today local_bar

Ramani Duraiswami

Full Professor, University of Maryland, College Park

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

#1903 Spotlight · Sreyan Ghosh, Arushi Goel, Jaehyeon Kim, Sonal Kumar, Zhifeng Kong, Sang-gil Lee, Chao-Han Huck Yang, Ramani Duraiswami, Dinesh Manocha, Rafael Valle, Bryan Catanzaro

A fully-open large audio-language model with SOTA performance across 20+ benchmarks.