Fei Sha
researcher and engineer in artificial intelligence and machine learning
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
- Sci. Adv.
- ICMLDySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic SystemsIn Proc. of ICML, 2024
- NAACLA Systematic Comparison of Syllogistic Reasoning in Humans and Language ModelsIn Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics, 2024
- JAMESWeatherBench 2: A Benchmark for the Next Generation of Data-Driven Global Weather ModelsJournal of Advances in Modeling Earth Systems, 2024
2023
- NeurIPSNeural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential EquationsIn Advances in Neural Information Processing Systems, 2023
- NeurIPSDebias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion ModelsIn Advances in Neural Information Processing Systems, 2023
- ICLREvolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated SystemsIn ICLR, 2023
2022
- ICLRMention Memory: incorporating textual knowledge into Transformers through entity mention attentionIn ICLR, 2022
2019
- ICMLActor-Attention-Critic for Multi-Agent Reinforcement LearningIn Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, 2019
2016
- CVPR
2013
- NeurIPSSimilarity Component AnalysisIn Proc. of Annual Conference on Neural Information Processing Systems (NIPS), 2013
2012
- CVPRGeodesic Flow Kernel for Unsupervised Domain AdaptationIn Proceedings of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012
2010
- NeurIPSUnsupervised Kernel Dimension ReductionIn Proceedings of Neural Information Processing (NIPS), 2010
2007
- NeurIPSLarge margin hidden Markov models for automatic speech recognitionIn Advances in Neural Information Processing Systems 19, 2007
2003
- NAACL-HLTShallow Parsing with Conditional Random FieldsIn Proceedings of Human Language Technology-NAACL 2003, 2003