About Me

I'm a first-year PhD student at MIT, advised by Phillip Isola. I am supported by a NSF Graduate Research Fellowship and an MIT HDTV Fellowship. I am broadly interested in generalization, generative models, and representation learning, particularly in computer vision. I have also worked in using insights from neuroscience and cognitive science to build better artificial intelligence systems.

Previously I got my bachelors in Computer Science and in Mathematics at MIT, working at the MIT Center for Brains, Minds, and Machines with Pawan Sinha and Xavier Boix. In the past I've also been fortunate to intern at Deepmind (large language models), D. E. Shaw (reinforcement learning research), Apple (applied machine learning), and Two Sigma (software engineering). In my free time I enjoy hiking, writing, and running.

Research

blind-date
Symmetry perception by deep networks: Inadequacy of feed-forward architectures and improvements with recurrent connections
Shobhita Sundaram*, Darius Sinha*, Matthew Groth, Tomotake Sasaki, Xavier Boix
Under Review

Preprint on arXiv

Poster presentation at the ICLR 2021 Generalization Beyond the Training Distribution in Brains and Machines Workshop

clean-usnob
GAN-based Data Augmentation for Chest X-ray Classification
Shobhita Sundaram*, Neha Hulkund*
KDD 2021 Applied Data Science for Healthcare Workshop

Paper on arXiv

clean-usnob
Do Neural Networks for Segmentation Understand Insideness?
Kimberly Villalobos*, Vilim Stih*, Amineh Ahmadinejad*, Shobhita Sundaram, Jamell Dozier, Andrew Francl, Frederico Azevedo, Tomotake Sasaki, Xavier Boix
Neural Computation 33, 2511-2549, 2021

Paper available here

Projects

blind-date
Facilitating Fairness in Transfer Learning through Distributionally Robust Finetuning

Final project for 6.864: Natural Language Processing

clean-usnob
Extension of a Bayesian Hierarchical Model for Moral Judgments

Final project for 6.804: Computational Cognitive Science

clean-usnob
Computational Reading of Gender in Novels (1770-1922)

Research conducted in the MIT Digital Humanities Lab, Fall 2018

Read about our findings in Ms. Magazine

Writing

blind-date MIT Science Policy Review, Associate Editor
clean-usnob MIT Chroma: "Rebuilding Despite the Risks"