Stars
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。
Code for paper "Towards Understanding Camera Motions in Any Video"
Klavis AI (YC X25): Open Source MCP integration for AI applications
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
Comprehensive tools and frameworks for developing foundation models tailored to recommendation systems.
DeMCP is the first Decentralized MCP network, offering SSE proxies for MCP services and mainstream LLMs, tackling trust and security with TEE and blockchain.
🎠 React Native swiper/carousel component, fully implemented using reanimated v2, support to iOS/Android/Web. (Swiper/Carousel)
✨✨latest advancements in VLA models(VIsion Language Action)
🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
A comprehensive React-based stock market analysis dashboard that enables users to visualize and compare historical market data from multiple stocks, featuring technical indicators, trend analysis, …
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer
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。
Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning (Best open-source multimodal reasoning model)
The code and data of ijcai2018 paper <Topic-to-Essay Generation with Neural Networks>
Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
Performant image component for React Native
[CVPR 2025] Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
Dataset approched by A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025)
[ICLR 2025] Improving Data Efficiency via Curating LLM-Driven Rating Systems
【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’
H2HDB is a comprehensive database for organising and managing H@H comic collections.
Efficient DiT architecture for text2any tasks, ICLR2025