Stars
MLCD & UNICOM : Large-Scale Visual Representation Model
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。
[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
Extended Agriculture-Vision Dataset: A continuous work of Agriculture-Vision, with great collaborators to bring Agriculture and Computer Vision / AI communities together to benefit humanity!
An open-source implementation for training LLaVA-NeXT.
User Identity Scaffolding for Multiple OIDC Authentications for User
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
The first open autoregressive foundational video AI model.
数据流引擎是一款面向数据集成、数据同步、数据交换、数据共享、任务配置、任务调度的底层数据驱动引擎。数据流引擎采用管执分离、多流层、插件库等体系应对大规模数据任务、数据高频上报、数据高频采集、异构数据兼容的实际数据问题。
WebGL Three.js Cesium.js Examples And Demo - WebGL 的 Three.js 和 Cesium.js 案例 --- Star ---点星星
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
[arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".
Dataset and code of GTSinger(NeurIPS 2024 Spotlight): A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
The official implementation of our pre-print paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".
The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, a…
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体，一个对话框提供所有主流格式数据…
The official codes for "PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents"
工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践；对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑，是内部流程管理和业务算法驱动的不二之选。