- taiwan
-
10:43
(UTC +08:00)
Highlights
Lists (4)
Sort Name ascending (A-Z)
Starred repositories
HarmonyOS Next innovative capabilities case repo.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习|数据合成
Official implementation of "REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving" (NeurIPS 2025)
A lightweight browser-to-NAS pipeline for capturing and downloading web videos. It integrates a Chrome Extension with a NAS-hosted Docker backend (FastAPI, workers, FFmpeg) to automatically detect,…
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
GigaTrain: An Efficient and Scalable Training Framework for AI Models
本项目是一个基于 Golang Gin 框架 开发的 B2C 电商平台,采用 MVC(Model-View-Controller)架构 进行模块化设计,能够扩展为实现前后端分离,支持后台商品管理、用户系统、订单交易、支付集成、数据分析等功能,系统地展示了现代Web应用的全貌。该项目描绘了一个功能完整、技术选型现代的全栈电商项目。它从前端交互到后端管理,从业务逻…
https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk
Official Pytorch implementation for ICML 2025 paper "Large Continual Instruction Assistant"
PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.
🧠 Prometheus: A Knowledge-Graph-Driven 🤖 AI Agent that maps 🗺, understands 🧩, and repairs 🛠 complex codebases — not by guessing, but by reasoning. ⚡
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.
MAD-Former: A Traceable Interpretability Model for Alzheimer’s Disease Recognition based on Multi-patch Attention
FIT: 企业级AI开发框架,提供多语言函数引擎(FIT)、流式编排引擎(WaterFlow)及Java生态的LangChain替代方案(FEL)。原生/Spring双模运行,支持插件热插拔与智能聚散部署,无缝统一大模型与业务系统。
TVM Documentation in Chinese Simplified / TVM 中文文档
AppPlatform 是一个前沿的大模型应用工程,旨在通过集成的声明式编程和低代码配置工具,简化和优化大模型的训练与推理应用的开发过程。本工程为软件工程师和产品经理提供一个强大的、可扩展的环境,以支持从概念到部署的全流程 AI 应用开发。
Explain Before You Answer: A Survey on Compositional Visual Reasoning