xid32 / SoundMindLinks
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.
☆1,103Updated last month
Alternatives and similar repositories for SoundMind
Users that are interested in SoundMind are comparing it to the libraries listed below
Sorting:
- DeepWism R2 is a next-generation AGI system built on the T3CEDS framework (Thin-Thick-Thin Crowd Entropy Dynamics System), which redefine…☆1,017Updated 6 months ago
- ☆516Updated 10 months ago
- ☆530Updated 11 months ago
- A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (re…☆557Updated this week
- ☆723Updated 6 months ago
- OmniAgent Framework is an advanced, modular AI orchestration system that transforms Web3 development by seamlessly integrating artificial…☆320Updated 11 months ago
- This is a database project.☆1,020Updated last week
- Liang - Non functional requirements should be part of function interfaces☆1,011Updated 4 years ago
- ☆600Updated 2 months ago
- AI Group is a powerful mobile intelligent assistant application that integrates multiple large language models (LLMs) and AI services, pr…☆1,096Updated 4 months ago
- UpTop is a BNB Chain-based liquidity protocol that allows users to unilaterally add BNB to liquidity pools, earn high yields, and support…☆75Updated 7 months ago
- Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling☆1,005Updated 3 months ago
- Framework that enables fine-tuning of vision-language grounding models on custom datasets☆601Updated 9 months ago
- 日历软件重写☆454Updated 9 months ago
- Dataset approched by A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection☆1,003Updated 9 months ago
- ☆998Updated 4 months ago
- AI-powered tool for efficient abstract and PDF screening in systematic reviews.☆1,301Updated 7 months ago
- AI-powered document analysis platform built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. In…☆697Updated this week
- ☆839Updated 6 months ago
- Vexa is a decentralized AI agent platform built on BNB Chain.☆347Updated 9 months ago
- ☆61Updated 5 months ago
- A Trusted Human-Multi-Agent Reinforcement Learning Interaction Framework☆502Updated 2 months ago
- Translate PDF, Word, PowerPoint, etc. | zotero翻译插件，微信扫码注册，新用户可免费翻译25万汉字或100万个英文字母。超能文献官网:suppr.wilddata.cn；☆806Updated 3 weeks ago
- Fat-Cat: A document-centric context management Agent. Making context as simple as reading chat history.☆281Updated last week
- ☆462Updated 8 months ago
- A public good tool to help users verify Safe (Gnosis Safe) transactions before signing or execution.☆525Updated 7 months ago
- PVPAI LLM 🔥The First Open-Source DeFAI Large Language Model Powered by DeepSeek.☆302Updated 11 months ago
- ☆683Updated 3 months ago
- ☆41Updated 4 months ago
- ☆53Updated 4 months ago