Ami Baid

I recently graduated from UT Austin with degrees in computer science and math as a Turing Scholar. During undergrad, I was a researcher in the UT Austin Computer Vision Lab, advised by Prof. Kristen Grauman. I'll be starting my Master's in CS at Stanford this fall🌲

My research focuses on audio-visual perception and generation. Recently, I've been working on improving how language models ground their outputs in information from diverse modalities.

Email  /  Resume  /  Scholar  /  GitHub

Research

Personal Visual Context Learning in Large Multimodal Models

Zihui Xue, Ami Baid, Sangho Kim, Mi Luo, Kristen Grauman

arXiv 2026   [paper] [project page]

Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models

Ami Baid, Zihui Xue, Kristen Grauman

ECCV 2026   [paper] [project page]

Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos

Changan Chen, Puyuan Peng, Ami Baid, Zihui Xue, Wei-Ning Hsu, David Harwath, Kristen Grauman

ECCV 2024, Oral   [paper] [project page]

Self-Supervised Visual-Acoustic Matching (acknowledged)

Arjun Somayazulu, Changan Chen, Kristen Grauman

NeurIPS 2023   [paper] [project page]

Internships

• Software engineering intern @ Stripe (summer 2025): added a visual modality to Stripe's LLM-based Terms-of-Service evaluation system.
• Software engineering intern @ Salesforce (summer 2024): automated workflows on Salesforce's internal Temporal.io platform; contributed to the open-source Terraform Temporal provider.

Other Projects

• Gaze-centered Egocentric Video Representations: a preprocessing pipeline that reallocates video resolution around the wearer's gaze, improving efficiency in egocentric video QA. [GitHub]