About

Hi! I am Tanvir. I am a PhD candidate in Computing and Information Science at Rochester Institute of Technology, where I work on reasoning in large language models, reinforcement learning with verifiable rewards, and cybersecurity applications, including cyber threat intelligence.

Research Interests

My primary research interests are in

• Reasoning in Large Language Models
• Reinforcement Learning with Verifiable Rewards (RLVR)
• Multimodal(Vision–Language) Learning and Evaluation
• Cyber Threat Intelligence and Security
• Explainable and Trustworthy AI
• Out-of-dsitribution robustness