Hi, I'm Farhan, a PhD student at Kahlert School of Computing, University of Utah (KSoC, UofU) and the AI Lead Researcher at Yaana Communications Lab (YCL). I obtained my Bachelor's degree from IUT-CSE. Currently, I am working with Prof. Kenneth Marino to build AI agents that help people.
News and Updates
- Sep 26: TimeWarp is headed to NeurIPS'26!
- Aug 26: FrugalPrompt is in LUHME at EMNLP'26!
- Aug 26: KNOWS will appear in Findings of EMNLP'26!
- May 26: Check out our new preprint, Dora Explorer, on making LLM agents explore better.
- Apr 26: BanHate is in ACL'26!
- Mar 26: Check out TimeWarp, a web agent benchmark on changing websites.
- Feb 26: Our visual survey of computer use agents is now live on the ICLR'26 Blogposts.
- Dec 25: Robustness to Transliteration won the best paper award at BLP at IJCNLP-AACL'25!
- Nov 25: Three papers at WACV'26, on few-shot VLM adapters, corruption robustness, and cultural VQA!
- Oct 25: FrugalPrompt is out!
- Aug 25: Started my PhD at the University of Utah!
- June 25: ChitroJera, a regionally relevant VQA dataset for Bangla, is headed to ECML-PKDD'25!
- Mar 25: Attended WACV'25.
- Jan 25: BanTH to appear in Findings of NAACL'25!
- Oct 24: Visual Robustness Benchmark for VQA will appear at WACV'25. I'm grateful to my wonderful teammates and advisors at IUT-CSE.
- Oct 24: FourierKAN outperforms MLP on Text Classification Head Fine-tuning will be presented at FITML at NeurIPS'24. Shoutout to my teammate Abdullah Al Imran.
- Sep 24: Our work on Bangla back-transliteration, BanglaTLit, is in Findings of EMNLP'24. Great work from team Penta!
- Jul 24: New preprint on my undergrad thesis, Visual Robustness Benchmark for VQA, is available on arXiv.
- May 24: Finalists at Robi Datathon 3.0, Bangladesh's largest data analysis event with 3,500+ participants. Another competition with team Penta!
- May 24: Participated in the EXIST-2024 shared task with my amazing team from Penta Global.
- Jan 24: Our VQA Survey is out in Information Fusion.
Research Map
The research map will help you navigate through my research portfolio. Click any node for details.
Research Highlights
TimeWarp: Evaluating Web Agents by Revisiting the Past
Project Page Paper Code Dataset Models

FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution

