Reviewed 37+ papers across top venues (2023-2027).
Conferences
ACLNeurIPSNAACLCoNLLEACLCOLING*SEM
Workshops
SemEvalTrustNLPSRWW-NUTELVM
Journals
Scientific ReportsBMC BioinformaticsPlant MethodsComputational and Structural Biotechnology
I’m a final-year CS Ph.D. researcher at the University of Maryland, Baltimore County (UMBC), advised by Dr. Frank Ferraro, with research internships at Amazon Science (Alexa AI; Summer 2025 + 2026) and Scale AI (Summer 2024). I make LLMs more reliable largely through decomposition and reinforcement learning, spanning reasoning, agentic, and multimodal settings. My work on agentic LLMs earned a $20K Google Cloud Gemini Academic Program Award (2026).
Reasoning & Decomposition
Semi-supervised RL for traceable decomposition-based claim verification [DecomposeRL]
Atomic, presupposition-free decomposition for robust claim verification [De-Presuppose]
Token-efficient math reasoning via distractor-aware computational graphs [DAGGER]
Curriculum-driven GRPO for math reasoning in under-resourced languages [GanitLLM]
Hierarchical event abstraction for compositional sequence modeling [SHEM]
Agentic LLMs & Reinforcement Learning
Tool-calling alignment via policy-grounded deliberation [PA3]
Multi-agent benchmarks for diagnosing collaboration failures [AgentCollabBench]
Mechanistic analysis of token saliency in on-policy distillation [Rock Tokens]
Metacognitive control in LLMs under resource constraints [TRIAGE]
Multimodal Learning & Evaluation
Reference-free factuality metric for video captions [VC-Inspector]
Calibrated abstention under modality conflict in omni-modal models [OMD]
Zero-shot multilingual text-to-video retrieval via temporal event decomposition [Q2E]
Graduating Spring 2027 · No visa sponsorship needed · actively seeking Research Scientist roles in NLP / Multimodal AI. Please reach out if you have an opening.
🚀 New preprint - OracleZoom: recursive image super-resolution that keeps zooming to 256× with ground truth only at 4×. A VLM judge prefers it over Chain-of-Zoom in 78% of decided comparisons at 256×. Try the demo.
🎉 Awarded a $20,000 Google Cloud research grant through the Gemini Academic Program to support my LLM agentic research at UMBC. Featured by UMBC and on LinkedIn.
Jun 1, 2026
🎉 Joined Amazon Science (Alexa AI) for my second summer - researching self-distillation with RL to push LLM reasoning on agentic tasks.
May 27, 2026
🚀 New preprint - DecomposeRL: a 7B claim-verifier that matches GPT-4.1-mini across 11 benchmarks - with fully inspectable reasoning traces.
May 26, 2026
🥳 AgentCollabBench accepted at the FAGEN workshop @ ICML 2026 - 900 tasks that catch when a multi-agent LLM team’s final answer is right but the reasoning quietly broke.
Beyond Research
I’ve competed internationally in algorithms and robotics, ranking 8th out of 300+ teams at the 2018 ACM ICPC Asia Dhaka Regional with multiple regional and national placements, reaching the top 70 on Kaggle 🥉 in the Birdcall Identification competition, and placing 9th at the University Rover Challenge 2015 (Utah, USA) and 22nd at the European Rover Challenge 2016 (Poland). Full list of awards →
Before the PhD, I also founded UniShopr (2017-2021), a cross-border e-commerce platform serving consumers in Bangladesh.
OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super ResolutionUnder review* Equal contribution
DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim VerificationUnder review
Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated ReasoningMathAI @NeurIPS 2025
