About

I am a Computer Vision researcher and engineer driven by the need for explainable and reliable multimodal reasoning. I am currently a Master’s student at the University at Buffalo, advised by Prof. Junsong Yuan, where I investigate low-level perception bottlenecks in Vision-Language Models (VLMs).

My work spans the entire AI lifecycle, from data curation to edge-device optimization. Most recently, I have focused on safety-critical applications, developing frameworks that align human intuition with model reasoning for tasks like high-density object counting. Previously, I spent three years at Citi developing innovative in-house tools to streamline and optimize inter team data workflows.

🔍 I am actively looking for full-time Research / Engineering / Pre-Doc / Fellowship positions in Computer Vision and Machine Learning starting June 2026. Please reach out if you think I might be a good fit for your team!

News

• [Nov 2025]: “Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting” paper accepted at WACV 2026 [Paper] [Code] [Video]
• [May 2025]: Summer’25 Internship at Mercedes-Benz R&D in San Jose as a Machine Learning Computing Intern on the Autonomous Driving - Middleware team. Focused on model optimization and deployment across various hardware targets.

Email: rbhyri [at] buffalo dot edu