More
Starred repositories
Elasticsearch GUI client for Mac, windows and linux, Opensearch GUI client for Mac, windows and linux
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
SurgClean Benchmark for Surgical Image Restoration.
A lightweight LMM-based Document Parsing Model
Escape room game with quiz-solving and smart AI navigation. Unity + NavMesh + C#.
UIKit Plus: Infusing SwiftUI-like Development Efficiency. Revolutionizing UIKit development through chain syntax, resultBuilder, and modern APIs, retaining full native control while achieving Swift…
data and codes for adaptive strategies for climate change adaptation: An application for flood risk management
Major Color Extract using SWASA and S-CIELAB
AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.
Hydra九头龙,面向PB级别知识库取数、情报系统、数据平台、大规模控制调度系统。建设云计算资源管理、任务/服务统一调度、数仓、微服务化、中台基建系统化能力。——以实现大规模分布式爬虫搜索引擎为例。
A codebase and a curated list of awesome deep long-tailed learning (TPAMI 2023).
Multi-Agent System Framework For Complex Tasks
AutoMouser automatically generates browser automation code from your mouse movements, capturing every click, drag, and hover to streamline your workflow and build robust, repeatable tests.
Build 3D Gaussian Splatting from scratch with NVIDIA Warp in Python — CPU/GPU compatible, with a clean and minimalist design focused on learning modern graphics.
Hybrid Latent Reasoning via Reinforcement Learning
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
OpenAPIDesigner is an open-source OpenAPI specification design tool that allows developers to design, write, and validate OpenAPI specifications.
AudioTrust: Benchmarking the Multi-faceted Trustworthiness of Audio Large Language Models
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
✨✨VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Moxin is a family of fully open-source and reproducible LLMs
Train your Agent model via our easy and efficient framework