Browser Use is an intelligent browser tool specifically designed for large language models. This innovative Python library allows AI agents to browse and interact with web pages as naturally as humans. Browser Use supports multi-tab management, visual...
TRELLIS is a 3D generative model developed by Tsinghua University, the University of Science and Technology of China, and Microsoft Research. Based on the Structured LATent (SLAT) representation, it generates high-quality, diverse 3D assets from text or image cues...
WiS (Who is Spy) is an innovative online AI competition platform launched by the technology research teams of Taotian Group and Alibaba. It is specifically designed for testing and analyzing multi-agent systems (MAS) based on large language models (LLMs). WiS...
DRT-o1 is a series of AI models developed by Tencent Research Institute that significantly improves the translation quality of literary works through Long Chain Thinking (CoT) technology, especially when dealing with rhetorical devices such as metaphors and allegories. The model can understand...
FastExcel is an open-source Java library that provides a fast, concise Excel processing tool that can solve the problem of large file memory overflow. FastExcel is compatible with EasyExcel and offers performance optimizations, bug fixes, and new features such as reading specified...
FinRobot is an open-source AI agent platform focused on applications in the financial sector. It leverages Large Language Models (LLMs) to build specialized AI agents capable of complex analysis and decision-making in the financial field. The platform utilizes Financial Thought Chains (CoT) to provide hints...
DeepSeek V3 is the latest open-source AI model from DeepSeek, the AI company under the well-known private equity giant, Magic Square Quant. It shows significant improvement in multi-language programming capabilities. Its performance in the Aider multi-language programming assessment...
3DHM (3D Human Motions) is an advanced 3D human motion generation technology developed by researchers at the University of California, Berkeley. It can generate dynamic human videos with 3D control from a single photograph, achieving the transformation from static images...
Diff-Instruct is an advanced knowledge transfer method used to extract knowledge from pre-trained diffusion models to guide the training of other generative models. It is based on a novel divergence metric—Integral Kullback-Leibler (IKL) divergence...
VidTok (Video Tokenizer) is an advanced video tokenizer open-sourced by Microsoft. It uses efficient algorithms to convert video content into a series of "video words." It supports both continuous and discrete tokenization, and features flexible compression ratios and diverse processing options...
Infinity is a visual generative model launched by ByteDance, based on bit-level autoregressive modeling, capable of generating high-resolution, realistic images based on language instructions. Infinity utilizes a tagger with an infinite vocabulary, a classifier, and bit-level self-correction...
ModernBERT is a modern encoder-only Transformer model jointly developed by Answer.AI, LightOn, Johns Hopkins University, NVIDIA, and HuggingFace. It represents a significant upgrade to the classic BERT model.
Cobalt is a free and open-source image, audio, and video downloader that provides a clean, ad-free experience. Cobalt supports downloading video, audio, and images from all platforms, including major video websites, social media, and music platforms.
CogAgent-9B is a dedicated agent task model trained on GLM-4V-9B. It only requires screenshots as input and does not require text representations such as HTML. CogAgent-9B supports high-resolution image processing and is bilingual (Chinese and English)...
AGUVIS is a unified, purely visual framework jointly developed by the University of Hong Kong and Salesforce. It is designed for autonomous GUI agents and can operate on various platforms, such as web, desktop, and mobile devices. AGUVIS is based on image observation and...
Enhance-A-Video is a video generation enhancement algorithm jointly developed by the National University of Singapore, the Shanghai Artificial Intelligence Laboratory, and the University of Texas at Austin. The algorithm significantly improves the quality of AI-generated videos, especially...
Valley is a multimodal large-scale model launched by ByteDance for processing diverse tasks involving text, image, and video data. Valley achieved top results in internal e-commerce and short video benchmarks and in OpenCom...
UniT2IXL is a native Chinese text-to-image model launched by China Unicom AI, trained and inferred entirely on the domestic Ascend AI hardware and software platform. The model employs a composite language encoding module, optimized for long Chinese texts...
DiTCtrl is a multi-cue video generation method based on the Multimodal Diffusion Transformer (MM-DiT) architecture, jointly developed by the Chinese University of Hong Kong, Tencent, and other institutions. DiTCtrl can generate multiple cues without additional training...
MNN (Mobile Neural Network) is a lightweight deep learning inference framework open-sourced by Alibaba Group, providing efficient model deployment capabilities for various devices including mobile devices, servers, PCs, and embedded devices. MNN...
Qiyuan Critical Care Model is the world's first large-scale critical care medical model jointly released by Tencent and Mindray Medical. Designed specifically for ICU wards, it addresses key pain points in intensive care. The model boasts trillions of parameters and has undergone extensive medical testing...
Poetry2Image is an iterative correction framework specifically designed for generating images of classical Chinese poems, proposed by Harbin Institute of Technology. The framework enhances the consistency between the poem and the image through automated feedback and correction loops, effectively...
PeterCat is an open-source intelligent Q&A chatbot assistant. PeterCat helps developers and community maintainers solve technical problems more efficiently, improving community support efficiency. PeterCat is based on automatically built knowledge bases and can integrate with GitHub...
PartGen is an advanced 3D object generation and reconstruction framework, jointly developed by the Visual Geometry Group at Oxford University and Meta AI. PartGen can recognize and generate 3D objects composed of meaningful parts, and these 3D objects can be generated based on text prompts...