Yash Mehta

yashsmehta95[at]gmail.com

Welcome to my academic website! I’m an engineer at heart with a deep learning background and a computer science degree. Currently, I’m pursuing a PhD in computational cognitive science at Johns Hopkins University and am a visiting PhD student at Harvard Medical School. My goal is to apply ideas from cognitive science to develop more advanced and effective AI systems in healthcare. Although my journey has been unconventional, it has been extremely rewarding. I’ve been fortunate to work on exciting projects alongside passionate and brilliant scientists, which has inspired me and shaped my approach to research. Some of the areas I have worked on include transformers, LLMs, neuroscience, and cognition. Prior to embarking on my research career, I worked briefly as a developer at Amazon.

I am deeply passionate about mentoring and guiding students interested in research. Each week, I set aside some time to chat with aspiring researchers. If you’d like to have a conversation, feel free to reach out to me directly.

w/ Mick Bonner

w/ Pranav Rajpurkar

w/ James Fitzgerald
Jan Funke

w/ Frank Hutter

w/ Tim Lillicrap, Peter Latham

w/ Erik Cambria

News

Oct 15, 2023	Update. Started at Harvard Medical School with Pranav Rajpurkar to work on knowledge graphs for automated radiology report generation 🏥
Sep 1, 2023	Talk. “Multimodal Foundation Models @ICML’23” at SenticLab in NTU Singapore!
Aug 19, 2023	Visit. Research visit to the Flatiron Institute and PolymathicAI team - multimodal foundation models for science!
Jul 20, 2023	Conference. Attended ICML 2023 in Hawaii! 🏄🏻‍♂️🌸
Mar 23, 2023	General. My application for US immigration has been approved under EB1A category - individual of outstanding ability! 🇺🇸
Dec 1, 2022	Conference. Co-presented work on node perturbation at NeurIPS 2022 in New Orleans! ✨🎷
Oct 1, 2022	Visit. 1 month as a student researcher in Larry Abbott’s lab at the Zuckerman Institute, Columbia University! 🗽
May 27, 2022	Got Married!
May 1, 2022	Editorial. Our special issue “Future-generation personality prediction from digital footprints” was accepted at FGCS international journal! Managing guest editor 🤝
Apr 25, 2022	Conference. Presented our NAS-BenchSuite paper on neural architecture search at ICLR’22.
Jan 10, 2022	Update. Started at HHMI Janelia Research Campus working on modeling synaptic plasticity with James Fitzgerald and Jan Funke 🪰
Nov 1, 2021	Teaching. Co-created attention and transformers module with Prof. Frank Hutter. Also served as TA for Deep Learning Lab, and Deep Learning MSc. courses.
Oct 15, 2020	Update. Joined the AutoML group with Frank Hutter at University of Freiburg, Germany, to work on neural architecture search.
Jan 10, 2019	Update. Joined Gatsby Unit, UCL in London as a Research Assistant working on biologically plausiblle credit assignment algorithms with Peter Latham and Tim Lillicrap (DeepMind)! ⚡️🙌🏼
Jul 15, 2018	Update. Started working at Amazon as a software development engineer in Bangalore.
Jul 1, 2018	Update. Graduated in Computer Science from BITS Pilani Goa! 🎓
Jan 15, 2018	Update. Started undergraduate research thesis with Erik Cambria on using large language models for personality trait prediction.

Selected Publications

NeurIPS

Towards Biologically Plausible Convolutional Networks

Roman Pogodin, Yash Mehta, Timothy Lillicrap, and Peter Latham

In Advances in Neural Information Processing Systems (NeurIPS) 2021

Bib PDF Code

@inproceedings{pogodin2021towards,
  title = {Towards Biologically Plausible Convolutional Networks},
  author = {Pogodin, Roman and Mehta, Yash and Lillicrap, Timothy and Latham, Peter},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {34},
  year = {2021},
}

ICLR

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, and 5 more authors

In International Conference on Learning Representations (ICLR) 2022

Bib PDF Code

@inproceedings{mehta2022bench,
  title = {NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy},
  author = {Mehta, Yash and White, Colin and Zela, Arber and Krishnakumar, Arjun and Zabergja, Guri and Moradian, Shakiba and Safari, Mahmoud and Yu, Kaicheng and Hutter, Frank},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
}

NeurIPS

Stability and Scalability of Node Perturbation Learning

Naoki Hiratani, Yash Mehta, Timothy Lillicrap, and Peter Latham

In Advances in Neural Information Processing Systems (NeurIPS) 2022

Bib PDF Code

@inproceedings{hiratani2022stability,
  title = {Stability and Scalability of Node Perturbation Learning},
  author = {Hiratani, Naoki and Mehta, Yash and Lillicrap, Timothy and Latham, Peter},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
}