Yuandong Tian web metrics

Research Scientist and Senior Manager
Meta/Facebook Artificial Intelligence Research (FAIR)
Email: yuandong [at] fb [dot] com

Brief Bio

Yuandong Tian is a Research Scientist and Senior Manager in Meta/Facebook AI Research (FAIR), working on deep reinforcement learning, representation learning and optimization. He is the recipient of 2021 ICML and 2013 ICCV . He is the lead scientist and engineer for project. Prior to that, he worked in Google Self-driving Car team in 2013-2014 and received a Ph.D in Ph.D in Robotics Institute, Carnegie Mellon University in 2013.

See my Google Scholar and CV.

Research Directions: Reinforcement Learning and Search, Representation Learning


[Jan. 24, 2022] 3 ICLR papers are accepted!

[Sep. 28, 2021] 4 NeurIPS papers are accepted!

[Jul. 19, 2021] Our paper got ICML Outstanding Paper Award Honorable Mention!

[Jun. 4, 2021] Invited talk in University of Washington (NeurolAI Lab) about . Slides here. Thanks Eli Shlizerman for inviting!

[May. 8, 2021] Three ICML papers are accepted as Long Oral (, and )! Thanks all the collaborators!

[Apr. 29, 2021] is accepted in SIGCOMM 2021.

[Apr. 21, 2021] Invited Guest Lecture in UPenn (Thanks Jing Li for the invitation). Slides here.

[Apr. 21, 2021] Invited talk in VALSE Webinar about understanding self-supervised learning. Slides here.

[Apr. 12, 2021] Invited Talk in UCL DARK Lab. Slides here.

[Feb. 28, 2021] Two papers on Neural Architecture Search are accepted in CVPR 2021. Thanks all the collaborators!

[Jan. 31, 2021] In Black-box optimization challenge of NeurIPS'20, two teams extended our and won 3rd and 8th place! See their reports (JetBrains, KAIST)

[Jan. 22, 2021] is accepted in AIStat!

[Dec. 12, 2020] Contributed talk in NeurIPS 2020 workshop of Self-supervised Learning, Theory and Practice.

[Dec. 12, 2020] Invited talk in NeurIPS 2020 workshop of Learning meets Combinatorial Algorithms.

[Nov. 30, 2020] Invited Talk (Slides) at Workshop of Reinforcement Learning from Batch Data and Simulation in Simons Institute of UC Berkeley

[Oct. 20, 2020] Invited Guest Lecture in University of Wisconsin Madison (Class syllabus: link)

[Oct. 14, 2020] Distinguished Guest Lecture in IIIS, Tsinghua University.

[Sep. 26, 2020] and are accepted in NeurIPS!

[Jun. 6, 2020] Invited guest lecture in UCLA (online)

[Jun. 1, 2020] (a solo author paper) is accepted in ICML 2020!

[Nov. 7, 2019] Invited Talk in IAS "Workshop on New Directions in Reinforcement Learning and Control" in Princeton University.

[Nov. 6, 2019] Invited Talk in NEC Laboratories Princeton.

[Oct. 27, 2019] Invited Talk in AI Sys Workshop in SOSP'19.

[Jun. 2019] Long oral talk about OpenGo in ICML 2019.

[Jan. 2019] Talks in Deep Learning Summit, AAAI 2019 Workshops (Reproducible AI and Game and Environments in Artificial Intelligence)

[Jan.-Jun. 2018]. Multiple talks in Stanford, AI NextCon, etc. link

[Dec. 20, 2017]. Keynote at Future Leaders of AI Retreat (FLAIR), Shanghai. link

[Dec. 6, 2017]. Oral talk about ELF platform, NIPS 2017, Long Beach. link

[Nov. 5, 2017]. DRL and Game Tutorial in AI Frontier, Santa Clara. link.

[Oct. 27, 2017]. DRL and Game Tutorial in Mountain View, ACMMM 2017 Slides.

Aug. 10, 2017. Presentation in Video Games and Machine Learning (VGML) Workshop, ICML 2017. Slides. The same talk is also presented in University of Sydney on Aug. 11, hosted by Dong Xu.

[Aug. 8, 2017]. "An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis", ICML 2017. Slides

[Jun. 30, 2017 - Jul. 9, 2017]. "AI In Games: Achievements and Challenges", 5 talks in China (Beijing, Shanghai, Shenzhen). Slides.
  • Jun. 30, 2017, Chinese Academia of Science, Institute of Automation (CASIA)
  • Jun. 30, 2017, Tsinghua University, State Key Laboratory of Intelligent Technology and Systems
  • Jul. 4, 2017. ShanghaiTech Symposium on Information Science and Technology (SSIST) 2017. link
  • Jul. 6, 2017. Brain-AI workshop. link
  • Jul. 9, 2017. CCF-GAIR 2017 link

Reinforcement Learning and Search

Multi-objective Optimization by Learning Space Partitions [arXiv]
Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo, Yuandong Tian
ICLR 2022

Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages [arXiv][Code]
Xinyun Chen, Dawn Song, Yuandong Tian
NeurIPS 2021

Learning Space Partitions for Path Planning [arXiv][Code]
Kevin Yang*, Tianjun Zhang*, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian
NeurIPS 2021

NovelD: A Simple yet Effective Exploration Criterion [arXiv][3 min video][code]

(old name: BeBold)
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
NeurIPS 2021

MADE: Exploration via Maximizing Deviation from Explored Regions [arXiv][code]
Tianjun Zhang*, Paria Rashidinejad*, Jiantao Jiao, Yuandong Tian, Joseph Gonzalez, Stuart Russell
NeurIPS 2021

Few-shot Neural Architecture Search [arXiv][Code]
Yiyang Zhao*, Linnan Wang*, Yuandong Tian, Rodrigo Fonseca, Tian Guo (*=Equal Contribution)
ICML 2021 (Long Oral)

Network Planning with Deep Reinforcement Learning [paper][code]
Hang Zhu (JHU), Varun Gupta, Satyajeet Singh Ahuja, Yuandong Tian, Ying Zhang, Xin Jin (PKU)

Multi-Agent Collaboration via Reward Attribution Decomposition [arXiv][Code][3 min video][Website]
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
arXiv 2020

Joint Policy Search for Multi-agent Collaboration with Imperfect Information [arXiv][Code][3 min video]
Yuandong Tian, Qucheng Gong, Tina Jiang
NeurIPS 2020

Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search [arXiv][Code]
Linnan Wang, Rodrigo Fonseca, Yuandong Tian
NeurIPS 2020

Sample-Efficient Neural Architecture Search by Learning Action Space [arXiv][Code]

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2021

Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero [arXiv][Code][Pre-trained models and game records][Other resources][Blogpost][Talk]

A open source reimplementation of DeepMind's zero-knowledge training and its application to the game of Go. Trained on 2000 GPUs for 9 days. With a single GPU and 50 seconds per move, the model won 20-0 versus 4 top 30 professional players, given human unlimited thinking time. It also won 980-18 versus LeelaZero (version Apr. 25).

ICML 2019 (Long Oral)

Yuandong Tian, Jerry Ma*, Qucheng Gong*, Shubho Sengupta*, Zhuoyuan Chen, James Pinkerton, Larry Zitnick

Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees [Link][Code]
Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma
ICLR 2019

M^3RL: Mind-aware Multi-agent Management Reinforcement Learning [Link][Code]
Tianmin Shu, Yuandong Tian
International Conference on Learning Representations (ICLR), 2019

Building Generalizable Agents with a Realistic and Rich 3D Environment [Arxiv Link][Code]
Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
Workshop in International Conference on Learning Representations (ICLR), 2018

ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games [Link][Repo][Demo]
Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, Larry Zitnick
Advances in Neural Information Processing Systems (NIPS), 2017
Oral presentation[link]

Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning [Link]
Yuxin Wu, Yuandong Tian
International Conference on Learning Representations (ICLR), 2017

Better Computer Go Player with Neural Network and Long-term Prediction [arXiv Page] [poster] [Code] [Pre-trained Models]
Yuandong Tian, Yan Zhu
International Conference on Learning Representations (ICLR), 2016

Understanding Representation Learned by Neural Networks

Deep Contrastive Learning is Provably (almost) Principal Component Analysis [arXiv]
Yuandong Tian
Arxiv 2022

Understanding Dimensional Collapse in Contrastive Self-supervised Learning [arXiv]
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
ICLR 2022

Understanding Self-supervised Learning Dynamics without Contrastive Pairs
[arXiv][3min video][Code][ICML Long talk][Slides for ICML Long talk]

Yuandong Tian, Xinlei Chen, Surya Ganguli

ICML 2021 (Outstanding Paper Award Honorable Mention) [link]

Understanding Self-supervised Learning with Dual Deep Networks [arXiv][3min video][Code]
Yuandong Tian, Lantao Yu, Xinlei Chen, Surya Ganguli

Understanding Robustness in Teacher-Student Setting: A New Perspective[arXiv]
Zhuolin Yang*, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian* (*=Equal Contribution)
AIStats 2021

Student Specialization in Deep ReLU Networks With Finite Width and Input Dimension [arXiv][Talk][Code]
Yuandong Tian
ICML 2020

Luck Matters: Understanding Training Dynamics of Deep ReLU Networks [arXiv][Workshop Poster][Code]

Yuandong Tian, Tina Jiang, Qucheng Gong, Ari Morcos
ICML 2019 workshop on Understanding and Improving Generalization in Deep Learning

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP [arXiv]

Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos
ICLR 2020

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers [arXiv]

Ari S. Morcos, Haonan Yu, Michela Paganini, Yuandong Tian
NeurIPS 2019

A Theoretical Framework for Deep Locally Connected ReLU Network [ArXiv link][Poster]
Yuandong Tian
Arxiv preprint, 2018

Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima [ArXiv link]
Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabas Poczos, Aarti Singh
International Conference on Machine Learning (ICML), 2018 (Long Oral)

When is a Convolutional Filter Easy To Learn? [ArXiv link][OpenReview]
Simon S. Du, Jason D. Lee, Yuandong Tian
International Conference on Learning Representations (ICLR), 2018

An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis [Link][ICLR Workshop version][Code]
Yuandong Tian
International Conference on Machine Learning (ICML), 2017

Other topics

Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing
Cheng Fu, Hanxian Huang, Xinyun Chen, Yuandong Tian, Jishen Zhao (UCSD)
ICML 2021 (Long Oral)
Semantic Amodal Segmentation [arXiv Page]
Yan Zhu, Yuandong Tian, Dimitris Mexatas, Piotr Dollár
Computer Vision and Pattern Recognition (CVPR), 2017
Single Image 3D Interpreter Network [arXiv Page]
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
European Conference on Computer Vision (ECCV), 2016
Oral presentation
Simple Baseline for Visual Question Answering [arXiv Page]
Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
ArXiv preprint, 2016

PhD work

Highlight: ICCV'13 Marr Prize Honorable Mentions

Theory and Practice of Globally Optimal Deformation Estimation[PDF]
Yuandong Tian, PhD thesis, CMU-RI-TR-13-25
Theory and Practice of Hierarchical Data-driven Descent for Optimal Deformation Estimation[PDF]
Yuandong Tian, Srinivasa G. Narasimhan,
International Journal of Computer Vision (IJCV), 2015
Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation[PDF][Detailed Proofs]
Yuandong Tian, Srinivasa G. Narasimhan,
ICCV 2013 Marr Prize Honorable Mentions
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation [PDF] [Evaluation Code][Project Page]
Yuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan,
Accepted as Poster in ECCV 2012
Learning from Crowds in the Presence of Schools of Thought [PDF][Dataset][Code][Presentation]
Yuandong Tian, Jun Zhu,
Depth from Optical Turbulence [Project Page]
Yuandong Tian, Srinivasa G. Narasimhan, Alan J. Vannevel
Accepted as Poster in CVPR 2012
Globally Optimal Estimation of Nonrigid Image Distortion[PDF]
Yuandong Tian, Srinivasa G. Narasimhan,
International Journal of Computer Vision (IJCV), As an extended version of [Tian and Narasimhan, CVPR 2010].
Rectification and 3D reconstruction of Curved Document Images [Project Page]
Yuandong Tian, Srinivasa G. Narasimhan,
Oral presentation in CVPR 2011

Local Isomorphism to Solve the Pre-image Problem in Kernel Methods
Dong Huang, Yuandong Tian, Fernando De la Torre
Accepted as Poster in CVPR 2011
A Globally Optimal Data-Driven Approach for Image Distortion Estimation [Project Page]
Yuandong Tian, Srinivasa G. Narasimhan,
Oral presentation in CVPR 2010

Seeing through water: Image restoration using model-based tracking [Project Page]
Yuandong Tian, Srinivasa G. Narasimhan,
Accepted as Poster in ICCV 2009
(De) Focusing on Global Light Transport for Active Scene Recovery
Mohit Gupta, Yuandong Tian, Srinivasa G. Narasimhan, Li Zhang
Oral presentation in CVPR 2009

Relationship between projector defocus and global illumination for statistically-modeled scenes. [Project Page]
Yuandong Tian, Mohit Gupta, Srinivasa G. Narasimhan, Li Zhang
Technical Report CMU-RI-TR-09-10, Carnegie Mellon University, March 2009.

Old Stuff

Easytoon: an easy and quick tool to personalize a cartoon storyboard using family photo album
Shifeng Chen, Yuandong Tian, Fang Wen, Ying-Qing Xu, Xiaoou Tang
ACMMM 2008 [PDF]
A Face Annotation Framework with Partial Clustering and Interactive Labeling
Yuandong Tian, Wei Liu, Rong Xiao, Fang Wen, Xiaoou Tang
Accepted as Poster in CVPR 2007 [PDF]
Homebrew programming on Sony PSP (Playstation Portable)
Short Notes on Graphcut and MRF
Yuandong Tian, 2009
A short introduction to Riemann Geometry
Yuandong Tian, 2009
Some notes in Pattern Recognition and Machine Learning
Yuandong Tian, 2008

知乎专栏/Column in Zhihu



2021年2月完结 博士们的科幻故事。
2012年1月完结 一群年轻人的奇幻冒险故事。
使命/The Goal
(English Version)
2008年11月 与人闲聊时有感而发。遂于忙碌之中匆匆写下。
优秀 2007年4月 我们都算是传统意义上的“好”学生,但鲜花和掌声总有一天会逝去,或是因为我们不够优秀,或是因为我们已不在意优秀。那究竟是什么支撑着人在孤寂的道路中前行?
非人之错 2006年 有些事情,不是人力所能改变的。不是人改变了世界,而是世界改变了人。



业余时间做研究的心得 2014年4月 在谷歌无人车组时业余时间做研究的心得。
数学的用处 2013年11月 以一个工科研究者的观点阐述下数学的用处。
如何学好理工科 2014年4月 如何学好理工科
博士五年总结 2013年9月 博士毕业后对博士研究的总结。
关于数学和Research的几篇短文 2008年7月 对数学和研究的一些粗浅见解。
我的CVPR历程 2007年1月 熬出第一篇一作CVPR的酸甜苦辣。金榜题名时,辛苦有谁知。
旅游记闻 2005年1月 2004年赴美交换顺便旅游的记闻及所思所想,四人同行,为期三周,足迹遍布美国的东西海岸。
我在Purdue的学习体会 2005年1月 2004年赴美国Purdue大学交换的学习体会,中外对比。
走向成功之点滴 2003年7月 大二时应唐氏基金会之约而写,说是为了一本名叫“走向成功”的书准备材料。这是一本给弟弟妹妹们励志的书,然而我却没写如何克服困难攀上顶峰之类励志的文。因为我想第一永远只有一个,剩下的人该如何面对那才是最重要的。