🏫 I am a Ph.D. Candidate in the Computer Science and Engineering Department at The Ohio State University, advised by Wei-Lun (Harry) Chao.

My research interests lie in machine learning and vision-language domain. Specifically,

• Long Video Understanding and Reasoning
• Multimodal Learning
• Interpretable/ Explainable AI

Previously, I received my M.Sc. degree in CSE from The Ohio State University. I also recieved B.Sc. degree in Software Engineering from IIT in University of Dhaka.

Professionally, I had a wonderful time working as research intern in Qualcomm, USA (2025) and a backend engineer in Samsung R&D Institute

Application wise,

• 🦋 I am doing research in a wonderful team of Imageomics where I work on fine-grained trait discovery.
• 🩺 I am also working with Somashekar Krishna from The Ohio State University Medical Center on pancreatic cancer diagonosis from video .

Service

• Area Chair: NeurIPS Imageomics Workshop 2025
• Workshop Organizing Committee: Imageomics Conference 2026
• Organizer: 3rd Workshop on Computer vision for Ecology in ECCV 2026 (Details soon)
• Conference Reviewer: CVPR (2025,2026), AAAI 2025, ICCV 2025, NeurIPS 2025, ECCV 2026, WACV 2025, ICLR 2026

News

• April 2026
  • Our 3rd Workshop on Computer vision for Ecology got accepted in ECCV 2026!
  • I will give a Lightning Talk and speak in Imageomics Conference 2026 Workshop on my CVPR paper Prompt-CAM!
• February 2026
  • Our paper AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models got accepted in CVPR 2026!
• January 2026
  • Our paper BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models got accepted in ICLR 2026!
• December 2025
  • Passed PhD Candidacy Exam!
• October 2025
  • Arxiv preprint available of our paper: BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models
• July 2025
  • Arxiv preprint available of our paper: AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models!
• May 2025
  • I will be joining Qualcomm in San Diego as summer research intern for 2025!
• March 2025
  • My Paper Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis got accepted in CVPR 2025! 🎉
  • Our Paper Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation got accepted in CVPR 2025 as well! 🎉
• January 2025
  • Arxiv pre-print is available of our paper Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis!
  • Arxiv pre-print is available of our paper Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation!
  • Arxiv pre-print is available of our paper Static Segmentation by Tracking: A Frustratingly Label-Efficient Approach to Fine-Grained Segmentation)!
• September 2024
  • My Paper Fine tuning is fine if calibrated has been accepted in NeurIPS 2024! 🎉
  • Our Benchmark CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs is accepted in NeurIPS 2024 Database Track! 🎉
• July 2024
  • A arxiv pre-print paper is available CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
• April 2024
  • I will be attending the Imageomics All Hands Meeting to present a poster
• February 2024
  • A paper was accepted in Imageomics: Discovering Biological Knowledge from Images using AI in AAAI 2024! I also gave a talk about our work.
• January, 2024
  • A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis was accepted at ICLR 2024! 🎉

Contact

Email: chowdhury.150@osu.edu