RL post-training of audio-language models with self-supervised tasks as verifiable rewards
-
NearAndDear98/Audio-R1-Qwen2.5-Omni-7B
Audio-Text-to-Text • Updated • 70 • 1 -
NearAndDear98/Audio-R1-Gemma-4-E4B-it
Audio-Text-to-Text • Updated • 32 -
NearAndDear98/Audio-R1-AF-Next-Think
Audio-Text-to-Text • Updated • 29 -
Audio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks
Paper • 2610.34609 • Published