@discover304
Love everything you like.
VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)
A comprehensive Flask-based REST API server for controlling soft robots via MuJoCo simulation or real hardware connections.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
This is a repo refactor of MuseCoco into a deployable service module, with the ability to adapt to new data and manage the history of its checkpoints, and abstract away the underlying detailed implementation (but with careful comments, it would be quite easy to navigate around).
An open protocol enabling communication and interoperability between opaque agentic applications.
An Interpretability amplifier or metrics of deep leanring models.
Open-source terminal-based application that transforms AI chatbot interactions into structured knowledge management workflows with branch management system.
Talk2Scene 是一个音频驱动的智能动画生成工具，能够自动解析语音杂谈文件，识别文本内容与时间节点，并基于 AI 推荐适合的角色姿态（STA）、表情（EXP）、动作（ACT）、背景（BG），在适当位置插入 CG 插画。最终生成结构化的场景事件数据，并自动合成预览视频，展现 AI 角色在不同场景中的动态表现。 该工具专为内容创作者、教育工作者、虚拟主播和 AI 爱好者设计，可广泛用于访谈视频、AI 互动演示、教育讲解等场景，帮助创作者轻松实现从音频到可视化动画的智能转换。
AI-powered multi-agent forex trading system. 8 GPT-4o agents collaborate via Redis pub/sub to analyze markets, detect signals, and execute leveraged trades on IG Markets. Full-screen Textual TUI dashboard with real-time monitoring.
此代码库托管了我们的项目代码和数据，该项目使用视觉错觉评估深度学习模型解读图形逻辑的能力。它包括我们独特的InDL数据集，展示我们实验的几个Jupyter笔记本，以及复现我们结果所需的Python脚本。 我们工作的目标是通过研究视觉错觉提供的感知和逻辑复杂交互，揭示深度学习模型的“黑盒”本质。有关我们的方法的更多详细信息，请参考我们的论文，链接在此：InDL: A New Datasets an
OpenMMLab's next-generation platform for general 3D object detection.
