Fei Sha

Scientist and engineer in artificial intelligence and machine learning

1 Meta Way

Menlo Park, CA 94025

Work: feisha at meta dot com

I am an AI Research Scientist at Meta.

I was a research scientist at Google Research.

My research interests are Artificial Intelligence / Machine Learning (AI/ML), and AI for Science / Scientific Machine Learning (SciML). At Google Research, I lead a team of scientists and engineers, working in those directions.

I was a Professor of Computer Science at University of Southern California (USC). I no longer offer research assistantships, postdoc or internship positions there. So please do not inquire those opportunities with me.

I do respond to service requests from research communities, including writing reference letters, serving on (grant) panels and editorial boards, organizing conferences. My bandwidth is limited so I apologize in advance if your request is not responded promptly.

Latest: my talk on our recent work on AI for Fluid Dynamics

news

Sep 15, 2026	keynote talk at 2nd Intl’ Symp. on AI and Fluid Mechanics
Sep 2, 2025	invited talk at Open SkAI 2026, NSF AI Institute for Astronomical Science
Jun 19, 2025	invited talk at U Chicago Institute for Mathematical and Statistical Innovation
Feb 3, 2025	seminar talk at Georgia Tech School of Mathematics
Nov 7, 2024	seminar talk at Harvard SEAS Widely Applied Mathematics Seminar
Oct 25, 2024	seminar talk at Cornell CS’s AI Seminar
Jul 19, 2024	invited talk at Future of Machine Learning Symposium
Jul 4, 2024	starting to serve as Program Co-Chair for ICLR 2025
Jun 4, 2024	opening lecture at Platform for Advanced Scientific Computing 2024
Jul 24, 2023	going to ICML 2023!

selected publications

2025

PNAS

Dynamical-generative downscaling of climate model ensembles

Ignacio Lopez-Gomez, Zhong Yi Wan, Leonardo Zepeda-Núnez, and 3 more authors

PNAS, 2025

@article{lopezgomez25r2d2,
  title = {Dynamical-generative downscaling of climate model ensembles},
  author = {Lopez-Gomez, Ignacio and Wan, Zhong Yi and Zepeda-N\'{u}nez, Leonardo and Schneider, Tapio and Anderson, John and Sha, Fei},
  year = {2025},
  volume = {122},
  number = {17},
  journal = {PNAS},
  pmid = {40279391}
}

2024

Sci. Adv.

Generative emulation of weather forecast ensembles with diffusion models

Lizao Li, Robert Carver, Ignacio Lopez-Gomez, and 2 more authors

Science Advances, 2024

@article{li24seeds,
  author = {Li, Lizao and Carver, Robert and Lopez-Gomez, Ignacio and Sha, Fei and Anderson, John},
  title = {Generative emulation of weather forecast ensembles with diffusion models},
  journal = {Science Advances},
  volume = {10},
  number = {13},
  year = {2024},
  pmid = {38552014}
}

ICML

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems

Yair Schiff, Zhong Yi Wan, Jeffrey B. Parker, and 4 more authors

In Proc. of ICML, 2024

@inproceedings{schiff24dyslim,
  title = {DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems},
  author = {Schiff, Yair and Wan, Zhong Yi and Parker, Jeffrey B. and Hoyer, Stephan and Kuleshov, Volodymyr and Sha, Fei and Zepeda-Nunez, Leonardo},
  year = {2024},
  booktitle = {Proc. of ICML},
}

NAACL

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models

Tiwalayo Eisape, Michael Tessler, Ishita Dasgupta, and 3 more authors

In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics, 2024

@inproceedings{eisape24syllogistic,
  title = {A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models},
  author = {Eisape, Tiwalayo and Tessler, Michael and Dasgupta, Ishita and Sha, Fei and Steenkiste, Sjoerd and Linzen, Tal},
  booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2024},
}

JAMES

WeatherBench 2: A Benchmark for the Next Generation of Data-Driven Global Weather Models

Stephan Rasp, Stephan Hoyer, Alexander Merose, and 15 more authors

Journal of Advances in Modeling Earth Systems, 2024

@article{rasp24weatherbench,
  author = {Rasp, Stephan and Hoyer, Stephan and Merose, Alexander and Langmore, Ian and Battaglia, Peter and Russell, Tyler and Sanchez-Gonzalez, Alvaro and Yang, Vivian and Carver, Rob and Agrawal, Shreya and Chantry, Matthew and Ben Bouallegue, Zied and Dueben, Peter and Bromberg, Carla and Sisk, Jared and Barrington, Luke and Bell, Aaron and Sha, Fei},
  title = {WeatherBench 2: A Benchmark for the Next Generation of Data-Driven Global Weather Models},
  journal = {Journal of Advances in Modeling Earth Systems},
  volume = {16},
  number = {6},
  year = {2024},
  doi = {10.1029/2023ms004019}
}

2023

NeurIPS

Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

Anudhyan Boral, Zhong Yi Wan, Leonardo Zepeda-Nunez, and 5 more authors

In Advances in Neural Information Processing Systems, 2023

@inproceedings{boral23les,
  author = {Boral, Anudhyan and Wan, Zhong Yi and Zepeda-Nunez, Leonardo and Lottes, James and Wang, Qing and Chen, Yi-Fan and Anderson, John and Sha, Fei},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Oh, A. and Naumann, T. and Globerson, A. and Saenko, K. and Hardt, M. and Levine, S.},
  pages = {69270--69283},
  publisher = {Curran Associates, Inc.},
  title = {Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations},
  volume = {36},
  year = {2023},
}

NeurIPS

Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models

Zhong Yi Wan, Ricardo Baptista, Anudhyan Boral, and 4 more authors

In Advances in Neural Information Processing Systems, 2023

@inproceedings{wan23debias,
  author = {Wan, Zhong Yi and Baptista, Ricardo and Boral, Anudhyan and Chen, Yi-Fan and Anderson, John and Sha, Fei and Zepeda-N\'{u}\~{n}ez, Leonardo},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Oh, A. and Naumann, T. and Globerson, A. and Saenko, K. and Hardt, M. and Levine, S.},
  pages = {47749--47763},
  publisher = {Curran Associates, Inc.},
  title = {Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models},
  volume = {36},
  year = {2023}
}

ICLR

Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems

Zhong Yi Wan, Leonardo Zepeda-Núñez, Anudhyan Boral, and 1 more author

In ICLR, 2023

@inproceedings{wan23evolve,
  author = {Wan, Zhong Yi and Zepeda-N\'{u}\~{n}ez, Leonardo and Boral, Anudhyan and Sha, Fei},
  title = {Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems},
  booktitle = {ICLR},
  year = {2023},
}

2022

ICLR

Mention Memory: incorporating textual knowledge into Transformers through entity mention attention

Michiel Jong, Yury Zemlyanskiy, Nicholas FitzGerald, and 2 more authors

In ICLR, 2022

@inproceedings{dejong22mention,
  title = {Mention Memory: incorporating textual knowledge into Transformers through entity mention attention},
  author = {de Jong, Michiel and Zemlyanskiy, Yury and FitzGerald, Nicholas and Sha, Fei and Cohen, William},
  booktitle = {ICLR},
  year = {2022},
}

2019

ICML

Actor-Attention-Critic for Multi-Agent Reinforcement Learning

Shariq Iqbal, and Fei Sha

In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, 2019

@inproceedings{iqbal19acc,
  author = {Iqbal, Shariq and Sha, Fei},
  editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  title = {Actor-Attention-Critic for Multi-Agent Reinforcement Learning},
  booktitle = {Proceedings of the 36th International Conference on Machine Learning,
                 {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
  series = {Proceedings of Machine Learning Research},
  volume = {97},
  pages = {2961--2970},
  publisher = {{PMLR}},
  year = {2019},
}

2016

CVPR

Synthesized classifiers for zero-shot learning

Soravit Changpinyo, Weilun Chao, Boqing Gong, and 1 more author

In Proc. of CVPR, 2016

@inproceedings{changpinyo16zero,
  author = {Changpinyo, Soravit and Chao, Weilun and Gong, Boqing and Sha, Fei},
  title = {Synthesized classifiers for zero-shot learning},
  booktitle = {Proc. of CVPR},
  year = {2016},
}

2013

NeurIPS

Similarity Component Analysis

Soravit Changpinyo, Kuan Liu, and Fei Sha

In Proc. of Annual Conference on Neural Information Processing Systems (NIPS), 2013

@inproceedings{chanpingyo13sca,
  author = {Changpinyo, Soravit and Liu, Kuan and Sha, Fei},
  title = {Similarity Component Analysis},
  booktitle = {Proc. of Annual Conference on Neural Information Processing Systems (NIPS)},
  year = {2013},
}

2012

CVPR

Geodesic Flow Kernel for Unsupervised Domain Adaptation

Boqing Gong, Yuan Shi, Fei Sha, and 1 more author

In Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012

@inproceedings{gong12gfk,
  author = {Gong, Boqing and Shi, Yuan and Sha, Fei and Grauman, Kristen},
  title = {Geodesic Flow Kernel for Unsupervised Domain Adaptation},
  booktitle = {Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  address = {Providence, Rhode Island},
  year = {2012}
}

2010

NeurIPS

Unsupervised Kernel Dimension Reduction

Meihong Wang, Fei Sha, and Michael I. Jordan

In Proceedings of Neural Information Processing (NIPS), 2010

@inproceedings{wang10ukdr,
  author = {Wang, Meihong and Sha, Fei and Jordan, Michael I.},
  title = {Unsupervised Kernel Dimension Reduction},
  booktitle = {Proceedings of Neural Information Processing (NIPS)},
  year = {2010},
}

2007

NeurIPS

Large margin hidden Markov models for automatic speech recognition

Fei Sha, and Lawrence K. Saul

In Advances in Neural Information Processing Systems 19, 2007

@inproceedings{sha07hmm,
  author = {Sha, Fei and Saul, Lawrence K.},
  title = {Large margin hidden {M}arkov models for automatic speech recognition},
  booktitle = {Advances in Neural Information Processing Systems 19},
  year = {2007},
  editor = {Sch\"{o}lkopf, B. and Platt, J.C. and Hofmann, T.},
  pages = {1249--1256},
  address = {Cambridge, MA},
  publisher = {MIT Press},
  owner = {feisha},
}

2003

NAACL-HLT

Shallow Parsing with Conditional Random Fields

Fei Sha, and Fernando Pereira

In Proceedings of Human Language Technology-NAACL 2003, 2003

@inproceedings{sha03shallow,
  author = {Sha, Fei and Pereira, Fernando},
  title = {Shallow Parsing with Conditional Random Fields},
  booktitle = {Proceedings of Human Language Technology-NAACL 2003},
  year = {2003},
  pages = {213--220},
  address = {Edmonton, Canada}
}