I am a second-year M.S. student in Computer Science at the University of Texas at Austin. My research centers on building models that can understand, anticipate, and assist human activity from video. I am particularly interested in long-horizon video reasoning, temporal modeling, and the integration of multimodal cues to improve anticipation and feedback in complex tasks.
My recent work explores pre-emptive error detection in procedural videos and reinforcement learning frameworks for adaptive view selection in ego–exo instructional settings.
I’m always happy to chat about ideas around video understanding, skill assessment/coaching, and multimodal reasoning. If you’re working on related problems or datasets and want to discuss potential collaboration, feel free to reach out by email.
UT Austin
Aug 2024 – May 2026
Amazon Web Services
May 2025 – Aug 2025
IIT Guwahati
Jul 2023 – Jul 2024
Arizona State University
May 2023 – Jun 2024
NUS
Jun 2022 – Jul 2022
Feel free to reach out for research collaborations or just to chat about computer vision and machine learning. I’m currently based in Austin, Texas.