BetaRare
xid32/SoundMind
We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow audio language models (AL…
- Owner
- xid32 (personal account)
- Stars
- Stars: 1,116
- Forks
- Forks: 131
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- audio-language-modelaudio-reasoningdatasetreinforcement-learning
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by xid32
All 2 repos by xid32- xid32/NAACL_2025_TWMStars: 317PythonAlpha
Nearby in Python
All Python repos- Doriandarko/make-it-heavyStars: 1,116PythonBeta
- EWEDLCM/FnDepotStars: 1,116PythonBeta
- binance/binance-skills-hubStars: 1,116PythonBeta
- whyliam/whyliam.workflows.youdaoStars: 1,116PythonBeta
- da03/Attention-OCRStars: 1,116PythonBeta
- szad670401/end-to-end-for-chinese-plate-recognitionStars: 1,116PythonBeta