Sharut Gupta
I am a second year Ph.D student at MIT CSAIL
advised by Prof. Stefanie Jegelka.
I received my Bachelor's and Master's degree (Dual) in Mathematics and Computing from the Indian Institute of Technology, Delhi.
Previously I've had the opportunity to intern at Meta AI, Google Research,
Microsoft Research and MILA.
My research interests broadly lie in self supervised learning, robustness and out-of-distribution generalization.
I seek to investigate mechanisms that enable the learning of representations that not only capture richer structural relationships in unlabeled data
but are also interpretable and can efficiently adapt to unseen data distributions.
I am always happy to discuss new research directions and am open to both collaborating/advising students (not restricted to MIT). So if you're interested to work on fundamentals of self supervised learning and robustness under distribution shifts, feel free to reach out to me!
What's New
- [04/2024] Organizing the WiDS Cambridge Datathon 2024, happening on April 27th 2024. Sign up here if interested.
- [01/2024] Our recent paper, Context is Environment got accepted at ICLR 2024!
- [01/2024] Our paper, Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning got accepted at ICLR 2024!
- [01/2024] Our work on Removing Biases from Molecular Representations via Information Maximization got accepted at ICLR 2024!
- [06/2023] Find me in Paris, interning at Meta AI with David Lopez-Paz and Kartik Ahuja.
- [03/2023] Organizing the WiDS Cambridge Datathon. Video coverage can be found here.
- [08/2022] I have officialy started my PhD at MIT!