Shailee Jain

Logo

Neuroscience | ML | NLP

Hi there! I am a postdoctoral researcher at the Chang lab in the Department of Neurosurgery, UC San Francisco.

In 2023, I finished my MS/PhD in Computer Science at the Huth Lab, UT Austin where I collaborated with researchers at Google AI Language and Intel Brain-Inspired Computing Lab. My thesis focused on jointly interpreting how systems like the human brain and neural NLP models process language. During my PhD, I was generously supported by fellowships from the Dingwall Foundations of Language and UT Austin Graduate School. I am very grateful to have won the best dissertation award from the Society for the Neurobiology of Language and the Glushko Dissertation Prize from the Cognitive Science Society.

Before that, I did my undergrad at NITK, Surathkal and spent some time with the ML group at Leuphana University, Germany.

I can most effectively be contacted through email {shailee.jain at ucsf.edu or shaileesjain at gmail.com}. I used to tweet but am now on BlueSky. Here are links to my CV and Google Scholar profile.

In light of what is happening to academia in the West, I hope to do my part by guiding young trainees interested in Neuro-AI research. Please feel free to email me with an intro and your questions.

Recent News

Publications

(*equal contribution)

  1. Explaining black box text modules in natural language with language models
    C. Singh, A. R. Hsu, R. Antonello, S. Jain, A. G. Huth, B. Yu, J. Gao NeurIPS XAIA Workshop [PDF]
  2. A natural language fMRI dataset with voxelwise encoding models
    A. LeBel, L. Wagner, S. Jain, A. Adhikari-Desai, B. Gupta, A. Morgenthal, J. Tang, L. Xu and A. G. Huth Nature Scientific Data [PDF]
  3. Semantic reconstruction of continuous language from non-invasive brain recordings
    J. Tang, A. LeBel, S. Jain and A. G. Huth
    Nature Neuroscience) [PDF]
  4. Computational language modeling and the promise of in silico experimentation
    S. Jain, V. A. Vo, L. Wehbe and A. G. Huth
    Neurobiology of Language 2022 [PDF]
  5. Self-supervised models of audio effectively explain human cortical responses to speech
    A. Vaidya, S. Jain and A. G. Huth
    International Conference on Machine Learning (ICML) 2022 [PDF]
  6. Voxelwise encoding models show that cerebellar language representations are highly conceptual
    A. LeBel, S. Jain and A. G. Huth
    Journal of Neuroscience 2021 [PDF]
  7. Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech
    S. Jain, V. A. Vo, S. Mahto, A. LeBel, J. S. Turek and A. G. Huth
    Advances in Neural Information Processing Systems (NeurIPS) 2020 [PDF]
  8. Approximating stacked and bidirectional recurrent architectures with the delayed recurrent neural network
    J. S. Turek, S. Jain, V. A. Vo, M. Capota, A. G. Huth and T. L. Willke
    Proceedings of the 37th International Conference on Machine Learning (ICML) 2020 [PDF]
  9. Incorporating context into language encoding models for fMRI
    S. Jain and A. G. Huth
    Advances in Neural Information Processing Systems (NeurIPS) 2018 [PDF] [Video] [Poster]
  10. Spatial language representation with multi-Level geocoding
    S. Kulkarni*, S. Jain*, M. J. Hosseini, J. Baldridge, E. Ie and L. Zhang
    Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics (SpLU-RoboNLP) @ACL-IJCNLP 2021 [PDF]
  11. Mining user trajectories in electronic text books
    A. Boubekki, S. Jain and U. Brefeld
    Proceedings of the Eleventh Annual International Conference on Educational Data Mining (EDM) 2018 [PDF]

Manuscripts in submission and preparation

(*equal contribution)

  1. A unifying computational account of temporal processing in natural speech across cortex
    V. A. Vo*, S. Jain*, N. M. Beckage, H. S. Chien, C. Obinwa and A. G. Huth (in submission) [PDF]
  2. A generative framework to bridge data-driven models and scientific theories in language neuroscience
    C. Singh, R. Antonello, S. Jain, A. Hsu, J. Gao, B. Yu and A. G. Huth (in submission) [PDF]
  3. Adding noise to model inputs can improve the prediction performance of speech encoding models for fMRI
    C. Obinwa, S. Jain, A. Vaidya and A. G. Huth (in preparation)
  4. Discovering distinct patterns of semantic integration across cortex using natural language encoding models for fMRI
    S. Jain and A. G. Huth (in preparation)

Teaching

  1. CS 342 Neural Networks with Dr. Alex Huth - TA + Guest lecturer
    • Recurrent Neural Networks
    • Language Models [Slides]
  2. NSC 110H Mapping the human cortex with Dr. Alex Huth - Guest lecturer
    • Temporal organization of language in the brain [Slides]

Service

  1. JoCN Forum - Handling Editor
  2. Bay Area Language Interest group (BayLI) - Co-organizer
  3. Can we investigate linguistic modularity in the brain with non-modular NLP systems? - Symposium Organizer (SNL 2023 Paris, France)
  4. Memory in Artificial and Real Intelligence (MemARI) - Workshop Organizer (NeurIPS 2022 New Orleans, USA)
  5. How Can Findings About The Brain Improve AI Systems? - Workshop Organizer (ICLR 2021 virtual)
  6. Context & Compositionality in Biological and Artificial Neural Systems](https://context-composition.github.io) - Workshop Organizer (NeurIPS 2019 Montreal, Canada)
  7. Women In Computer Science (WiCS) @UT Austin - Graduate Mentor (2019, 2020, 2023)
  8. UT CS Masters Admissions Committee (2021, 2022)
  9. NeurIPS, ICLR, ICML, WiML, Nature Human Behavior, Nature Communications, Neuron (assisted), Nature Neuroscience (assisted) - Reviewer

In the Press