Research Interests
My core interest is in developing practical theory of machine learning that pushes principled algorithm design towards real-world applications. I work closely with domain experts to understand the frontier challenges in applied machine learning, distill those challenges into mathematically precise formulations, and develop novel methods to tackle them.

My fundamental research is largely focused on the following areas:
  • Neurosymbolic AI, bulding AI systems that elegantly blend learning with symbolic models and reasoning, leading to greater efficiency and generalization than using learning alone.
  • AI for Experts, building AI systems that maximize productivity of expert engineers and scientists, including how experts communicate with AI systems (both teaching the AI system, and interpreting the resulting models).
  • Autonomous Decision Making, building AI systems that can make decisions autonomously, often with guarantees such as safety, stability, or robustness. Applications include robotics and control systems, and experiment design.
[curriculum vitae]
Selected Papers
(see Google Scholar for up-to-date publication list)

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
Dan Zhang, Sining Zhoubian, Ziniu Hu, Yisong Yue, Yuxiao Dong, Jie Tang
Neural Information Processing Systems (NeurIPS), 2024
[arxiv]

Active Learning-Assisted Directed Evolution
Jason Yang, Ravi G. Lal, James C. Bowden, Raul Astudillo, Mikhail A. Hameedi, Sukhvinder Kaur, Matthew Hill, Yisong Yue, Frances H. Arnold
[bioRxiv]

A Foundation Model for Cell Segmentation
Uriah Israel, Markus Marks, Rohit Dilip, Qilin Li, Morgan Sarah Schwartz, Elora Pradhan, Edward Pao, Shenyi Li, Alexander Pearson-Goulart, Pietro Perona, Georgia Gkioxari, Ross Barnowski, Yisong Yue, David Ashley Van Valen
[bioRxiv][service]

Automatic Gradient Descent: Deep Learning without Hyperparameters
Jeremy Bernstein, Chris Mingard, Kevin Huang, Navid Azizan, Yisong Yue
[arxiv][code][blog post]

TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis
Sabera Talukder, Yisong Yue, Georgia Gkioxari
[arxiv][code]

Robust Agility via Learned Zero Dynamics Policies
Noel Csomay-Shanklin, William D. Compton, Ivan Dario Jimenez Rodriguez, Eric R. Ambrose, Yisong Yue, Aaron D. Ames
International Conference on Intelligent Robots and Systems (IROS), 2024
[arxiv]

Online Policy Optimization in Unknown Nonlinear Systems
Yiheng Lin, James A. Preiss, Fengze Xie, Emile Anand, Soon-Jo Chung, Yisong Yue, Adam Wierman
Conference on Learning Theory (COLT), 2024
[arxiv]

SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code
Ziniu Hu, Ahmet Iscen, Aashi Jain, Thomas Kipf, Yisong Yue, David A. Ross, Cordelia Schmid, Alireza Fathi
International Conference on Machine Learning (ICML), 2024
(Oral Presentation)
[arxiv]

Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
Yujia Huang, Adishree Ghatare, Yuanzhe Liu, Ziniu Hu, Qinsheng Zhang, Chandramouli S Sastry, Siddharth Gururani, Sageev Oore, Yisong Yue
International Conference on Machine Learning (ICML), 2024
(Oral Presentation)
[arxiv][website]

LyaNet: A Lyapunov Framework for Training Neural ODEs
Ivan Dario Jimenez Rodriguez, Aaron D. Ames, Yisong Yue
International Conference on Machine Learning (ICML), July 2022.
[arxiv][code]

Self-Supervised Keypoint Discovery in Behavioral Videos
Jennifer J. Sun*, Serim Ryou*, Roni Goldshmid, Brandon Weissbourd, John Dabiri, David J. Anderson, Ann Kennedy, Yisong Yue, Pietro Perona
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
[arxiv]

Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
Michael O’Connell*, Guanya Shi*, Xichen Shi, Kamyar Azizzadenesheli, Anima Anandkumar, Yisong Yue, Soon-Jo Chung
Science Robotics, May 2022.
[arxiv][online][code][video][press release]

MLNav: Learning to Safely Navigate on Martian Terrains
Shreyansh Daftry, Neil Abcouwer, Tyler Del Sesto, Siddarth Venkatraman, Jialin Song, Lucas Igel, Amos Byon, Ugo Rosolia, Yisong Yue, Masahiro Ono
IEEE Robotics and Automation Letters (RA-L), May 2022
[conference][journal][video]

End-to-End Sequential Sampling and Reconstruction for MR Imaging
Tianwei Yin*, Zihui Wu*, He Sun, Adrian V. Dalca, Yisong Yue, Katherine L. Bouman
Machine Learning for Health (ML4H), December 2021.
(Best Paper Award)
[arxiv][project]

Neurosymbolic Programming
Swarat Chaudhuri, Kevin Ellis, Oleksandr Polozov, Rishabh Singh, Armando Solar-Lezama, Yisong Yue
Foundations and Trends in Programming Languages, Volume 7: No. 3, pages 158-243, December 2021.
[preprint][online]

Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
Cameron Voloshin, Hoang M. Le, Nan Jiang, Yisong Yue
Neural Information Processing Systems (NeurIPS), December 2021.
[arxiv][code]

Meta-Adaptive Nonlinear Control: Theory and Algorithms
Guanya Shi, Kamyar Azizzadenesheli, Michael O'Connell, Soon-Jo Chung, Yisong Yue
Neural Information Processing Systems (NeurIPS), December 2021.
[arxiv][code]

Task Programming: Learning Data Efficient Behavior Representations
Jennifer J. Sun, Ann Kennedy, Eric Zhan, David J. Anderson, Yisong Yue, Pietro Perona
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021.
(Best Student Paper Award)
[arxiv][code][project]

Online Robust Control of Nonlinear Systems with Large Uncertainty
Dimitar Ho, Hoang M. Le, John Doyle, Yisong Yue
International Conference on Artificial Intelligence and Statistics (AISTATS), April 2021.
[pdf][arxiv]

A General Large Neighborhood Search Framework for Solving Integer Programs
Jialin Song, Ravi Lanka, Yisong Yue, Bistra Dilkina
Neural Information Processing Systems (NeurIPS), December 2020.
[pdf][arxiv][code]

GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learning
Benjamin Rivière, Wolfgang Hoenig, Yisong Yue, Soon-Jo Chung
IEEE Robotics and Automation Letters (RA-L), June 2020.
(Best Paper Nomination)
[pdf][arxiv][demo video]

Preference-Based Learning for Exoskeleton Gait Optimization
Maegan Tucker*, Ellen Novoseller*, Claudia Kann, Yanan Sui, Yisong Yue, Joel Burdick, Aaron D. Ames
International Conference on Robotics and Automation (ICRA), May 2020.
(Best Paper Award)
[pdf][arxiv][demo video][project]

Imitation-Projected Programmatic Reinforcement Learning
Abhinav Verma*, Hoang M. Le*, Yisong Yue, Swarat Chaudhuri
Neural Information Processing Systems (NeurIPS), December 2019.
[pdf][arxiv][code][demo video]

Batch Policy Learning under Constraints
Hoang M. Le, Cameron Voloshin, Yisong Yue
International Conference on Machine Learning (ICML), June 2019.
(Oral Presentation)
[pdf][arxiv][project]

Hierarchical Imitation and Reinforcement Learning
Hoang M. Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III
International Conference on Machine Learning (ICML), July 2018.
[pdf][arxiv][project]

Iterative Amortized Inference
Joseph Marino, Yisong Yue, Stephan Mandt
International Conference on Machine Learning (ICML), July 2018.
[pdf][arxiv][code]

Multi-dueling Bandits with Dependent Arms
Yanan Sui, Vincent Zhuang, Joel Burdick, Yisong Yue
Conference on Uncertainty in Artificial Intelligence (UAI), August 2017.
[pdf][arxiv]

The K-armed Dueling Bandits Problem
Yisong Yue, Josef Broder, Robert Kleinberg, Thorsten Joachims
Conference on Learning Theory (COLT), June, 2009.
[pdf][slides]
Tutorials
  • Imitation Learning, co-taught with Hoang Le, presented at ICML 2018.
    [link]
  • An Introduction to Ensemble Methods: Bagging, Boosting, Random Forests and More, presented at Disney Research.
    [slides]
  • Practical Online Retrieval Evaluation, co-taught with Filip Radlinski, presented at SIGIR 2011.
    [slides][demo scripts]
  • Learning to Rank, co-taught with Filip Radlinski, presented at NESCAI 2008.
    [part1][part2]
Other Talk Materials
  • Neurosymbolic AI for Safety-Critical Agile Control, Princeton, October, 2024.
    [slides]
  • Learning for Reliable Control in Dynamical Systems, Georgia Tech, March, 2024.
    [slides]
  • Controlling the Structure of Inference and Learning in Neural Networks, Johns Hopkins University, March, 2024.
    [slides]
  • AI for Adaptive Experiment Design, Genentech AI Seminar, Feburary, 2023.
    [slides][older video]
  • Neurosymbolic Programming, Caltech Explainable AI for Science Workshop, September, 2021.
    [slides][video]
  • Personalized Preference Learning from Spinal Cord Stimulation to Exoskeletons, July, 2021.
    [video][slides]
  • Improving Policy Learning via Programmatic Domain Knowledge, Caltech, April, 2021.
    [slides]
  • Competitive Algorithms for Online Control, Simons Institute Workshop for Mathematics of Online Decision Making, October, 2020.
    [slides]
  • Learning to Optimize as Policy Learning, Princeton University, October, 2020.
    [slides]
  • Learning for Safety-Critical Control in Dynamical Systems, Control Meets Learning, January, 2021.
    [slides][video]
  • New Frontiers in Imitation Learning, University of Chicago, November, 2019.
    [slides]
  • Policy Learning with Certifiable Guarantees, University of California Los Angeles, October, 2019.
    [slides]
  • Real-World Bayesian Optimization, KDD 2019 Workshop on Data Collection, Curation, and Labeling for Mining and Learning, August, 2019.
    [slides][video]
  • Two Vignettes in Robust Detection and Adversarial Analysis in Control, CVPR 2019 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems, June, 2019.
    [slides]
  • Structured Imitation and Reinforcement Learning, NeurIPS 2018 Workshop on Imitation Learning for Robotics, December, 2018.
    [slides]
  • Machine Teaching for Human Learners, IJCAI 2018 Workshop on Humanizing AI, July, 2018.
    [slides]
  • Inference + Imitation, ICML 2018 Workshop on Tractable Probabilistic Models, July, 2018.
    [slides]
  • The Dueling Bandits Problem, Massachusetts Institute of Technology, September, 2017.
    [slides]
  • Learning to Optimize for Structured Output Spaces, University of California Santa Barbara, April, 2017.
    [slides]
  • Recent Applications of Latent Factor Models, Second Spectrum, September, 2015.
    [slides]
  • Learning Spatial Models of Basketball Gameplay, KDD 2015 Workshop on Large-Scale Sports Analytics, August, 2015.
    [slides]
  • Balancing the Explore/Exploit Tradeoff in Interactive Structured Prediction, Cornell University, December, 2014.
    [slides][video]
  • Learning with Humans in the Loop, Disney Research, May, 2013.
    [slides]
  • Optimizing Recommender Systems as a Submodular Bandit Problem, University of Toronto, November, 2012.
    [slides]
  • An Introduction to Structural SVMs and its Application to Information Retrieval, University of California Berkeley, October, 2012.
    [slides]
  • Practical and Reliable Retrieval Evaluation Through Online Experimentation, WSDM 2012 Workshop on Web Search Click Data, February, 2012.
    [slides]
  • An Interactive Learning Approach to Optimizing Information Retrieval Systems, Carnegie Mellon University, September, 2010.
    [slides][video]
  • New Learning Frameworks for Information Retrieval, Microsoft Research, March, 2010.
    [video]
  • Diversified Retrieval as Structured Prediction, SIGIR 2009 Workshop on Redundancy, Diversity and Interdependent Document Relevance, July, 2009.
    [slides]
  • Information Retrieval as Structured Prediction, University of Massachusetts Amherst, April, 2009.
    [slides]
[All Content © 2024 Yisong Yue]