Profile photo

Swapnanil Mukherjee

Ashoka University

About Me

I am a final year undergraduate student at Ashoka University. My research interests lie in multimodal AI, problems at the intersection of vision and language, commonsense abilities in foundation models, and reasoning.

I am currently an intern at the Precog Lab at IIIT Hyderabad where I am investigating modality bias and preference in large multimodal models (MLLMs) Microsoft Research India. Previously, I have worked at Sarvam, KCDH-Ashoka, and the Mphasis AI & Applied Tech Lab at Ashoka. I am currently pursuing my undergraduate thesis on neurosymbolic reasoning supervised by Prof. Debayan Gupta (Ashoka University) and Prof. Somak Aditya (IIT Kharagpur). For more details, check out my CV, or look at my research.

Aside from work, there aren't many things that I do (which I am slowly trying to change). But sometimes, when I do find the motivation, I enjoy obsessing over frames. I am quite into comic universes, have an alarming number of Spotify minutes, and I try to swim sometimes. Please reach out to me if you find any of these interesting, or just want to have a chat!

[NOTE] I am also actively looking for PhD positions starting Fall 2026 in the aforementioned research areas. If there are any openings and I might be a good fit for your group, do let me know!

Recent News

October 2025 I will be attending EMNLP in Suzhou, China to present our NLKI paper. Let's catch up if you're there!
August 2025 The preprint and code for our paper NLKI has been released.
August 2025 Our paper, NLKI, is accepted to the Findings of EMNLP!
June 2025 I will be in Hyderabad till August, interning at the Precog Lab at IIIT-Hyderabad!

Recent Publications

See all →
NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

NLKI: A lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghoshal, Somak Aditya

EMNLP 2025 Findings

Next-Gen Profiling of Tumor-resident Stem Cells using Machine Learning

Next-Gen Profiling of Tumor-resident Stem Cells using Machine Learning

Debojyoti Chowdhury, Bhavesh Neekhra, Shreyansh Priyadarshi, Swapnanil Mukherjee, Debashruti Maity, Debayan Gupta, Shubhasis Haldar

bioaRxiv (preprint)