Jiaheng Hu
胡佳恒

Welcome to my homepage! My name is Jiaheng Hu (Jeff). Starting from Fall 2022, I'm a Computer Science PhD student at UT-Austin, fortunate to be co-advised by Professor Peter Stone and Professor Roberto Martín-Martín. My research interest is in Robot Learning and Reinforcement Learning, with a focus on their applications to Mobile Manipulation.

I obtained my M.S. in Robotics at Carnegie Mellon Univeristy in 2022, supervised by Professor Howie Choset; and graduated summa cum laude from Columbia University with a B.S. in Computer Science in 2020.

Email  /  Google Scholar  /  Twitter  /  LinkedIn  /  Github

profile photo

News


Talks


  • Nov 2024: Towards Building Continually Learning Robot Systems. University of Michigan EECS 542 Guest Lecture
  • Oct 2024: FLaRe: Towards Learning Adaptive Robot Policies. Amazon Science Hub Symposium Student Talk
  • Aug 2024: Towards Building Continually Learning Robot Systems. University of Washington CSE 163 Guest Lecture
  • Aug 2024: Structural Factorization in Robotic Reinforcement Learning. University of Washington Robotics Colloquium
  • Jul 2024: Structural Factorization in Robotic Reinforcement Learning. NVIDIA Seattle Robotics Lab
Publications

*: Equal contribution.     †: Equal advising.

FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning
Jiaheng Hu, Rose Hendrix, Ali Farhadi, Aniruddha Kembhavi, Roberto Martín-Martín, Peter Stone, Kuo-Hao Zeng†, Kiana Ehsani
ICRA (under review), 2025
CoRL X-Embodiment Workshop, 2024, Best Paper Finalist
CoRL LLHomeRobots Workshop, 2024, Oral Spotlight
paper / website / video

SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
Zizhao Wang*, Jiaheng Hu*, Caleb Chuck*, Stephen Chen, Roberto Martín-Martín, Amy Zhang, Scott Niekum, Peter Stone
NeurIPS, 2024
paper / code / project page

Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Jiaheng Hu, Zizhao Wang, Peter Stone†, Roberto Martín-Martín
NeurIPS, 2024
paper / code / project page

Learning to Look: Seeking information for Decision Making via Policy Factorization
Shivin Dass, Jiaheng Hu, Ben Abbatematteo, Peter Stone, Roberto Martín-Martín
CoRL, 2024
paper / project page

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes
Chen Tang*, Ben Abbatematteo*, Jiaheng Hu*, Rohan Chandra, Roberto Martín-Martín, and Peter Stone
Annual Review of Control, Robotics, and Autonomous Systems, 2024
paper

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
DROID Dataset Team
RSS, 2024
paper / project page / data visualizer

Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Open X-Embodiment Collaboration
ICRA, 2024, Best Paper Award
paper / project page / code

ELDEN: Exploration via Local Dependencies
Jiaheng Hu*, Zizhao Wang*, Peter Stone†, Roberto Martín-Martín†
NeurIPS, 2023
paper / poster / video

Causal Policy Gradient for Whole-Body Mobile Manipulation
Jiaheng Hu, Peter Stone, Roberto Martín-Martín
RSS, 2023
paper / website / code / poster
GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation
Jiaheng Hu, Julian Whitman, Howie Choset
CoRL, 2022
paper / code / poster
Large-scale Heterogeneous Multi-Robot Coverage via Domain Decomposition and Generative Allocation
Jiaheng Hu, Howard Coffin, Julian Whitman, Matthew Travers, Howie Choset
WAFR, 2022
paper / code / talk

Modular Robot Design Optimization with Generative Adversarial Networks
Jiaheng Hu, Julian Whitman, Matthew Travers, Howie Choset
ICRA, 2022
paper / code / poster

Communication Learning via Backpropagation in Discrete Channels with Unknown Noise
Benjamin Freed, Guillaume Sartoretti, Jiaheng Hu, Howie Choset
AAAI, 2020
paper

Non-archival & Others
TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation
Shivin Dass, Wensi Ai, Yuqian Jiang, Samik Singh, Jiaheng Hu, Ruohan Zhang, Peter Stone, Ben Abbatematteo, Roberto Martín-Martín
ICRA MoMa Workshop & RSS MoMa Workshop, 2024
project page / arXiv / code

Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI
Emily Jin*, Jiaheng Hu*, Zhuoyi Huang, Ruohan Zhang, Jiajun Wu, Li Fei-Fei, Roberto Martín-Martín
NeurIPS GenPlan Workshop & NeurIPS ALOE Workshop, 2023
paper / poster / code

UT Austin Villa 3D Simulation Robocup 2023
William Macke, Bo Liu, Caroline Wang, Jiaheng Hu, Shuozhe Li, Patrick MacAlpine, Peter Stone
3rd place at RoboCup 2023
paper

Composition Learning in “Modular” Robot Systems
Jiaheng Hu
Master's Thesis, 2022
paper / event

Teleoperated Robot Grasping in Virtual Reality Spaces
Jiaheng Hu, David Watkins, Peter Allen
NEMS, 2021
paper / code

Community Service
Fun Facts
  • I'm a big fan of contract bridge, and have been playing in various tournaments over the years. I won the 2nd place in the 2022 NABC 0-10k pairs, the champion of 2021 GNT flight C representing NYC, and the 1st prize in 2016 Chinese High School National representing my highschool, RDFZ.
  • I play a few video games semi-competitively, including Counter-Strike (MM rank: LE), SGS, and Pokemon (VGC).
  • I actively follow soccer tournaments, especially La Liga and Premier League. I used to play in my highschool varsity, but played less frequently nowadays due to injuries.

Website template source: Jon Barron