ā AACL 2025 in Mumbai, India (Dec 20-24) (canceled)
š I'm open to meet! Email me to schedule a chat!
Peer Review
Reviewed 28+ papers across top venues (2023ā2025).
Conferences
ACLNeurIPSNAACLCOLING*SEM
Workshops
SemEvalTrustNLPSRWW-NUTELVM
Journals
Scientific ReportsBMC BioinformaticsPlant MethodsComputational and Structural Biotechnology
I am a final-year Ph.D. researcher in Computer Science at the University of Maryland, Baltimore County (UMBC), advised by Dr. Frank Ferraro. Iāve also interned at Amazon Science (Alexa AI; Summer 2025 + Summer 2026) and Scale AI (Summer 2024). My research focuses on three areas where modern LLMs fail predictably - (1) complex reasoning, (2) tool-use, and (3) modality conflict - to make them more reliable, efficient, and aligned.
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 Ā· No visa sponsorship needed Ā· actively seeking Research Scientist roles in NLP / Multimodal AI. Please reach out if you have an opening.
š Joined Amazon Science (Alexa AI) for my second summer - researching self-distillation with RL to push LLM reasoning on agentic tasks.
May 27, 2026
š New preprint - DecomposeRL: a 7B claim-verifier that matches GPT-4.1-mini across 11 benchmarks - with fully inspectable reasoning traces.
May 26, 2026
š„³ AgentCollabBench accepted at the FAGEN workshop @ ICML 2026 - 900 tasks that catch when a multi-agent LLM teamās final answer is right but the reasoning quietly broke.
Iāve 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 š„ 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 ā
Before the PhD, I also founded UniShopr (2017-2021), a cross-border e-commerce platform serving consumers in Bangladesh.
Featured Publications
Check out Google Scholar for a full list of my publications.
Submitted
DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
Shubhashis Roy Dipta,Ā Ankur Padia,Ā andĀ Francis Ferraro