OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.

Code of LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

Liquid: Language Models are Scalable and Unified Multi-modal Generators

The 1st dynamic phishing kit dataset

Vim mode for VSCode, run Vim/Nvim in integrated terminal with seamless switching

Smarter security: AI-enhanced static scanning with Semgrep.

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Residual Kolmogorov-Arnold Network (RKAN) is designed to enhance the performance of classic CNNs by incorporating RKAN blocks into existing architectures.

GENERator: A Long-Context Generative Genomic Foundation Model

抖音，小红书，视频号，快手等多个自媒体平台的一键发布工具

The repository for the paper "Image Inversion: A Survey from GANs to Diffusion and Beyond".

Official implementation for "JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework"

Brain-Body Co-Design for Embodied Agents: A Survey of Neural Approaches

A public good tool to help users verify Safe (Gnosis Safe) transactions before signing or execution.

✨✨Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy

A C++ header-only memory allocator designed for multi-threaded application

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"

Mixed local channel attention for object detection （The codes of MLCA）

Flame is an open-source multimodal AI system designed to translate UI design mockups into high-quality React code. It leverages vision-language modeling, automated data synthesis, and structured tr…

Dynamic Topic Segmentation in Dialogues: Enhancing Boundaries with Topic-Aware Propagation

YOLOv11-RGBT: Towards a Comprehensive Multispectral Object Detection Framework（Supports RGBT detection for all YOLO series from YOLOv3 to YOLOv12, as well as RTDETR.））

Dataset approched by A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection

SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.

The official Soundwave repository

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。