Yisong Yue (he/him)
California Institute of Technology
1200 E. California Blvd.
CMS, 305-16
Pasadena, CA 91125

Office: 303 Annenberg

Contact Information >

I am a professor of Computing and Mathematical Sciences at the California Institute of Technology. My research interests lie primarily in machine learning, and span the entire theory-to-application spectrum from foundational advances all the way to deployment in real systems. 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.


ICLR 2024: I will be serving as the Senior Program Chair at ICLR 2024.

I am committed to promoting diversity, equity, and inclusion in my research group, in my courses, within the CMS department, at Caltech more broadly, and within my research communities.

• Diversity -- I recognize that diversity, in all its shapes and forms, strengthens us both culturally and intellectually.
• Equity -- I will fight for equal treatment of all people, regardless of race, gender, sexual orientation, or any other attributes that do not define a person's academic and research potential.
• Inclusion -- I will work to create an inclusive working environment, so that everyone feels their voices are heard and their contributions are recognized.

Read more about diversity, equity, and inclusion at the CMS Department and EAS Division at Caltech.

My current research interests can be broadly organized into three overlapping groups:

AI for Autonomy: study how AI methods can enable novel capabilities in autonomous systems; characterize and address key technical bottlenecks (e.g., data-driven safety guarantees); deploy in real systems.

Selected Publications

• Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies
  Ivan Dario Jimenez Rodriguez*, Noel Csomay-Shanklin*, Yisong Yue, Aaron D. Ames
  Conference on Learning for Dynamics and Control (L4DC), June 2022.
  [arxiv][video]
• 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]
• 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]

AI for Science: study how AI methods can improve workflows in science and accelerate knowledge discovery; develop methods for automated experiment design and human-intelligible modeling; deploy in real systems.

Selected Publications

• Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings
  Sabera Talukder, Jennifer J. Sun, Matthew Leonard, Bingni W. Brunton, Yisong Yue
  [arxiv]
• 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]
• DeepGEM: Generalized Expectation-Maximization for Blind Inversion
  Angela Gao, Jorge Castellanos, Yisong Yue, Zachary Ross, Katherine Bouman
  Neural Information Processing Systems (NeurIPS), December 2021.
  [pdf][code][project]
• 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]
• 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]

Core AI/ML Research: study the underlying fundamental questions pertaining practical algorithm design, inspired by real-world applications in science and engineering.

Selected Publications

• Automatic Gradient Descent: Deep Learning without Hyperparameters
  Jeremy Bernstein, Chris Mingard, Kevin Huang, Navid Azizan, Yisong Yue
  [arxiv][code]
• Conformal Generative Modeling on Triangulated Surfaces
  Victor Dorobantu, Charlotte Borcherds, Yisong Yue
  [arxiv][project][code]
• 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]
• 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]
• 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]
• Learning Differentiable Programs with Admissible Neural Heuristics
  Ameesh Shah*, Eric Zhan*, Jennifer J. Sun, Abhinav Verma, Yisong Yue, Swarat Chaudhuri
  Neural Information Processing Systems (NeurIPS), December 2020.
  [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]

• ICLR 2024: I will be serving as the Senior Program Chair at ICLR 2024.
  
• Automatic Gradient Descent: We have developed a new hyperparameter-free optimizer for deep neural networks. Our method has been demonstrated at ImageNet scale using ResNet50 architectures. [arxiv][code]
• Conformal Generative Modeling: We have developed a new framework for generative modeling that works on a wide range of manifolds. [project]
  
• Sabbatical at Latitude AI: I have started my role as Principal Scientist at Latitude AI. Read more here.
• ICML 2023: I will be serving as Communications Co-Chair (with Marco Cuturi) for ICML 2023.
• Invited Talk: I recently gave an invited talk at DeepMath 2022 on developing architecture-aware theory & practical algorithms for neural networks. [slides]
  
• Neurosymbolic Programming for Science: we recently put out a position paper on Neurosymbolic Programming for Science. This position is informed by our experience collaborating with scientists: science is an iterative process of analyzing data, proposing hypotheses, and conducting experiments. Because scientists reason more readily in symbolic terms, it is important to develop frameworks that natively inherit both the flexibility of neural networks and the rich semantics of symbolic models.
  
• Farewell! We had four members depart the group during the 2021-2022 Academic Year:
  • Ugo Rosolia completed his postdoc and started as a research scientist at Amazon.
  • Guanya Shi completed his Ph.D. and will start as faculty at CMU.
  • Eric Zhan completed his Ph.D. and started at Argo AI.
  • Jeremy Bernstein completed his Ph.D. and will start as a postdoc at MIT.
  
• Group Assimilation Exercise: I wrote a post about the Group Assimilation Exercise that my group does annually. The goal of the exercise is the lower the barriers to the group for providing me with constructive feedback.
  
• Neural-Fly published in Science Robotics: our work on Neural-Fly has been published in Science Robotics. [article][press release]
  
• Neurosymbolic Programming Summer School (July 11-13 2022 @Caltech): Neurosymbolic programming is an exciting new area at the intersection of Program Synthesis and Machine Learning that aims to learn models that incorporate program-like structure. More info here.