TinyTroupe is an experimental Python library released by Microsoft for simulating artificial agents (TinyPersons) with specific personalities, interests, and goals, allowing them to interact within a simulated environment (TinyWorld). TinyTroupe...
Thinking Claude is a project that enhances the "deep thinking" capabilities of the Claude-3.5 AI model based on the Deep Thinking protocol and browser extensions, making its thinking logic closer to that of humans. It supports AI in a natural, unfiltered way...
OmniVision is a compact multimodal model with 968M parameters, optimized for edge devices. OmniVision can handle both visual and text input, and based on improvements to the LLaVA architecture, it significantly reduces the number of image tokens, lowers latency, and...
Free Video-LLM is an innovative, training-free, and highly efficient video language model that leverages cue-guided visual perception technology to achieve efficient understanding of video content. The model uses pre-trained image LLMs and requires no additional training to adapt...
LogoCreator is an open-source logo generator that uses Flux Pro 1.1 technology provided by Together AI to quickly create professional-style logos. The project uses Next.js and TypeScript to build its application framework, and incorporates Shadcn and Tailwind...
The Faxin Legal Foundation Model is a general-purpose model with hundreds of billions of parameters, based on the research achievements of Tsinghua University and Mianbi Intelligent. Released by the Supreme People's Court, it is positioned as a national-level legal AI infrastructure. It provides generative AI underlying capabilities...
Audio Decomposition is an audio processing technology that uses Fourier transform and envelope matching to separate individual notes and instruments in music, converting music into sheet music. The Audio Decomposition open-source project is developed by Matthew...
Florence-2 is a versatile vision model developed by Microsoft Azure AI, capable of performing various computer vision tasks such as image captioning, object detection, visual localization, and image segmentation. Florence-2 is based on the Transformer architecture...
k0-math is the latest mathematical reasoning model from Dark Side of the Moon, emphasizing deep thinking abilities. In benchmark math tests such as MATH, middle school entrance exams, college entrance exams, and postgraduate entrance exams, k0-math outperforms OpenAI's o1 series models. The model is based on...
MagicQuill is an open-source AI-powered interactive image editing tool jointly developed by the Hong Kong University of Science and Technology, Ant Group, Zhejiang University, and the University of Hong Kong. Based on a user-friendly interface and AI-supported intelligent suggestions, it enables precise local image editing...
ai-chatbot is an open-source project launched by Vercel, built on the Next.js framework and the Vercel AI SDK. ai-chatbot provides a fully functional and easily customizable AI chatbot template to help developers quickly build high-performance chatbots...
LLaMA-Mesh is a project jointly launched by Tsinghua University and NVIDIA. It combines 3D mesh generation with Large Language Models (LLMs) to enable the direct generation of 3D models from text prompts. The project uses OBJ file format to store 3D meshes...
iAgents is a multi-AI agent collaboration framework developed by Tsinghua University. It's based on equipping each user with a personal AI agent to facilitate collaboration and complete daily tasks. The agents can understand user files and commands, learn from collaboration, and achieve self-management...
DanceFusion is an open-source framework developed by Tsinghua University, focusing on audio-driven dance motion reconstruction and generation. Combining a hierarchical spatiotemporal Transformer-VAE and a diffusion model, DanceFusion can handle incomplete motion capture on social media...
Symphony Creative Studio is an AI-powered video creation tool launched by TikTok, helping advertisers and content creators streamline the video production process. Symphony Creative Studio integrates video generation, conversion, and extension capabilities...
Skywork O1 is the 4.0 version of the Skywork Model 4.0 launched by Kunlun Tech. It is the first O1 model in China with Chinese logical reasoning capabilities. Skywork O1 inherently incorporates thinking, planning, and reflection abilities into its model output, significantly improving...
Voyage Multimodal-3 is an advanced multimodal embedding model from Voyage AI. It can process interleaved text and images, and capture key visual features from screenshots of PDFs, slides, tables, etc., without requiring complex document parsing...
Hali is a multimodal, multi-agent collaborative AI agent launched by Terminus in collaboration with the international accessible luxury brand Buttons. Hali possesses four key characteristics: human-like thinking, long memory, physical world perception, and multi-agent collaboration. Its semantic understanding accuracy exceeds...
Agent K v1.0 is an end-to-end autonomous data science agent jointly developed by Huawei Noah's Ark Lab and the University College London team. It can automate, optimize, and generalize the processing of various data science tasks. Agent K v1.0 is based on...
Pixtral Large is an open-source, 124 billion-parameter ultra-multimodal model from Mistral AI in France. It boasts state-of-the-art image understanding capabilities, supports 128K context, and can understand text, charts, and images. Pixtral Large is based on Mistral...
Qwen2.5-Turbo is an advanced language model launched by Alibaba, which expands the context length from 128k to 1M, equivalent to 1 million English words or 1.5 million Chinese characters. This expansion allows the model to handle longer texts, such as novels...
LLaVA-o1 is an open-source visual language model developed by a research team comprised of researchers from Peking University, Tsinghua University, Pengcheng Lab, Alibaba DAMO Academy, and Lehigh University. It is based on Llama-3.2-Vision...
PixelWave Flux.1-dev 03 is an AI image generation model fine-tuned on the NVIDIA 4090 based on the FLUX.1-dev model. It boasts excellent generalization capabilities and performs admirably in handling various artistic styles, photographic, and anime images...
Computer Use OOTB is an open-source GUI framework that uses the Claude 3.5 Computer Use API to automate computer control. The framework supports cross-platform operation, allowing users to easily deploy it on Windows and macOS systems...