About Me
I am a fourth year undergraduate student at MIT EECS, where I am grateful to be under the guidance of Professor Nir Shavit as a member of the Shavit Lab. I have also conducted research with Professor Ila Fiete as part of the Fiete Lab and at NASA’s Jet Propulsion Laboratory under Dr. Tom Lu and Dr. Ed Chow. I am an awardee of the 2025 MIT Peter J. Eloranta Summer Undergraduate Research Fellowship.
I am curious about how underlying network structure determines system behavior, through the lens of interpretability. My goal is to build efficient systems whose internal structures are understandable and to derive scalable principles that generalize circuit-level behavior in large models.
News
- November 2025: My self-proposed first-author work Multi-View Canonical Correlation Analysis for Cross-Lingual Fake News Detection was accepted to the MIT Undergraduate Research Journal (MURJ) vol. 50, Fall 2025
- October 2025: My first-author work Expand Neurons, Not Parameters is on Arxiv and submitted to ICLR 2026
- May 2025: I served as a first author of a proposal selected for an MIT Peter J. Eloranta Summer Undergraduate Research Fellowship to support my self-led original research.
- October 2024: I was selected as a Cerebras Research Fellow
- April 2024: I gave a talk on my work Intelligent knowledge base search tool using large language model and graph neural network at the 2024 SPIE Defense + Commercial Sensing Conference in National Harbor, MD.
- March 2024: My work Intelligent knowledge base search tool using large language model and graph neural network was accepted into SPIE Defense + Commercial Sensing 2024 as an Invited Paper and Oral Presentation
Selected Works
Multi-View Canonical Correlation Analysis for Cross-Lingual Fake News Detection
Published in MURJ, 2025
Inimai Subramanian
Download Paper
Expand Neurons, Not Parameters
Preprint on arXiv, 2025
Linghao Kong*, Inimai Subramanian*, Yonadav Shavit, Micah Adler, Dan Alistarh, & Nir N. Shavit
Download Paper
Intelligent knowledge base search tool using large language model and graph neural network
Published in SPIE 2024 as an Invited Paper and Oral Presentation
Kevin Payumo, Inimai Subramanian, Thomas Lu, Edward Chow
Download Paper
