I am a PhD student in Computer Science at IIIT-Delhi. My research focuses on video generation and understanding, with a particular interest in model efficiency and temporal modeling. Currently, I am studying how video-language models represent and reason about temporal dynamics.
TL;DR: We introduce a psychophysics-inspired framework to probe the temporal resolution limits of Video-LLMs, identifying a representation-behavior gap in temporal sensitivity.
I research generative video models, specifically focusing on temporal consistency, frame interpolation, and distributed training setups.
Studied optimization, neural representation models, and statistical learning. My master's thesis was supervised by Prof. Deepak Mishra.
Learned basic computer science theory, systems programming, and algorithms.
Writing on AI, generative models, and the machinery underneath.