Nihal Nayak

One-Page Resume | CV (Updated in Jan 2025)
I am a PostDoc at Harvard University (SEAS) working with David Alvarez-Melis. My research involves identifying the limitations of various components in intelligent systems, such as large language models (LLMs), and improving them with data-centric solutions.
I completed my Ph.D. in Computer Science at Brown University where I worked with Stephen Bach. During my Ph.D., I focused on building zero-shot systems, a class of intelligent systems that generalize to new classes, tasks, and environments without human annotations. I introduced principled approaches to building and evaluating these systems through synthetic datasets (Bonito), composition (CSP, CLIP Binding), and structured knowledge (ZSL-KG).
Email : nnayak [at] seas [dot] harvard [dot] edu
news
Jul 8, 2025 | Our work on pre-training foundation models in Academia was accepted to COLM 2025. |
---|---|
Jun 1, 2025 | Started a new position as a Postdoctoral Fellow at Harvard University (SEAS). |
May 16, 2025 | Our work on predicting unobserved drug interactions using graph paths with large language models was accepted to KDD 2025. |
Apr 25, 2025 | Invited talks at Ai2 (Video), Netflix, and Snowflake on Data-Centric Approaches to Adapting Foundation Models. |