Trisanth Srinivasan

Email: trisanth[at]cyrionlabs[dot]org         

Google Scholar      Github      Resume

I am currently a research intern at NYU mLab and a Machine Learning Researcher and Co-Founder at Cyrion Labs. My work focuses on human-computer interaction, visual language models, bias, and applied AI.

Previously, I contributed to scalable systems and AI-driven platforms in roles ranging from Full-Stack Developer to CTO in startups and established companies. In my free time, I volunteer as a computer refurbishing technician making computers more accessible for the visually impaired.

April 2025: One Paper (PhysNav-DG: A Novel Adaptive Framework for Robust VLM-Sensor Fusion in Navigation Applications) Accepted to DG-EBF @ IEEE CVPR 2025

March 2025: Second Demo (VIZ: Virtual & Physical Navigation System for the Visually Impaired) Accepted to IEEE CVPR 2025

March 2025: One Demo (GenECA: A Generalizable Framework for Real-Time Multimodal Embodied Conversational Agents) Accepted to IEEE CVPR 2025

March 2025: Joined NYU mLab as a Research Intern. I will be working on network filtering technology in K-12 Environments

March 2025: One PrePrint Paper Published on arXiv

Introduces an adaptive framework that fuses visual language models with sensor data, enhancing navigation in complex, dynamic environments.

Proposes a novel approach to automated UI element annotation using semantic web technologies, enhancing accessibility and usability of web interfaces.

Presents a novel voice-controlled navigation agent using a ReAct-inspired architecture, offering improved accessibility for the visually impaired.

Introduces a robust framework for multimodal interactions with embodied conversational agents, emphasizing emotion-sensitive interaction.

Addresses the challenges faced by the visually impaired by utilizing generative AI to mimic human behavior for complex digital tasks and physical navigation.

The website template was adapted from Yu Deng.