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

NeurIPSSpotlight2025

Authors: 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
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

language model reasoning speech audio

← All NeurIPS 2025 Spotlight papers · Browse the whole archive