Vishvesh Trivedi

I am a Master’s student at the Courant Institute of Mathematical Sciences, New York University and a Research Volunteer at the Biomedical Data Sciences Hub (Bio-DaSH) lab in NYU Langone Health, where I work with Prof. Gustavo Stolovitzky on benchmarking clinical AI tools and making them more robust to temporal and demographic biases.

Previously, I was a Visiting Research Fellow at CVIT, IIIT Hyderabad, advised by Prof. C.V. Jawahar and Prof. Anand Mishra where I advanced lecture presentation understanding using synthetic slide generation. We published our findings at ICDAR 2025 (Oral) and made the dataset and generation pipeline openly accessible.

In summer 2023, I interned at Wells Fargo , developing semantic-aware audio transcriptions for onboarding presentations tailored to over 15,000 visually impaired employees worldwide. During my undergraduate studies at SVNIT, Surat, I worked with Prof. Rupa G Mehta to enhance the explainability of thoracic disease predictors through clinical ontology integration.

My current interest areas are in Clinical AI Reasoning & Safety, Mechanistic Interpretibility, Multimodal Synthetic Data Generation, and Optimizing Inference pipelines of LLMs/VLMs.

Beyond research, I’m a former competitive swimmer from India, served as Chapter Head of the ACM Student Chapter at NIT Surat, and was an editor for its official publication club, Renesa. These days I am into running and museum-hopping in and around NYC.