Jiaheng Hu

Jiaheng Hu
胡佳恒

Welcome to my homepage! My name is Jiaheng Hu (Jeff). I'm a final year PhD candidate in CS at UT-Austin, fortunate to be co-advised by Prof. Peter Stone and Prof. Roberto Martín-Martín. My research is generously supported by the Two Sigma PhD Fellowship. During my PhD, I spent time as research intern at Amazon FAR (current), Google Deepmind, and Allen AI.

Before my PhD, I completed a fully funded M.S. in Robotics at CMU and earned my undergraduate degree in computer science from Columbia University, graduating summa cum laude. I'm also a student representative of the IEEE/RAS Mobile Manipulation TC.

In my free time, I enjoy playing bridge and soccer. See Fun Facts for details!

Email / Google Scholar / Twitter / LinkedIn / Github

Experience

FAR

DeepMind

Allen AI

UT-Austin

CMU RI

Columbia

Research

I research Robot Learning and Reinforcement Learning. My long-term goal is to develope continually self-improving robots that can learn and adapt autonomously in unstructured environments over a long period of time. Nowadays, I'm particularly interested in post-training of generalist robot policies (e.g. VLAs, LLM agents).

News

June 2026: Honored to serve as an Area Chair for CoRL 2026.
May 2026: Joined Amazon FAR as a Research Intern.
June 2025: Gave a talk at Google Deepmind on Self-Improving Robots.
Apr 2025: I am honored to be awarded the Two Sigma PhD Fellowship!
Apr 2025: I am selected for the ICRA Doctoral Consortium this year.
Nov 2024: Guest lecture at University of Michigan on Continually Learning Robots.
Aug 2024: Two talks at Nvidia SRL and University of Washington on Factorization in Robotic RL.

Selected Publications (Full list)

*: Equal contribution. †: Equal advising.

	What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents Jiaheng Hu, Mohit Shridhar, Caden Lu, Dhruv Shah, Hao-Tien Lewis Chiang, Jie Tan, Annie Xie arXiv, 2026 paper / website
	Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning Jiaheng Hu, Jay Shim, Chen Tang, Yoonchang Sung, Bo Liu, Peter Stone†, Roberto Martín-Martín† Reinforcement Learning Journal (RLC), 2026 ICRA RL4IL Workshop, 2026, Best Paper Award paper / code
	Factored Latent Action World Models Zizhao Wang, Chang Shi, Jiaheng Hu, Kevin Rohling, Roberto Martín-Martín, Amy Zhang, Peter Stone ICML, 2026 paper
	Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress Priyanka Mandikal, Jiaheng Hu, Shivin Dass, Sagnik Majumder, Roberto Martín-Martín†, Kristen Grauman† ICRA, 2026 CoRL Beyond Rigid Worlds Workshop, 2025, Best Poster Award paper / website
	RoboSSM: Scalable In-context Imitation Learning via State-Space Models Youngju Yoo, Jiaheng Hu, Yifeng Zhu, Bo Liu, Qiang Liu, Roberto Martín-Martín, Peter Stone IROS, 2026 paper / code
	Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input Zifan Xu, Myoungkyu Seo, Dongmyeong Lee, Hao Fu, Jiaheng Hu, Jiaxun Cui, Yuqian Jiang, Zhihan Wang, Anastasiia Brund, Joydeep Biswas, Peter Stone ICRA, 2026 paper
	SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training Jiaheng Hu, Peter Stone, Roberto Martín-Martín CoRL, 2025 paper / code / website / video / press
	L3M+P: Lifelong Planning with Large Language Models Krish Agarwal, Yuqian Jiang, Jiaheng Hu, Bo Liu, Peter Stone IROS, 2025 paper
	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, 2025 CoRL X-Embodiment Workshop, 2024, Best Paper Finalist paper / code / website / video
	Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes Chen Tang, Ben Abbatematteo, Jiaheng Hu, Rohan Chandra, Roberto Martín-Martín, Peter Stone Annual Review of Control, Robotics, and Autonomous Systems, 2025 AAAI SMP Track*, 2025 paper
	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
	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 / video
	Causal Policy Gradient for Whole-Body Mobile Manipulation Jiaheng Hu, Peter Stone, Roberto Martín-Martín RSS, 2023 paper / website / code
	GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation Jiaheng Hu, Julian Whitman, Howie Choset CoRL, 2023 paper / code
	Modular Robot Design Optimization with Generative Adversarial Networks Jiaheng Hu, Julian Whitman, Matthew Travers, Howie Choset ICRA, 2022 paper / code

Community Service

Workshop Organizers:
- 5th Workshop on Mobile Manipulation and Embodied Intelligence, IROS 2026
- Causality for Robotics: Answering the Question of Why, IROS 2023
Conference/Journal:
- Area Chair:
  - CoRL 2026
- PC Member:
  - IJCAI 2024
- Reviewer:
  - NeurIPS, ICLR, ICML, AAAI, IJCAI
  - CoRL, RSS, ICRA, IROS, T-RO, RAL
Teaching Assistant:
- Gateway to Robotics (UT-Austin)
- Robot Learning (UT-Austin)
- Artificial Intelligence (Columbia)
- Computational Robotics (Columbia)

Fun Facts

I'm a big fan of contract bridge, and have been playing in various tournaments over the years. I was a member of the USBF U31 team, and have won GNT flight C champion (Team NYC) and the 2nd place in the NABC 0-10k pairs.
I like video games. Here are some video games I've each spent 1000+ hours on:
- Counter-Strike (Rank: Legendary Eagle)
- San Guo Sha (Here's a video of my game featured by a streamer)
- Pokemon (VGC & All main series games) - check out our pokemon AI!
I actively follow soccer tournaments, especially Premier League (COYG!) and UCL. I used to play in my highschool varsity and am always down for pickup games.

Website template source: Jon Barron