SoundMind

Public

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 (ALMs) with deep bimodal reasoning abilities.

audio-language-model audio-reasoning dataset reinforcement-learning

Creat：2025-06-13T10:41:16

Update：2025-06-19T10:52:38

https://arxiv.org/abs/2506.12935

1.1K

Stars

Stars Increase

Related projects

Transformers

Hot

bert

? Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

148148

2年前

+109today

Rust

Hot

compiler

Empowering everyone to build reliable and efficient software.

105659

4个月前

+78today

TypeScript

javascript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

105568

4个月前

+30today

Generative Ai For Beginners

Hot

21 Lessons, Get Started Building with Generative AI ? https://microsoft.github.io/generative-ai-for-beginners/

94424

5个月前

+291today

D2l Zh

Hot

book

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

71539

4个月前

+64today

Gpt_academic

academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

69074

4个月前

+8today