About Me

Hello! I’m a PhD student at the University of Washington in the Ubicomp Lab advised by Prof. Shwetak Patel.

I work on a lot of different things, but currently have a focus on conversational & voice AI systems for different applications. I develop techniques to either (1) run models on-device or (2) split models across devices to create responsive and intelligent conversational AI. The other side of my work looks at how conversational AI systems can gather better context from users in real-life contexts where answers are often incomplete or need further investigation.

I was previously at the University of Michigan ECE, where I worked with Prof. Robert Dick on embedded systems and resource-constrained ML. I also worked on computer architecture for a while, both at Michigan and at SambaNova Systems.

Please reach out at vysri [at] cs [dot] washington [dot] edu if you’d like to chat about research, interesting ideas, or anything else!

News

📄 08/26 Our paper Thinking While Speaking was accepted to EMNLP Findings!

🏆 03/26 Honored to be a recipient of the CIFAR Next Gen Trainee Fellowship

08/25 Back at Google, this time on the XR & Devices team. Stay tuned for exciting things!

📄 05/25 Our paper Substance over Style: Evaluating Proactive Conversational Coaching Agents was accepted to ACL 2025 Main Track!

🏆 01/25 Received the NCWIT AiC Collegiate Award for my research on human-centered intelligent systems!

🏆 10/24 Won the Madrona Prize Runner Up for my work on Knowledge Boosting during Low-Latency Inference!

07/24 Started a position as a student researcher at Google Health!

📄 06/24 Our paper Knowledge Boosting: Model Collaboration During Low-Latency Inference was accepted to Interspeech 2024!