Last Updated:

Sharut Gupta

I am a fourth year Ph.D student at MIT CSAIL advised by Prof. Phillip Isola and Prof. Stefanie Jegelka. Prior to this, I did my undergrad in Mathematics and Computing at Indian Institute of Technology, Delhi (IIT Delhi) during which I was fortunate to be mentored by Prof. Yoshua Bengio for my thesis. I have spent time at Meta Superintelligence Labs (Meta AI), and Google DeepMind.

My research interests broadly lie in multimodal representation learning, robustness and out-of-distribution generalization. Recently, I have been thinking about the role of data from diverse modalities and its implications for unified architectures. I am always happy to discuss new research directions and am open to collaborating. So if you're interested to work on these topics, feel free to reach out to me!

What's New

Publications

Full list at Google Scholar

* denotes equal contribution


Image Description
Canonicalizing Multimodal Contrastive Representation Learning Sharut Gupta*, Sanyam Kansal*, Stefanie Jegelka, Phillip Isola, Vikas Garg
Blog post | Code


Image Description
ReasonCACHE: Teaching LLMs To Reason Without Weight Updates Sharut Gupta, Phillip Isola, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja, Mark Ibrahim, Mohammad Pezeshki
Blog post


Image Description
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola
ICLR 2026 | Blog post | Code
Also at NeurIPS'25 UniReps

Image Description
Sequential-Parallel Duality in Prefix-Scannable Models Morris Yau*, Sharut Gupta*, Valerie Engelmayer, Kazuki Irie, Stefanie Jegelka, Jacob Andreas
ICLR 2026


Image Description
Learning Diffusion Models with Flexible Representation Guidance Chenyu Wang*, Cai Zhou*, Sharut Gupta, Zongyu Lin, Stefanie Jegelka, Stephen Bates, Tommi Jaakkola
NeurIPS 2025 ORAL @FM4LS | Blog post | Code
Oral Presentation at ICML'25 FM4LS
Image Description
Latent Thought Chain Sharut Gupta, Jarred Barber, Dilip Krishnan (Gemini Team, Google DeepMind)
U.S. PATENT
Developed an alternative approach to the traditional chain-of-thought-based reasoning, enhancing the reasoning capabilities of large language models by around 18% over real-world reasoning benchmarks

Image Description
In-Context Symmetries: Self-Supervised Learning through Contextual World Models Sharut Gupta*, Chenyu Wang*, Yifei Wang*, Tommi Jaakkola, Stefanie Jegelka
NeurIPS 2024 ORAL @SSL MIT NEWS MIT PODCAST | Code
Oral Presentation (top 4) at NeurIPS'24 SSL

Image Description
An Information Criterion for Controlled Disentanglement of Multimodal Data Chenyu Wang*, Sharut Gupta*, Xinyi Zhang, Sana Tonekaboni, Stefanie Jegelka, Tommi Jaakkola, Caroline Uhler
ICLR 2025 ORAL @UniReps HONORABLE MENTION | Code
Oral Presentation (top 4) and the Honorable Mention Award at NeurIPS'24 UniReps
Image Description
Understanding the Role of Equivariance in Self-supervised Learning Yifei Wang, Kaiwen Hu, Sharut Gupta, Ziyu Ye, Yisen Wang, Stefanie Jegelka
NeurIPS 2024
Also at ICML'24 TF2M

Image Description
Context is Environment Sharut Gupta, Stefanie Jegelka, David Lopez-Paz, Kartik Ahuja
ICLR 2024 BOOK CHAPTER | Code | Talk
Also at NeurIPS'23 DistShift, NeurIPS'23 R0-FoMo
Image Description
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning Sharut Gupta*, Joshua Robinson*, Derek Lim, Soledad Villar, Stefanie Jegelka
ICLR 2024 | Code | Talk
Also at ICML'23 TAG-ML, NeurIPS'23 SSL
Image Description
Removing Biases from Molecular Representations via Information Maximization Chenyu Wang, Sharut Gupta, Caroline Uhler, Tommi Jaakkola
ICLR 2024 | Code |
Also at NeurIPS'23 New Frontiers of AI for Drug Discovery and Development
Image Description
Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond Tasuku Soma, Khashayar Gatmiry, Sharut Gupta, Stefanie Jegelka
arXiv
Image Description
Collaborative privacy-preserving approaches for distributed deep learning using multi-institutional data Sharut Gupta, Sourav Kumar, Ken Chang, Charles Lu, Praveer Singh, Jayashree Kalpathy-Cramer
RSNA RadioGraphics 2023
Image Description
Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation Farshid Varno, Laya Rafiee, Sharut Gupta, Stan Matwin, Mohammad Havaei
ECCV 2022
Image Description
FL Games: A federated learning framework for distribution shifts Sharut Gupta, Kartik Ahuja, Mohammad Havaei, Niladri Chatterjee, Yoshua Bengio
NeurIPS FL 2022 SPOTLIGHT @FL
Spotlight Presentation at NeurIPS'22 FL Workshop
Image Description
Addressing catastrophic forgetting for medical domain expansion Sharut Gupta, Praveer Singh, Ken Chang, Liangqiong Qu et al.
NeurIPS ML4H 2022 SPOTLIGHT @ML4H | Code | Talk
Spotlight Presentation at NeurIPS'22 ML4H
More Publications

Work Experience


Meta Superintelligence Labs

Research Intern

Manager: Mohammad Pezeshki, Mark Ibrahim

June 2025 - August 2025

Google DeepMind (Gemini)

Student Researcher

Manager: Dilip Krishnan

May 2024 - Sept 2024

Meta AI (FAIR Labs)

Research Intern

Managers: David Lopez-Paz, Kartik Ahuja

May 2023 - Aug 2023

Mila - Quebec AI Institute

Research Intern

Host: Prof. Yoshua Bengio

Sept 2021 - May 2022

Google Research

Software Eng. Intern

Manager: Sriram Lakshminarasimhan

May 2021 - July 2021

Microsoft Research and Development

Research Intern

Manager: Mithun Das Gupta

May 2020 - July 2020

Harvard University (QTIM)

Research Intern

Host: Prof. Jayashree Kalpathy-Cramer

Jan 2020 - May 2021

INRIA

Research Intern

Hosts: Prof. Paul Muhlethaler, Prof. Soumya Banerjee

May 2019 - July 2019

Research Outreach and Leadership

Invited Talks

AI, ML and Computer Vision Meetup, Microsoft and Voxel51 (here)
2026
Annual National Collegiate Research Conference (NCRC) 2026 at Harvard University
2026
Aspen Meeting on Foundation Models!
2025
MIT CSAIL Embodied Intelligence Seminar (here)
2024
NeurIPS Workshop on Self-Supervised Learning - Theory and Practice (here)
2024
NeurIPS Workshop on Federated Learning: Recent Advances and New Challenges (here)
2022
TAG-DS, The Pacific Northwest Seminar on Topology, Algebra, and Geometry in Data Science
2024
The Quantitative Translational Imaging in Medicine (QTIM)
2024
MIT Machine Learning (ML) Tea Seminar series
2024
MIT LIDS and STATS Tea Talks
2024

Research Outreach

WiDS Cambridge Datathon | co-organizer of the WiDS Cambridge Datathon as a part of the global WiDS Conference Datathon (video coverages can be found for 2024 and 2023)
2023-present
TILOS AI Institute | co-organizer of the TILOS Social at NeurIPS'23 and NeurIPS'24
2023-2024
ML Tea, MIT | co-organizer of ML Tea, a weekly seminar series from members of the machine learning community around MIT
2023-2025
The Gradient | editor for biweekly newsletter covering recent AI news and research at the Gradient substack.
2023-2025
NeurIPS | recieved the volunteer award to help organize the NeurIPS conference.
2022

Teaching

Graduate Teaching Assistant, Deep Learning at MIT
Course information can be found here

2024
Instructor, Mysteries of the Hilbert's Hotel, Splash MIT
Taught a class on the Mysteries of Hilbert's Infinite Hotel ("Room" for thought!) to a class of 100 high school students. The slides for the class are available here

2023
Undergraduate Teaching Assistant, Differential Equations at IIT Delhi
Systems of differential equations, Existence and uniqueness theorems for initial value problems of semilinear and nonlinear ODEs, continuous dependence and well-posed ness; Comparison theorems of Sturms, Sturm-Liouville eigenvalue problems; Phase-plane analysis, Linear and Non-linear stability, Liapunov functions and applications;First order Partial differential equations, Method of characteristics, local and global solutions, envelop of solutions, complete and general solutions; Second order equations: Heat and Wave equation, fundamental solutions, method of eigenfunctions, Duhamel's principle. Maximum priciples for Heat and Laplace equation,Greens functions.

2021
Undergraduate Teaching Assistant, Analysis and Design of algorithms at IIT Delhi
Models of computation: RAM and Turing Machines; Algorithm Analysis techniques; Basic techniques for designing algorithms: dynamic programming, divide-and-conquer and Greedy; DFS , BFS and their applications; Some Basic Graph Algorithms; linear time sorting algorithms; NP-Completeness and Approximation Algorithms.

2021
Undergraduate Teaching Assistant, Probability and Stochastic Processes at IIT Delhi
Axioms of probability, Probability space, Conditional probability, Independence, Bayes' rule, Random variable, Some common discrete and continuous distributions, Distribution of Functions of Random Variable, Moments, Generating functions, Two and higher dimensional distributions, Functions of random variables, Order statistics, Conditional distributions, Covariance, Correlation coefficient, conditional expectation, Modes of convergences, Laws of large numbers, Central limit theorem, Definition of Stochastic process, Classification and properties of stochastic processes, Simple Markovian stochastic processes, Gaussian processes, Stationary processes, Discrete and continuous time Markov chains, Classification of states, Limiting distribution, Birth and death process, Poisson process, Steady state and transient distributions, Simple Markovian queuing models (M/M/1, M/M/1/N, M/M/c/N, M/M/N/N, M/M/∞).

2020

Social Engagements & Leadership

Executive Team, MIT EECS Graduate Application Assistance Program (GAAP)
The Graduate Application Assistance Program (GAAP) is a student-run initiative offered by PhD students in the MIT EECS department. It pairs applicants with current student volunteers, who mentor them 1:1 through the graduate application process, meeting periodically with applicants all the way up to the deadline. More information here.

2024-2026
Session Chair, ACM SIGKDD
Chaired the session on Responsible AI as a part of 'Data Science in India', an ACM SIGKDD India Chapter event. More information about this event is available here.

2022
Deputy General Secretary Mentorship, Board for Student Welfare (BSW), IIT Delhi
  • Initialised an auxiliary program to tackle crucial issues of substance abuse, intellectual plagiarism and language issues
  • Co-established the Office of Accessible Education (OAE) providing special assistance for the disabled community
  • Founded research mentorship and journal club at IIT Delhi, which is dedicated towards fostering student research
More information about the board is available here.


2020-2021
Student Representative, IIT Delhi Strategy and Vision Document 2030 Implementation Committee
The IIT Delhi Endowment Fund was launched by the Honourable President of India in 2019, backed by an initial commitment of INR 250 crore by alumni, with a stated goal of raising USD 1 billion over a period of time. Subsequently, IIT Delhi initiated the development of its vision and direction for 2030, with a focus to build and use the Endowment Fund towards achieving these goals. More details can be found here.

2020-2021
Core Team Member, Initiative for Gender Equity and Sensitisation (IGES), IIT Delhi
Initiative for Gender Equity and Sensitisation (IGES), under Indian Institute of Technology, Delhi, aims to create a safe and violence-free educational atmosphere for all, irrespective of diversities in identities of gender, sex, caste, class, ethnicity, language, race, disability and sexual orientation. IGES also advocates a zero tolerance policy against sexual harassment. More information can be found here.

2020-2021
Captain, National Baseball Championship
Captained the state team of Chandigarh at the IndianNational Baseball Championship in 2016.
2016

Generative Coding

Disclaimer: I'm a novice to generative art, and I'm still finding my feet. But I think I'm learning and having fun. In case you find something cool and interesting, or are looking forward to collaborating, please feel free to get in touch with me! It would really mean a lot :)
Here are a few of my attempts at generative art using p5js.