Fei Sha

researcher and engineer in artificial intelligence and machine learning

feisha.jpg

1600 Amphitheatre Parkway

Montain View, CA 94093

Work: fsha at google dot com

I work at Google Research.

My research interests are Artificial Intelligence / Machine Learning (AI/ML), and AI for Science / Scientific Machine Learning (SciML), with a specific application focus on AI for Weather and Climate Science. 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 provide research assistantships, postdoc or internship positions there. So please do not inquire those opportunities with me.

I do respond to service requests to the research communities, though my bandwidth is limited.

news

Jul 19, 2024 giving a talk at Future of Machine Learning Symposium
Jul 4, 2024 serving as Program Co-Chair for ICLR 2025
Jul 24, 2023 going to ICML 2023!
Jul 3, 2023 moving my website at USC (last archive) to this one.

selected publications

2024

  1. 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
  2. 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
  3. 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
  4. 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

2023

  1. 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
  2. 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
  3. 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

2022

  1. 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

2019

  1. 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

2016

  1. CVPR
    Synthesized classifiers for zero-shot learning
    Soravit Changpinyo, Weilun Chao, Boqing Gong, and 1 more author
    In Proc. of CVPR, 2016

2013

  1. NeurIPS
    Similarity Component Analysis
    Soravit Changpinyo, Kuan Liu, and Fei Sha
    In Proc. of Annual Conference on Neural Information Processing Systems (NIPS), 2013

2012

  1. 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

2010

  1. NeurIPS
    Unsupervised Kernel Dimension Reduction
    Meihong Wang, Fei Sha, and Michael I. Jordan
    In Proceedings of Neural Information Processing (NIPS), 2010

2007

  1. 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

2003

  1. NAACL-HLT
    Shallow Parsing with Conditional Random Fields
    Fei Sha, and Fernando Pereira
    In Proceedings of Human Language Technology-NAACL 2003, 2003