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 current research studies post-training optimization and system-level methods for LLMs and multimodal foundation models, with a focus on agentic reasoning and controllable adaptation. Ongoing work spans

Reasoning reliability and verification: retrieval-grounded structured inference and agentic retrieve-verify workflows for scientific claim and feasibility assessment, hallucination mitigation in multimodal QA (FilterRAG)
Privacy-preserving and controllable model adaptation: federated fine-tuning of LLMs with Differential Privacy (FedMentor, FedMentalCare), targeted multimodal unlearning (Multimodal Unlearning Survey)

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.

Research News (View All)

Feb 01, 2026	🏛️ Awesome Academic NLP Research Labs Worldwide released — a curated list of academic NLP research labs worldwide.
Jan 21, 2026	📢 Our paper Multimodal Unlearning Survey has been online.
Jan 07, 2026	🎉 Our paper FedMentor has been accepted for poster presentation at the Trusted AI Symposium, hosted by the Amazon AGI team.
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! 🧠✨

Publications Spotlight

Full publication list on Google Scholar →

Under Review

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, and Vaidehi Patil

In , 2026

TechRxiv Bib

@inproceedings{sarwar2026multimodalunlearning,
  title = {Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks},
  author = {Sarwar, Nobin and {Roy Dipta}, Shubhashis and Liu, Zheyuan and Patil, Vaidehi},
  year = {2026},
  techrxiv = {http://dx.doi.org/10.36227/techrxiv.176945748.88280394/v1},
  dimensions = {true}
}

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}
}