Stone Tao

I am a 2nd-year PhD student at UC San Diego advised by professor Hao Su. I'm grateful to have my research be funded by the NSF Graduate Research Fellowship.

My current research interests revolve around a general goal of building efficient, adaptable, and capable embodied AI. A big chunk of my direction is around scalable datasets/benchmarks for embodied AI by tackling the intersection of simulation and machine learning. To this end, my research revolves around reinforcement learning, simulation, few-shot learning, imitation learning, auto curriculum-learning, as well as high-quality robotics/game benchmarks. If you are interested in working with me / just want to chat about stuff feel free to reach out to my email / twitter!

On the side, I'm also interested in building and running high-quality open-source AI competitions for education and research. I co-founded the Lux AI Challenge and collaborate frequently with Kaggle to build and deliver these AI competitions.

Previously I was an undergraduate at UC San Diego, advised by Hao Su (on robotics and reinforcement learning) and Steven Dow (on AI x HCI). During my undergraduate I interned at QuantCo (machine learning) advised by Ben Thompson and LaunchDarkly (full-stack software engineering).

News

  • Mar, 2025: ManiSkill3 is accepted as an Oral presentation at the ICLR Robot Learning Workshop.
  • Jan, 2025: Two papers accepted to ICLR'25.
  • Dec, 2024: Lux AI Season 3 has started! Compete for a $50,000 prize pool on Kaggle.
  • May, 2024: ManiSkill3 Beta has been released! State-of-the-art fully open-source robotics simulation with the fastest parallel visual simulation, faster than most other simulators. 1000s of FPS for visual RL on just google colab! Comes with a ton of features for teleoperation, rendering, reinforcement learning and more.
  • May, 2023: The NeurIPS edition of Lux AI Challenge Season 2 focusing on large-scale multi-agent RL was accepted to NeurIPS'23 as an Competition!
  • March, 2023: Received the NSF Graduate Research Fellowship!
  • March, 2023: Incoming PhD at UC San Diego advised by Hao Su!
  • February, 2023: Podcast with Kaggle on Lux AI Season 2 and Reinforcement Learning
  • January, 2023: Lux AI Season 2 Started: Check it out!

Publications / Preprints

thumbnail for Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

Xiu Yuan*, Tongzhou Mu*, Stone Tao, Yunhao Fang, Michael Zhang, Hao Su

ICLR 2025

arXiv / project page / code

thumbnail for ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

Stone Tao, Fanbo Xiang, Arth Shukla, Yuzhe Qin, Xander Hinrichsen, Xiaodi Yuan, Chen Bao, Xinsong Lin, Yulin Liu, Tse-kai Chan, Yuan Gao, Xuanlin Li, Tongzhou Mu, Nan Xiao, Arnav Gurha, Zhiao Huang, Roberto Calandra, Rui Chen, Shan Luo, Hao Su

2025 ICLR Robot Learning Workshop, Oral Presentation

arXiv / project page / code

thumbnail for Lux AI Season 3: Lux AI Season 3: Multi-Agent Meta Learning at Scale

Lux AI Season 3: Lux AI Season 3: Multi-Agent Meta Learning at Scale

Stone Tao, Akarsh Kumar, Bovard Doerschuk-Tiberi, Isabelle Pan, Addison Howard, Hao Su

NeurIPS 2024 (Competitions Track)

/ project page / code

thumbnail for Lux AI Season 2 (NeurIPS Edition)

Lux AI Season 2 (NeurIPS Edition)

Stone Tao, Qimai Li, Yuhao Jiang, Jiaxin Chen, Xiaolong Zhu, Bovard Doerschuk-Tiberi, Isabelle Pan, Addison Howard

NeurIPS 2023 (Competitions Track)

/ project page / code

thumbnail for Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

Stone Tao, Xiaochen Li, Tongzhou Mu, Zhiao Huang, Yuzhe Qin, and Hao Su.

ICML 2023

arXiv / project page / code

thumbnail for ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

Jiayuan Gu†, Fanbo Xiang†, Xuanlin Li*, Zhan Ling*, Xiqiang Liu*, Tongzhou Mu*, Yihe Tang*, Stone Tao*, Xinyue Wei*, Yunchao Yao*, Xiaodi Yuan, Pengwei Xie, Zhiao Huang, Rui Chen, Hao Su.

ICLR 2023

arXiv / project page / code

thumbnail for Emergent Collective Intelligence from Massive-Agent Cooperation and Competition

Emergent Collective Intelligence from Massive-Agent Cooperation and Competition

Hanmo Chen*, Stone Tao*, Jiaxin Chen, Weihan Shen, Xihui Li, Sikai Cheng, Xiaolong Zhu, Xiu Li

NeurIPS 2022 Deep RL Workshop

arXiv / code

thumbnail for Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations

Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations

Tongzhou Mu*, Zhan Ling*, Fanbo Xiang*, Derek Cathera Yang*, Xuanlin Li*, Stone Tao, Zhiao Huang, Zhiwei Jia, and Hao Su.

NeurIPS 2021 (Datasets and Benchmark Track)

arXiv / project page / code

Presentations / Talks

Scaling Embodied AI via Simulation and Sim-integrated Robot Learning
Institute for AI Industry Research (AIR), Tsinghua University, Jan, 2025
Slides (pptx), PDF

ManiSkill3: Scalable Simulation+Rendering for Generalizable Embodied AI
ECHO AI Talk, October, 2024 / Recording
CVPR 2024 Embodied AI Workshop, June, 2024

Lux AI Season 2 and Reinforcement Learning
Kaggle Podcast, Feb, 2023 / Recording

AI Competition Design For Multi-Agent Environments / Games
Kaggle Podcast, Nov, 2022
Learning in Foundation Environments (LIFE), Oct, 2022
Slides

Pinned Projects

Awards

NSF Graduate Research Fellowship (2023-)

Awarded the NSF Graduate Research Fellowship for my proposal on sample efficient, scalable robotic learning and human robot interaction. Receiving $147,000 in funding over 3 years.

UCSD CSE Award for Excellence in Leadership

Received the annual award for demonstrated excellence in leadership inside and outside of UCSD

UCSD CSE Alumni Advisory Board Leadership Excellence Scholarship

Awarded scholarship in 2021 and 2022 for demonstration of leadership at UCSD and outside of UCSD

MIT Battlecode (AI Competition)

MIT Battlecode 2021 | Finalist, 9th overall, Won the Adapative Strategy Award - Jan. 2021 | Bot Code | Post Mortem

MIT Battlecode 2020 | Finalist, 5th overall, top soloist - Jan. 2020 | Bot Code | Post Mortem

MIT Battlecode 2019 | Finalist, 9th overall, 4th out of high school teams - Jan. 2019 | Bot Code

Halite AI Competition

Halite 3 | Placed 66th out of 4000+ students and professionals globally. Achieved admiral status by placing above Two Sigma's base bot. 5th placed high school student out of 500+ HS students. 1st place JavaScript bot. - Nov. 2018 to Jan. 2019