Bandhav Veluri

Bandhav Veluri

I'm a Research Scientist at Sesame AI working on conversational AI. Previously, I spent a couple of years at Meta Superintelligence Labs where I worked on one of the first full-duplex spoken language models based on auto-regressive LLMs. I graduated with a PhD in Computer Science at the University of Washington advised by Prof. Shyam Gollakota and Prof. Michael Taylor. I completed my Bachelor's degree at the Indian Institute of Technology Roorkee.

News

Apr 2026AV-Dialog accepted to ACL 2026!
Sep 2025Started as research scientist at Sesame!
Nov 2024Presented SyncLLM at EMNLP Main 2024!
Jul 2024More than 500 stargazers at Look Once to Hear github repo
May 2024Look Once to Hear covered by MIT Tech Review! P.S: Also in U.S. News & World Report, GeekWire, UW News and a shout-out from Jeff Dean 😍
May 2024Look Once to Hear received best paper honorable mention award at CHI 2024 🏆
Nov 2023Semantic Hearing covered by MIT Tech Review and UW News!

Selected Publications

Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents

Bandhav Veluri, Benjamin N Peloquin, Bokai Yu, Hongyu Gong, Shyamnath Gollakota

EMNLP Main 2024

IRIS: Wireless Ring for Vision-based Smart Home Interaction

Maruchi Kim*, Antonio Glenn*, Bandhav Veluri*, Yunseo Lee, Eyoel Gebre, Aditya Bagaria, Shwetak Patel, Shyamnath Gollakota

ACM UIST 2024

Look Once to Hear: Target Speech Hearing with Noisy Examples

Bandhav Veluri*, Malek Itani*, Tuochao Chen, Takuya Yoshioka, Shyamnath Gollakota

ACM CHI 2024  🏆 Best paper honorable mention

Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables

Bandhav Veluri*, Malek Itani*, Justin Chan, Takuya Yoshioka, Shyamnath Gollakota

ACM UIST 2023

Real-Time Target Sound Extraction

Bandhav Veluri, Justin Chan, Malek Itani, Tuochao Chen, Takuya Yoshioka, Shyamnath Gollakota

IEEE ICASSP 2023

NeuriCam: Video Super Resolution and Colorization Using Key Frames

Bandhav Veluri, Ali Saffari, Collin Pernu, Joshua Smith, Michael Taylor, Shyamnath Gollakota

MobiCom 2023

* Co-primary authors