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

I just 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 dissertation focused on jointly interpreting how systems like the human brain and neural NLP models process language. During my PhD, I was supported by fellowships from the Dingwall Foundations of Language and UT Austin Graduate School. My dissertation recently won an award from the Society for the Neurobiology of Language!

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 shaileejain at utexas.edu} (P.S shailee at cs.utexas.edu is no longer funtional!). I also tweet sometimes (working on it!) (well, I guess it’s mastodon now). You can find my CV here.

Recent News

• August, 2023:
  • Check out our new preprint on investigating temporal processing in the brain w/ interpretable LMs.
  • Moved to SF and started as a postdoc at the Chang lab!
• July, 2023:
  • Honored to receive the Dissertation Award from the Society for the Neurobiology of Language.
  • I just defended my PhD, hoorah! A big thank you to my wonderful advisor, committee, collaborators, friends and family!
• May, 2023:
  • Our large-scale fMRI dataset paper was accepted at Nature Scientific Data! [OpenNeuro] & [Code]
  • New preprint with Microsoft Research on model interpretability in language models and the brain!
  • Stoked that my SNL’23 symposium proposal was accepted— “Can we investigate linguistic modularity in the brain with non-modular NLP systems?” See you in Marseille!
• April, 2023: Our new decoding study in Nature Neuroscience was featured in NYT, NPR, Scientific American, CNBC, NBC & more! Here are my inputs in Stat News & CBS Austin.
• January, 2023:
  • Our op piece on in silico experimentation with LM-based encoding models is now out in NoL!
  • Our paper on decoding language from the brain was accepted at Nature Neuroscience!
• December, 2022:
  • Very excited to be selected for the Miller Research Grant from UC Berkeley!
  • I finally set up my mastodon.
• October, 2022: TWO new preprints! Reconstruting speech from fMRI & a large-scale naturalistic language fMRI dataset
• August, 2022: Awarded the William Orr Dingwall Foundations of Language fellowship. Thank you, Dingwall foundation!
• May, 2022: Our work on self-supervised speech models for language encoding was accepted at ICML!
• March, 2022: Excited to be a speaker at the “Mechanisms, functions, and methods for diversity of neuronal and network timescales” workshop @ COSYNE’22
• Oct, 2021:
  • Presenting new work at SNL’21 on doing meta-science with temporally controlled LSTMs.
  • Excited to be selected for and attend the MIT EECS Rising Stars workshop :)
  • Presenting new(-ish) work at MPI’s Combinatorics’21 on investigating semantic integration across cortex. [Best poster award!]
• Sept, 2021 - Our work on investigating language in the cerebellum was accepted at Journal of Neuroscience!
• May, 2021 - Our ICLR workshop ‘How Can Findings About The Brain Improve AI Systems?’ is live!
• April, 2021 - Awarded the UT Austin Graduate School Summer Fellowship (2021)

Publications

(*equal contribution)

1. 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 (to appear) [PDF]
2. Semantic reconstruction of continuous language from non-invasive brain recordings
   J. Tang, A. LeBel, S. Jain and A. G. Huth
   Nature Neuroscience (to appear) [PDF]
3. 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 (to appear) [PDF]
4. 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]
5. Voxelwise encoding models show that cerebellar language representations are highly conceptual
   A. LeBel, S. Jain and A. G. Huth
   Journal of Neuroscience 2021 [PDF]
6. 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]
7. 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]
8. 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]
9. 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]
10. 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. Discovering distinct patterns of semantic integration across cortex using natural language encoding models for fMRI
   S. Jain and A. G. Huth (in preparation)

Conference Abstracts

1. Mapping the timescales of language representations in the cerebellum
   LeBel, A., S. Jain, Ivry, R. and A. G. Huth
   Society for the Neurobiology of Language (SNL) 2022
2. Semantic reconstruction of continuous language from non-invasive brain recordings
   J. Tang, A. LeBel, S. Jain and A. G. Huth
   Society for the Neurobiology of Language (SNL) 2022
3. Discovering distinct patterns of semantic integration across cortex using natural language encoding models for fMRI
   S. Jain and A. G. Huth [Best poster award]
   Combinatorics, Leipzig Lectures on Language 2021
4. A unifying computational account of temporal processing in natural speech across cortex
   S. Jain, V. A. Vo, N. M. Beckage, H. S. Chien, C. Obinwa and A. G. Huth
   Society for the Neurobiology of Language (SNL) 2021
5. Uncovering compositional semantics in fMRI language encoding with transformers
   S. Jain, A. LeBel and A. G. Huth
   From Neuroscience to Artificially Intelligent Systems (NAISyS), CSHL 2020
6. Natural language encoding models for fMRI reveal distinct patterns of semantic integration across cortex
   S. Jain, A. LeBel and A. G. Huth
   Society for the Neurobiology of Language (SNL) 2020
7. Contextualized Language Information Yields Massive Improvements in Encoding Models for Human fMRI
   S. Jain and A. G. Huth
   Asilomar 2019
   
8. Improving language encoding for fMRI with transformers
   S. Jain, A. LeBel and A. G. Huth
   Society for Neuroscience (SfN) 2019
9. Voxelwise encoding models of the cerebellum during natural speech processing
   A. LeBel, S. Jain and A. G. Huth
   Society for Neuroscience (SfN) 2019
10. Phonological feature and pitch classification with a branched convolutional neural network
    I. M. Griffith, A. LeBel, S. Jain, A. G. Huth, and L. S. Hamilton
    Society for Neuroscience (SfN) 2019 and Advances and Perspectives in Auditory Neuroscience (APAN) 2019

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. NeurIPS, ICLR, ICML, Nature Human Behavior, Neuron (assisted) - Reviewer
2. Memory in Artificial and Real Intelligence (MemARI) - Workshop Organizer (NeurIPS 2022)
3. How Can Findings About The Brain Improve AI Systems? - Workshop Organizer (ICLR 2021)
4. Context & Compositionality in Biological and Artificial Neural Systems - Workshop Organizer (NeurIPS 2019)
5. Women In Computer Science (WiCS) @UT Austin - Graduate Mentor (2019, 2020, 2023)
6. UT CS Masters Admissions Committee (2021, 2022)

In the Press

• Language decoding (Tang et al.): NYT, NPR, Scientific American, CNBC, NBC, Stat News & CBS Austin.
• Inspired AI Inspires Insights About The Brain (And Vice Versa) Texas Advanced Computing Center Brain 2019
• How AI Is Deepening Our Understanding of the Brain SingularityHub