scherer, Danfei Xu, Tom Silver
Robotics: Science and Systems (RSS), 2026
project page / arXiv / code

RoboVista figure
RoboVista: Evaluating Vision Language Models for Diverse Robot Applications

Shuangyu Xie*, Kaiyuan Chen*, Ziyang Chen, Simeon Adebola, Yixuan Huang, Zehan Ma, Tianshuang Qiu, Wentao Yuan, Dhruv Shah, Pannag R Sanketi, Ken Goldberg
Robotics: Science and Systems (RSS), 2026
project page / arXiv

LAP: Language-Action Pre-training Enables Zero-Shot Cross-Embodiment Transfer

Lihan Zha, Asher James Hancock, Mingtong Zhang, Tenny Yin, Yixuan Huang, Dhruv Shah, Allen Z. Ren, Anirudha Majumdar
Robotics: Science and Systems (RSS), 2026
project page / arXiv / code

Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-Language Models

Mingen Li, Houjian Yu, Yixuan Huang, Youngjin Hong, Hantao Ye, Changhyun Choi
IEEE International Conference on Robotics and Automation (ICRA), 2026
Best Paper Award on Robot Learning -- Finalist
project page / arXiv

Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference

Yixuan Huang, Novella Alvina†, Mohanraj Devendran Shanthi, Tucker Hermans
Conference on Robot Learning (CoRL), 2025
project page / arXiv

Points2Plans: From Point Clouds to Long-Horizon Plans with Composable Relational Dynamics

Yixuan Huang, Christopher Agia, Jimmy Wu, Tucker Hermans, Jeannette Bohg
IEEE International Conference on Robotics and Automation (ICRA), 2025
project page / arXiv / code

Latent Space Planning for Multi-Object Manipulation with Environment-Aware Relational Classifiers

Yixuan Huang, Nichols Crawford Taylor†, Adam Conkey, Weiyu Liu, Tucker Hermans
IEEE Transactions on Robotics (T-RO), 2024
project page / arXiv / code

Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models

Yixuan Huang, Jialin Yuan, Chanho Kim, Pupul Pradhan†, Bryan Chen, Li Fuxin, Tucker Hermans
IEEE International Conference on Robotics and Automation (ICRA), 2024
project page / arXiv

Planning for Multi-Object Manipulation with Graph Neural Network Relational Classifiers

Yixuan Huang, Adam Conkey, Tucker Hermans
IEEE International Conference on Robotics and Automation (ICRA), 2023
project page / arXiv / code

Toward Learning Context-Dependent Tasks from Demonstration for Tendon-Driven Surgical Robots

Yixuan Huang, Michael Bentley, Tucker Hermans, Alan Kuntz
International Symposium on Medical Robotics (ISMR), 2021
Best Paper Award -- Finalist, Best Student Paper Award -- Finalist
project page / arXiv