Bo Dai

Georgia Tech
Google Ressearch






Address

Contact


Twitter

I am an assistant professor at CSE in Georgia Tech. I am also affiliated with Google DeepMind as a staff research scientist.

My principal research interest lies on Agent AI upon Generative Models, aiming for creating agents with decision-making and planning ability through modeling the world.

CODA E1342A, 756 W Peachtree St NW, Atlanta, GA 30308

  • bodai at cc.gatech.edu    (for general academic work)
  • bodai at google.com    (for Google related work)

daibond_alpha

Experiences

Mar 2023 - NOW

Sep 2018 - NOW

Aug 2013 - Aug 2018

Selected Publications [Google Scholar]

Peer Reviewed Publications

  • Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint
    Haitong Ma, Zhaolin Ren, Bo Dai, Na Li
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2024. Oral
    [ Paper ] [ Website ]

  • BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
    Haotian Sun, Yuchen Zhuang, Wei Wei, Chao Zhang, Bo Dai
    International Conference on Machine Learning (ICML) 2024. Spotlight
    [ Paper ] [ Website ] [ Code ]

  • Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning
    Hongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans, Bo Dai
    International Conference on Machine Learning (ICML) 2024.
    [ Paper ] [ Website ] [ Code ]

  • Ordering-based Conditions for Global Convergence of Policy Gradient Methods
    Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh, Csaba Szepesvari, Dale Schuurmans
    Advances in Neural Information Processing Systems (NeurIPS) 2023. Oral
    [ Paper ]

  • Learning Universal Policies via Text-Guided Video Generation
    Yilun Du*, Mengjiao Yang*, Bo Dai, Hanjun Dai, Ofir Nachum, Joshua B. Tenenbaum, Dale Schuurmans, Pieter Abbeel
    Advances in Neural Information Processing Systems (NeurIPS) 2023. Spotlight
    [ Paper ][ Blog ][ Website ]

  • AdaPlanner: Adaptive Planning from Feedback with Language Models
    Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai, Chao Zhang
    Advances in Neural Information Processing Systems (NeurIPS) 2023.
    [ Paper ][ Code ]

  • Stochastic Gradient Succeeds for Bandits
    Jincheng Mei*, Zixin Zhong*, Bo Dai, Alekh Agarwal, Csaba Szepesvari, Dale Schuurmans
    International Conference on Machine Learning (ICML) 2023.
    [ Paper ]

  • Learning to Optimize with Stochastic Dominance Constraints
    Hanjun Dai, Yuan Xue, Niao He, Yixin Wang, Na Li, Dale Schuurmans, Bo Dai
    International Conference on Artificial Intelligence and Statistics (AISTATS) 2023.
    [ Paper ]

  • Latent Variable Representation for Reinforcement Learning
    Tongzheng Ren, Chenjun Xiao, Tianjun Zhang,
    Na Li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans, Bo Dai

    International Conference on Learning Representations (ICLR) 2023.
    [ Paper ][Website][ Code ]

  • Discrete Langevin Samplers via Wasserstein Gradient Flow
    Haoran Sun, Hanjun Dai, Bo Dai, Haomin Zhou, Dale Schuurmans
    International Conference on Artificial Intelligence and Statistics (AISTATS) 2023.
    [ Paper ]

  • A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning
    Tongzheng Ren, Tianjun Zhang, Csaba Szepesvari, Bo Dai
    Conference on Uncertainty in Artificial Intelligence (UAI) 2022.
    [ Paper ]

  • Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach
    Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao and Wei Wei
    Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021.
    [ Paper ] [ Code ]

  • CoinDICE: Off-Policy Confidence Interval Estimation
    Bo Dai*, Ofir Nachum*, Yinlam Chow, Lihong Li, Csaba Szepesvari, Dale Schuurmans
    Advances in Neural Information Processing Systems (NeurIPS) 2020. Spotlight
    [ Paper ] [ Code ]

  • Differentiable Top-k Operator with Optimal Transport
    Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister
    Advances in Neural Information Processing Systems (NeurIPS) 2020.
    [ Paper ] [ Code ]

  • DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
    Ofir Nachum*, Yinlam Chow*, Bo Dai, Lihong Li
    Advances in Neural Information Processing Systems (NeurIPS) 2019. Spotlight
    [ Paper ] [ Code ]

  • Exponential Family Estimation via Adversarial Dynamics Embedding
    Bo Dai*, Zhen Liu*, Hanjun Dai*, Niao He, Arthur Gretton, Le Song, Dale Schuurmans
    Advances in Neural Information Processing Systems (NeurIPS) 2019.
    [ Paper ] [ Code ]

  • SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
    Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song
    International Conference on Machine Learning (ICML) 2018. Long Oral
    [ Paper ]

  • Syntax-Directed Variational Autoencoder for Structured Data.
    Hanjun Dai*, Yingtao Tian*, Bo Dai, Steven Skiena and Le Song
    International Conference on Learning Representations (ICLR) 2018
    [ arxiv ] [ Code ]

  • Learning from Conditional Distributions via Dual Embeddings
    Bo Dai, Niao He, Yunpeng Pan, Byron Boots, Le Song
    International Conference on Artificial Intelligence and Statistics (AISTATS) 2017.
    [ Paper ]

  • Discriminateive Embeddings of Latent Variable Models for Structured Data.
    Hanjun Dai, Bo Dai and Le Song
    International Conference on Machine Learning (ICML) 2016.
    [ arxiv ] [ Code ]

  • Provable Bayesian Inference via Particle Mirror Descent.
    Bo Dai, Niao He, Hanjun Dai and Le Song
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2016. Best Paper
    [ Paper ]

PhD Thesis

  • Learning over Functions, Distributions and Dynamics via Stochastic Optimization.
    Bo Dai, 2018
    [ Thesis ]

Teaching

CSE 6243, Advanced Machine Learning, Fall 2024, Georgia Tech

CSE 6243, Advanced Machine Learning, Fall 2023, Georgia Tech

Reinforcement Learning via Optimization Lens, Summer 2021, ETH & EPFL

Reinforcement Learning via Optimization Lens, Fall 2020, Google Brainiversity

CSE 6740, Machine Learning, Spring 2015/Fall 2016, Georgia Tech

Selected Awards

AISTATS Best Paper Award, 2016

NeurIPS Machine Learning for Molecules and Materials workshop Best Paper Award, 2017

Ross Fellowship, 2011-2012

Summa Cum Laude, Nanjing University

National Scholarship, Nanjing University

Team

Current Students

Haotian Sun, Georgia Tech CSE PhD

Yitong Li, Georgia Tech CS Master

Dmitry Shribak, Georgia Tech ECE PhD

Former Members

Jincheng Mei, UAlberta PhD, Research Scientist at Google Brain

Chenjun Xiao, UAlberta PhD, Assistant Professor at CUHK, Shenzhen

Zhuangdi Zhu, MSU PhD, Assistant Professor at George Mason University

Tongzheng Ren, UT Austin PhD, Quantitative Researcher at Citadel Securities

Software

Representation-based Reinforcement Learning : The implementation of our research on provable and practical reinforcement learning algorithms for general stochastic nonlinear dynamics through the representation lens.
[ Webpage ] [ Code ]

Services

Action Editor of Transactions on Machine Learning Research (TMLR)

(Senior) Area Chair of top conferences for multiple years between 2019-2024: NeurIPS, ICML, ICLR, AISTATS

Co-organizer of Workshop on Evaluations and Assessments of Neural Conversation Systems at EMNLP 2021

Co-organizer of Workshop on Reinforcement Learning at Google, 2021

Co-organizer of Optimization Foundations of Reinforcement Learning Workshop at NeurIPS 2019