Lists (2)
Stars
A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.
LLaQo, a Large Language Query-based Coach in the domain of expressive performance
CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
Science-Star: A Platform for Building, Extending, and Experimenting with Scientific Agents.
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
(MICCAI 2021 [MSNet] & MICCAI 2022 GOALS Challenge [M2SNet]) Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
Antibody Mass Spectrometry De Novo Benchmark
[ICCV 2025] LocalDyGS : Multi-view Global Dynamic Scene Modeling through Adaptive Local Feature Decoupling
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Official implementation for "HA-VLN: A Benchmark for Human-Aware Navigation in Discrete-Continuous Environments with Dynamic Multi-Human Interactions, Real-World Validation, and an Open Leaderboard".
Tego is a pluggable Node.js framework for building customizable development platforms. It enables developers to create their own no-code/low-code systems or event-driven applications, while the cor…
A comprehensive, production-ready framework for building intelligent AI agents with advanced capabilities including tool calling, persistent memory, intelligent concurrency, and event-driven observ…
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
一个由WPF开发的超轻量的OCR桌面端应用，支持多语言OCR；自定义prompt，deepseek AI校对；剪贴板实时监控
53AI Hub is an open-source AI portal, which enables you to quickly build a operational-level AI portal to launch and operate AI agents, prompts, and AI tools. It supports seamless integration with …
( TPAMI2022 / CVPR2019 Oral ) Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
职星学院企业培训系统是一套基于点播、直播、考试、培训、面授等功能完善的在线教育系统，开源版是基于商业版精简实现的一个企业员工培训系统，致力于打造一个各行业都适用的在线培训系统、企业培训平台、员工培训系统、企业内部培训系统。
The code for TPAMI paper "Text-Guided Human Image Manipulation via Image-Text Shared Space"
Unified Multimodal Model for image generation/editing/understanding
Easiest and laziest way for building multi-agent LLMs applications.
Nexent is a zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required. Nexent also offers powerful capabilities for agent running control, data processing …
[NeurIPS 2025] Efficient Reasoning Vision Language Models
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
A lightweight LMM-based Document Parsing Model