Nobin Sarwar

I am a second-year Computer Science Ph.D. student in the Language Understanding Lab at the University of Maryland, Baltimore County, advised by Prof. Francis Ferraro.

My research focuses on Trustworthy Foundation Models, including self-improving optimization, reasoning, privacy-preserving LLMs [1], unlearning, and robustness [2]. In reasoning, I develop methods that evaluate scientific claims with LLMs by coupling targeted retrieval with structured inference. This coupling makes the inference chain explicit and anchors conclusions in feasible evidence. A second thrust of my work develops privacy-aware and robust learning for distributed settings, focusing on federated language models and Differential Privacy for sensitive data.

Previously, I earned my MS in Computer Science from the University of Texas Rio Grande Valley, where I worked on privacy-preserving federated learning for biometrics and differential privacy, contributing to projects that received NSF funding.

Actively exploring Summer Internship in NLP, CV and/or ML. Please contact me if you have relevant opportunities.

Research News

Nov 28, 2025	✨ Excited to receive a travel grant from the GenAI4Health Workshop organizers to present FedMentor at NeurIPS 2025!
Sep 27, 2025	🎉 Our paper FedMentor is accepted for presentation at the GenAI4Health Workshop, NeurIPS 2025 — The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance! 🧠✨
Sep 02, 2025	🎉 Selected for the ICCV 2025 Broadening Participation program. Excited to engage with the CV community! ✨
Aug 16, 2025	🎉 Our paper FilterRAG has been accepted at T2FM Workshop, ICCV 2025! 🔍✨

Publications Spotlight

Full publication list on Google Scholar →

NeurIPS ’25

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health

Nobin Sarwar and Shubhashis Roy Dipta

In GenAI4Health Workshop, NeurIPS (Code will be released soon!), 2025

arXiv Bib PDF Code Poster

@inproceedings{sarwar2025fedmentor,
  title = {FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health},
  author = {Sarwar, Nobin and {Roy Dipta}, Shubhashis},
  booktitle = {GenAI4Health Workshop, NeurIPS (Code will be released soon!)},
  year = {2025},
  url = {https://genai4health.github.io/},
  dimensions = {true}
}

ICCV ’25

FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA

Nobin Sarwar

In T2FM Workshop, ICCV, 2025

arXiv Bib PDF Poster Slides

@inproceedings{sarwar2025filterrag,
  title = {FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA},
  author = {Sarwar, Nobin},
  booktitle = {T2FM Workshop, ICCV},
  year = {2025},
  url = {https://t2fm-ws.github.io/T2FM-ICCV25/},
  dimensions = {true}
}