Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input.

LakeSoul is an end-to-end, realtime and cloud native Lakehouse framework with fast data ingestion, concurrent update and incremental data analytics on cloud storages for both BI and AI applications.

数据标注是一款专门对文本数据进行处理和标注的工具，通过简化快捷的文本标注流程和动态的算法反馈，支持用户快速标注关键词并能通过算法持续减少人工标注的成本和时间。数据标注的过程先由人工标注构筑基础，再由自动标注反哺人工标注，最后由人工标注进行纠偏，从而大幅度提高标注的精准度和高效性。数据标注是一个完全开源的项目，无商业版，但是需要依赖开源的数字底座进行人员岗位管控。各类词库结果会定期在本平台公开。

lightweight, flexible ECS for web games

Analysis and visualization of multi-omics data. In ongoing development: multi-modal fusion, sparse learning, and spatio-temporal effects...

临时百度、阿里、腾讯、AWS、华为云存储桶检测工具,凭据有效性、Bucket存在性、上传下载、对象存在性、权限检测

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction

A cross-platform client application designed for real-time audio capture, processing, and playback. Built using the Tauri framework, AntiRec provides a seamless experience across different operatin…

A python package that integrate algorithms and various machine learning approaches to extract features (genes) effective for classification and attribute them accordingly.

A C++ implementation of Open Interpreter, based on llama.cpp. / Open Interpreter 的 C++ 实现，基于 llama.cpp

The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Polaris: An LLVM-based obfuscator that protects software at various levels

Advanced Unsupervised Image Enhancement with GAN

Official comfyui repository of Hellomeme

Provide JSON file template that demonstrate how to create customize Well-Architected reviews using Custom lenses.

Unified KV Cache Compression Methods for Auto-Regressive Models

一个简洁、高性能、跨平台、多语言支持的服务端开发框架，面向Service及Component，底层c++实现。

An open-source implementation for training LLaVA-NeXT.

Multilayered AV/EDR Evasion Framework

The official code for "BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities"

[COLING'22] Code for "SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER"

[ACL'23] Code for "SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition"

Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥