Hello! I’m currently a second-year graduate student pursuing a Master’s degree in Intelligent Information Systems (MIIS) at the Language Technologies Institute within the School of Computer Science at Carnegie Mellon University (expected graduation: August 2025).

Before CMU, I completed an Integrated Dual Degree (B.Tech+M.Tech) from the Department of Electrical Engineering at Indian Institute of Technology Kharagpur, with a specialization in Signal Processing and Machine Learning. I graduated with an Institute Order of Merit for academic excellence (9.18 CGPA).

I have a passion for AI research and have worked on various projects related to natural language processing, multimodal AI, recommender systems, conversational grounding, and LLM applications at prestigious institutions such as CMU, Inria Paris, Sony Research India, MIT IDSS, UCL, Triomics, and the University of Alberta. My recent work focuses on vision-language models for radiology report generation, code review automation, conversational grounding, and domain-specific pre-training techniques.

Currently, I am working on my capstone project, ChartBench, a multi-task synthetic chart understanding benchmark that evaluates multimodal large language models on incremental chart code editing. I also serve as a Teaching Assistant for the NLP course at CMU’s Language Technologies Institute.

From February 2026, I will be joining Apple as a Machine Learning Engineer in the Instructional Products team.

If you have any ideas that you would like to collaborate on, hit me up!

News

• [Feb 26] Will be joining Apple as a Machine Learning Engineer in the Instructional Products team!
• [Aug 25] Started the final semester of my Master’s program at CMU!
• [May 25] Started as an ML Research Intern at Apple on the Proactive Intelligence team.
• [Jan 25] Began my third semester in the MIIS program at CMU.
• [Nov 24] Our work on Conversational Grounding was presented at EMNLP 2024 in Miami!
• [May 24] Our work FastDoc: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy was accepted in the Transactions of Machine Learning Research (TMLR) Journal!!!
• [March 24] My work on SERPENT-VLM: Self-Refining Radiology Report Generation was accepted at the 6th Clinical Natural Language Processing Workshop at NAACL 2024!
• [January 24] Started working as a Research Engineering Intern at OncoLLM Team, developing state-of-the-art LLMs for oncology using Qwen2 family models.
• [December 23] Attended EMNLP’23 in Singapore.
• [October 23] Our work on CLMSM: Multi-Task Learning Framework for Pre-training on Procedural Text was accepted in EMNLP Findings 2023!
• [August 23] Started working on Master’s Capstone project on Chart Understanding Benchmarking.
• [June 23] Joined ALMAnaCH Team at Inria Paris as a Summer Research Intern working on Conversational Grounding!
• [December 22] Joined Sony Research India as a Data Science Intern working on Recommendation Systems with Graph Attention Networks!
• [August 22] One system description paper accepted at the Social Media Mining for Health Applications Shared Task (COLING 2022)
• [May 22] Received full Talent Bursary to attend Amii AI Week 2022!
• [April 22] One paper accepted at the Language Resources and Evaluation Conference (LREC 2022)
• [January 22] Started working as a Research Associate at TrAIL Lab, IIT Kharagpur
• [December 21] Accepted in Mitacs Globalink Research Internship program to intern at University of Alberta under Prof. Lili Mou
• [December 21] One paper accepted at the Scientific Document Understanding Workshop at AAAI 2022
• [September 21] Two papers accepted – one at ICONIP 2021 and one at 8th workshop on Argument Mining at EMNLP 2021
• [April 21] Started working as a Research Associate at the Complex Networks Research Group, IIT Kharagpur under Prof. Niloy Ganguly and Prof. Pawan Goyal
• [February 21] Selected as a Delegate to attend HUII 2021 Harvard Conference from 5-7 Feb, 2021
• [December 20] Started working as a Research Intern at the Financial Computing and Analytics Group at University College London

Research Interests

My research interests lie primarily in the following broad domains:

• Multimodal AI & Vision-Language Models: Developing methods for radiology report generation, chart understanding, and cross-modal reasoning.
• Large Language Models (LLMs): Code review automation, reinforcement learning from verifiable feedback, domain-specific continual pre-training.
• Conversational AI: Conversational grounding, multi-turn dialogue understanding, multi-agent interaction.
• Domain-Specific NLP: Legal document analysis, clinical NLP, procedural text understanding.
• Representation Learning: Graph neural networks for recommendation systems, contrastive learning.

Current Projects

• ChartBench: Multi-task synthetic chart understanding benchmark for evaluating multimodal LLMs on incremental chart code editing (CMU Capstone Project).
• CRScore++: Reinforcement learning framework combining verifiable tool feedback and AI feedback for code review comment generation.
• Inference Algorithms for LLMs: Research on beam search, self-refinement, and reranking methods for language models.