Latest AI Resources

HunyuanImage 2.1 is Tencent's open source graphic model, designed for high-quality image generation. The model supports native 2K resolution, can accurately render complex scenes and details, so that the character's expression and movement can be vividly reproduced.

Molmo 2 is an open source multimodal model released by the Allen Institute for AI (Ai2) to improve video and multi-image understanding. Three variants are included; Molmo 2 (8B), Molmo 2 (4B) and Molmo 2-O...

UniPixel is a novel multimodal model jointly proposed by Hong Kong Polytechnic University, Tencent, Chinese Academy of Sciences and Vivo to achieve pixel-level visual language understanding. By unifying object referencing and segmentation capabilities, it supports a variety of fine-grained tasks such as image segmentation, video segmentation, region understanding, and pi...

CWM (Code World Model) is a 32-billion-parameter open-source world language model released by the Meta FAIR team, designed for code generation and reasoning. Introducing the concept of "world model", it can simulate the code execution process, predict the variable state changes, and advance...

LandPPT是基于大语言模型的开源AI PPT生成工具，支持通过主题或上传文档（PDF/Word/Excel）一键生成专业演示文稿。集成了多模型驱动、实时联网搜索和AI绘图功能，提供丰富的模板和场景...

Ling-V2 is a family of large-scale language models based on the MoE architecture introduced by the Ant-Belling team. The first version, Ling-mini-2.0, has 16 billion total parameters, with only 1.4 billion parameters activated per input token.

Depth Anything 3 (DA3) is a 3D visual reconstruction model developed and open-sourced by the Byte Jump Seed team. Through a single Transformer architecture to realize the spatial geometry of any viewpoint reconstruction, only need to predict the depth map and ray map can restore the three-dimensional scene, compared to...

IQuest-Coder-V1是九坤投资旗下至知创新研究院研发的开源代码大模型系列，专注于代码智能领域，具备自动编程、Bug修复和代码解释等能力。模型采用创新的Code-Flow训练范式，从代码库演化...

WorldMirror 1.1 (WorldMirror) is an open source 3D reconstruction of large models released by Tencent's WorldMirror team, which is an upgraded version of the WorldMirror series. It supports multi-view images, videos, and multi-modal a priori inputs such as camera position, internal reference, depth map, etc. It breaks through the traditional 3D reconstruction that only relies on...

Alpamayo-R1 is a NVIDIA-developed Vision-Language-Action (VLA) model with reasoning capability, designed to enhance the decision-making capability of autonomous driving in complex scenarios. By introducing a causal chain reasoning mechanism, the vehicle is able to analyze scene causality (e.g., "cause before...

nanobot 是香港大学数据智能实验室（HKUDS）开源的超轻量级个人AI助手框架，仅用约 4,000行Python代码实现了完整的多通道AI助手功能。作为 OpenClaw 的轻量替代品，nano...

Paper2Video is an open-source presentation video project for automatic generation of academic papers by Show Lab at National University of Singapore. Using the PaperTalker multi-intelligence framework, papers are transformed into full presentation videos containing slides, subtitles, voiceover and speaker avatar...

HunyuanVideo 1.5 is a Tencent hybrid big model team open source lightweight video generation model , based on the Diffusion Transformer (DiT) architecture , the number of parameters is 8.3B. support for generating 5-10 seconds of high-definition video , sub...

EverMemOS is an open source long-term memory operating system launched by the Shanda team led by Chen Tianqiao, designed for AI intelligences to solve the problem of memory breakage caused by the fixed context window of large language models. The system is based on the human brain memory mechanism, using a four-layer architecture (agent layer, memory layer, index layer...

Mini-o3 is an open source model jointly launched by ByteDance and the University of Hong Kong, focusing on solving complex visual search problems. The model has a powerful multi-round interactive reasoning capability, and can locate the target through deep exploration and trial-and-error.

Youtu-Embedding is a generalized text representation model open-sourced by Tencent's Youtu Lab, designed for enterprise-level applications. Through deep neural networks to map the text to a high-dimensional vector space, so that semantically similar sentences are closer in that space, to achieve accurate semantic retrieval.

MAI-UI is an open source generalized GUI intelligent body base model from Alibaba Tongyi Labs, with four major capabilities: cross-application operation, fuzzy semantic understanding, active user interaction and multi-step process coordination. Adopting end-cloud collaboration architecture, the lightweight model resides in the device to handle daily tasks, and complex tasks can call the cloud big...

女娲智能体OS（Nuwax Agent OS）是西南财经大学赵宇教授团队推出的全球首个开源通用智能体操作系统。具备自主执行引擎，可实现从需求拆解到任务规划与执行的全链路自动化。系统支持可视化工作流编排...

Granite-Docling-258M is an ultra-compact open source visual language model from IBM designed for efficient document conversion. The model converts documents into machine-readable formats while leaving layout, tables, formulas, and other elements intact.

TuriX-CUA 是开源的 AI 桌面自动化工具，能通过截屏、多模态模型决策和自动化操作实现电脑交互。让 AI 模型直接操作电脑桌面环境。支持 macOS 和 Windows 系统，通过先进的计算机...

NitroGen is an open source gaming AI model developed by NVIDIA in conjunction with Stanford University, Caltech, and other institutions, capable of playing over 1,000 different types of games. The model is based on the GROOT N1.5 architecture, and is realized by analyzing 40,000 hours of game video data (including joystick operation annotation)...

LongCat-Flash-Thinking is a highly efficient reasoning model released by the LongCat team at Mission LongCat that has become more powerful and specialized while maintaining the extreme speed of LongCat-Flash-Chat. The model is based on logic, math, code, intelligence...

AnyI2V is an image animation generation framework jointly launched by Fudan University, Alibaba Dharma Institute and others, which supports the conversion of static conditional images (e.g., grids, point clouds, etc.) into dynamic videos without the need for complex training processes and large amounts of data.

GELab-Zero is an open source end-side multimodal GUI Agent model by Step Leap Team , built on Qwen3-VL-4B-Instruct base model with 4B parameters.It can recognize UI elements and perform operations such as clicking and sliding, and supports cross-application tasking ...

RoboBrain-X0 is the world's first open source embodied model that supports zero-sample cross-ontology generalization open-sourced by Wisdom Source Research Institute, which is of great industrial significance. It can drive multiple real robots of different configurations to complete basic operation tasks without fine-tuning, and after a small amount of sample fine-tuning, it demonstrates the ability to replicate ...

VLAC is an open source embodied reward macromodel from Shanghai Artificial Intelligence Laboratory. Based on InternVL multimodal macromodel, it integrates Internet video data and robot operation data to provide process reward and task completion estimation for robot reinforcement learning in the real world.VLAC can effectively ...

AionUi是一个免费开源的多AI Agent桌面应用，支持将Gemini CLI、Claude Code等命令行AI工具整合到图形界面，提供本地文件操作、多会话管理、跨平台运行等功能。支持macOS...

GLM-ASR is a family of high-performance speech recognition models open-sourced by Smart Spectrum AI, including the cloud-based model GLM-ASR-2512 and the open-source end-side model GLM-ASR-Nano-2512.GLM-ASR-2512 is the world's leading cloud-based speech recognition model, supporting multiple...

nanochat is an open source project released by AI legend and former Tesla AI Director Andrej Karpathy that allows individuals to quickly train a small ChatGPT-like language model at a very low cost and simplicity. The entire project uses only about 800...

Hybrid Motion1.0 (HY-Motion1.0) is Tencent Hybrid team open source text generated 3D action model , using 1 billion parameters Diffusion Transformer architecture , can be directly generated through natural language description of high-quality 3D character animation .

MiMo-Embodied is the world's first cross-embodied base model that successfully integrates Embodied AI and autonomous driving open-sourced by Xiaomi Group. It solves the knowledge migration problem between Embodied AI and autonomous driving, and realizes the unified modeling of tasks in the two fields.

Paper2Any是北京大学DCAI课题组开源的多模态辅助平台，专注于从论文PDF、图片和文本中快速生成多种科研内容。具备一键生成科研绘图的功能，能从多种输入源生成模型架构图、技术路线图和实验数据图等...

HunyuanOCR is a high-performance optical character recognition model open-sourced by the Tencent hybrid team, with a reference number of only 1 billion. Developed based on the hybrid multimodal architecture, it adopts an end-to-end design and can efficiently handle text detection, recognition and document parsing tasks. The model scored 94.1 points in the complex document test, surpassing...

LazyCraft is an open source AI Agent application development and management platform built by Shangtang based on the open source framework LazyLLM, which provides one-stop AI application development solutions for enterprises and developers. It helps developers to quickly build and release large model applications with low threshold and low cost...

InternVLA-M1 is an open-source embodied operating "brain" of Shanghai Artificial Intelligence Laboratory, which is a large model of two-system operation oriented to instruction following. It builds a complete closed loop covering "think-act-learn" and is responsible for high-level spatial reasoning and task planning. The model adopts a two-phase training cur...

PaCoRe (Parallel Coordinated Reasoning) is StepFun's open source innovative parallel collaborative reasoning framework, through a massively parallel thinking mechanism, from multiple perspectives to simultaneously explore the problem solution, breaking through the traditional...

OpenScreen is an open source and free screen recording tool that provides users with an easy to use and fully functional alternative to Screen Studio. It supports both Mac and Windows, is completely free and follows the MIT protocol, and can be used for individual...

EchoCare is a large model of ultrasound base developed by the Center for Artificial Intelligence and Robotics Innovation (CAIR) at the Hong Kong Institute of Innovation and Research of the Chinese Academy of Sciences (CAS), trained based on the world's largest ultrasound image dataset (more than 4.5 million images), covering multi-center, multi-region, multi-ethnicity, and more than 50 individuals...

FlowAct-R1是字节跳动开源的实时交互数字人视频生成框架，能通过单张参考图和音频流式生成无限时长的高保真全身动态视频。核心创新在于分块流式生成技术，将视频拆解为0.5秒一小段接力处理，配合结构化...

Qwen3-Next is a new generation of hybrid architecture big model open source by Ali Tongyi, combining Gated DeltaNet and Gated Attention technology, good at dealing with long text, fast inference and saving computing resources.

ChronoEdit, an open-source AI image editing framework developed by NVIDIA in conjunction with the University of Toronto, redefines the image editing task as a video generation task to ensure that the editing results are temporally and physically consistent. By distilling a pre-trained video generation model with 14B parameters from a...

MobileLLM-R1 is Meta's open source series of efficient inference models designed for mathematical, programming and scientific reasoning. It contains a base model and a final model, with 140 million, 360 million and 950 million parameter versions, respectively. The models are not generic chat models and are supervised fine-tuned (SFT...

MiMo-V2-Flash is an open source MoE architecture large model released by Xiaomi, with 309 billion total parameters and 15 billion active parameters, focusing on efficient reasoning and intelligent body applications. The model adopts hybrid attention architecture and multi-word meta-prediction technology, with an inference speed of 150 tokens/second, into...

Ming-flash-omni-Preview is an open-source full-modal macromodel released by Ant Group inclusionAI, with a parameter scale of hundreds of billions, based on the sparse MoE architecture of Ling 2.0, with total parameters of 103B and activations of 9B. in full-modal understanding and generating...

AntAngelMed（蚂蚁·安诊儿医疗大模型）是浙江省卫生健康信息中心、蚂蚁健康、浙江省安诊儿医学人工智能科技有限公司联合开发的开源医疗大模型。模型采用混合专家架构（MoE），总参数量达1000亿...

Androidify is Google's open source project to help developers learn how to build AI-driven apps on Android. The project uses Google's latest technologies such as Jetpack Compose, Gemini API (via Fire...

SHARP (Sharp Monocular View Synthesis in Less Than a Second) is Apple's open source monocular view synthesis technology. It can quickly generate a realistic 3D representation of a scene from a single photo in less than a second...

FLUX.2 [klein] 是 Black Forest Labs 推出的开源轻量级图像生成与编辑模型，专为快速推理和低延迟应用场景设计。支持文本生成图像、图像编辑以及多参考图像生成，能在不到1秒内...

LLaVA-OneVision-1.5 is an open-source multimodal model by the EvolvingLMMS-Lab team, using 8B parameter scale, through a compact three-phase training process (language-image alignment, conceptual equalization and knowledge injection, and instruction fine-tuning) on 128 A800...

DeepSeek-OCR 2是DeepSeek团队开源的新一代OCR模型，核心创新在于采用DeepEncoder V2架构，将传统固定栅格扫描的视觉编码方式升级为基于语义推理的动态处理。模型通过因果流...

VitaBench is the first interactive Agent evaluation benchmark for complex life scenarios released by the LongCat team of Meituan, assessing the comprehensive capabilities of large model intelligences in real life scenarios. The three high-frequency life scenarios of take-away ordering, restaurant dining, and traveling are used as the carrier to build the package...

OmniVinci is an open-source, fully modal large-scale language model developed by NVIDIA that solves the problem of modal fragmentation in multimodal models through architectural innovation and data optimization. Alignment of visual and audio embeddings is enhanced by OmniAlignNet, which utilizes temporally embedded group capture...

KAT-Dev-72B-Exp is an open-source programming-specific large language model launched by the Racer team, optimized based on reinforcement learning technology, which achieved an accuracy rate of 74.6% in the SWE-Bench Verified benchmark test, the best performance of any open-source model at present. The model uses innovative...

FireRed-Image-Edit 是小红书 Super Intelligence 团队开源的通用图像编辑模型，基于扩散 Transformer 架构，在 GEdit、ImgEdit 等多个权威评测...

VibeThinker-1.5B is a 1.5 billion parameter large-scale language model open-sourced by Weibo AI. Fine-tuned based on Alibaba's Qwen2.5-Math-1.5B, it is optimized for mathematical and coding tasks and performs well, with industry-leading inference performance.

SmartResume is Alibaba open source intelligent resume parsing and optimization tool , can efficiently extract structured information from PDF, images or Office documents , such as basic information , education and work experience . By integrating OCR technology and PDF metadata...

Glow is open source command line tool for elegantly rendering Markdown files in the terminal. The tool supports highlighting code blocks , mathematical formulas and other complex elements , providing a wealth of features such as custom styles , paging display , mouse support and so on.

GPT-5-Codex is a powerful programming optimization model from OpenAI, further enhanced by GPT-5 and designed for software engineers. The model generates high-quality code quickly, supports multiple programming languages, and optimizes existing code to improve performance.

FIBO is the world's first open source text generation image model with native JSON support developed by Bria AI. Based on the DiT (Diffusion Transformer) architecture with 8B parameters, it adopts the Flow Matching training method...

SAM 3D is a 3D reconstruction model based on the SAM series from Meta, including two branches, SAM 3D Objects and SAM 3D Body. SAM 3D Objects can generate interactive 3D object models from a single photo, supporting...

Mixed World Model 1.5 (Tencent HY WorldPlay) is the industry's first open source real-time world modeling framework released by Tencent, covering the entire chain of data, training, and streaming inference deployment. The core is the WorldPlay autoregressive diffusion model, which uses Next-F...

Fara-7B is a Microsoft open source release of a 7-billion-parameter-scale computer-operated agent (CUA) model based on the Qwen 2.5-VL-7B architecture. By visually parsing web page screenshots and performing clicks, inputs, and other actions on the screen, without relying on additional accessibility trees or multiple large models...

MedASR is a 105 million parameter medical speech recognition model open-sourced by Google, fine-tuned on a 5,000-hour desensitized clinical corpus, optimized for drug, dosage, and anatomical terminology, with a built-in 6-gram medical language model, and a word error rate of only 4.6 on the private radiology dataset RAD-DICT...

Frappe Builder is open source low-code website builder, developed by Frappe, the core feature is to provide a Figma-like visual editor that supports drag-and-drop components to build websites quickly. Part of the Frappe ecology (Frappeverse)...

OpenAutoGLM is an open source intelligent body model with the ability of "cell phone use", which can understand the content of the cell phone screen through multi-modal perception, and automatically generate the operation flow to complete the user-specified tasks. Users only need to use natural language to describe the needs, such as "open Meituan to search for nearby hot pot ...

Paper2Slides is an open source AI tool from the Data Intelligence Laboratory of the University of Hong Kong that converts academic papers into professional slides or posters in one click. Using RAG (Retrieval Augmented Generation) technology, directly parsing the document content rather than relying on network information, to ensure that the generated PPT is highly consistent with the original...

ClipSketch AI is open source video to hand-drawn split-screen tool designed for short video creators. It can convert videos from B station, Little Red Book and other platforms into hand-drawn style storyboards with one click, support marking key frames, automatic generation of sub-scenes and social copy, and can integrate user-defined roles.

Step-Audio-EditX is an open source audio editing grand model, developed by the Step-Star team, focusing on fine-grained manipulation of audio content through artificial intelligence technology. The model can dynamically adjust the mood of the audio, speaking style (such as petulant, old man accent, etc.) and paralinguistic elements (such as laughter, sigh...

OpenAgents is the open source project that creates a network of AI agents and facilitates open collaboration between agents. A basic network infrastructure is provided to enable AI agents to seamlessly connect and collaborate. Users can quickly start their own agent network, extend functionality through a modular architecture, support...

LongCat-Flash-Omni is an open source fully modal big language model released by the LongCat team of Meituan. With a parameter scale of 560 billion (27 billion activated parameters), it realizes millisecond-level real-time audio and video interaction capabilities while maintaining a large number of parameters.

SAM Audio is an open source multimodal audio segmentation model introduced by Meta to accurately separate arbitrary target sounds from complex audio mixes. By combining textual, visual, and temporal dimensional cues, it enables flexible and efficient audio processing for tasks such as audio editing, denoising, sound extraction, and...

OpenAkita是开源的自进化AI助手框架，提供智能、灵活且易于使用的AI辅助工具。每日自动执行内存整合、错误自检与修复、任务复盘，遇到卡壳时自动生成新技能并安装依赖，越用越聪明。支持Windows...

ERNIE-4.5-21B-A3B-Thinking is Baidu's open source large-scale language model focused on reasoning tasks. Using the Mixed Expert (MoE) architecture , the total number of references to 21 billion , each token activates 3 billion parameters to support 128K long context window ...

ClawFeed是开发者Kevin He推出的开源AI新闻摘要工具，解决信息过载问题。通过聚合Twitter、RSS、GitHub等多平台信息源，利用AI自动生成4小时、每日、每周和每月的结构化摘要...

LongCat-Audio-Codec is an open source speech codec solution from the LongCat team of Meituan. The program is designed for Speech Large Language Model (Speech LLM), through the semantic and acoustic dual Token parallel extraction mechanism , taking into account the semantic and acoustic features of speech ...

Zen Browser is an open source browser based on the Firefox kernel, focusing on a simple and efficient browsing experience, with the core features of vertical tab bar and workspace isolation. With the sidebar design, it can clearly display the full titles of 50+ tabs and supports multi-window split-screen browsing.

Wan-Move is an open source AI video generation framework jointly developed by Ali Tongyi Labs, Tsinghua University and other organizations, focusing on high-quality video synthesis through precise motion control technology. The core technology is "potential trajectory guidance", which can seamlessly add point-level motion control to the existing image-to-video model...

Step-Audio-R1.1是阶跃星辰开源的全球首个原生语音推理模型，最新升级版本在权威评测榜单Artificial Analysis Speech Reasoning中以96.4%准确率登顶。模型...

AutoMV is an open source music video generation system developed by the M-A-P team in collaboration with several universities, which can automatically generate coherent music videos based on complete songs without training.It adopts a multi-intelligence body collaboration model, including music analysis, scriptwriting, directing, and quality control modules, and can accurately analyze the lyrics, beats, and...

DeepSearchQA is Google's open-source AI research Agent test benchmark, specifically designed to evaluate the performance of intelligences on complex multi-step query tasks. It consists of 900 hand-designed "causal chain" tasks covering 17 domains, requiring the AI to act like a human researcher and push through multi-step...

PersonaLive is an open source real-time AI face-swapping live streaming framework, jointly developed by the University of Macau, dzine.ai, and the GVC Lab at the University of the Greater Bay Area. It can realize low-latency and high frame rate digital person drive on ordinary consumer-grade graphics cards (12GB video memory), and support real-time through the camera...

LLaSO is an open source speech model launched by Beijing Depth Logic Intelligence Technology Co. Ltd, which solves the problems of data dispersion and insufficient task coverage in the field of large-scale speech language modeling by integrating speech and text data and providing alignment datasets, command fine-tuning datasets and evaluation benchmarks.

Kaleido is an open source multi-subject reference video generation model jointly developed by Hefei University of Technology, Tsinghua University and Smart Spectrum AI. It generates subject-consistent videos through multiple reference images, solving the deficiencies of existing models in multi-subject consistency and background decoupling.Kaleido generates videos through specialized data...

VTP (Visual Tokenizer Pre-training) is a key technology for visual generative models proposed by MiniMax Conch Video team, which enhances the performance of generative systems by improving the pre-training method of visual tokenizer (tokenizer). The traditional method...

UniWorld V2 is a new generation of image editing model jointly launched by RabbitZhan Intelligence and UniWorld team of Peking University. It has significant advantages in the field of image editing, especially in Chinese comprehension and execution of complex commands. The model can accurately render artistic Chinese fonts and support fine...

GLM-5是智谱AI推出的旗舰级开源大模型，采用744B参数规模（激活40B），专为Agentic Engineering智能体工程打造。模型在编程与Agent能力上取得开源SOTA表现，SWE-be...

Nemotron 3 is a family of open source AI models released by NVIDIA in Nano, Super and Ultra sizes. It adopts the hybrid potential expert hybrid (latent MoE) architecture to significantly improve inference efficiency and reduce operating costs. Among them...

json-render是Vercel Labs开源的AI生成UI的工具，通过“AI → JSON → UI”的流程实现结构化、可控的界面生成。要求AI仅输出符合预定义Schema的JSON数据，前端再...

SurfSense is an open source AI research and knowledge management tool. Highly customizable, it can connect to search engines, Slack, Jira, Notion, YouTube, GitHub, and many other external data sources to facilitate users to integrate information. Users can upload a variety of...

T5Gemma 2 is a new generation encoder-decoder model open-sourced by Google, based on the Gemma 3 architecture upgraded with multimodal and long context processing capabilities. It supports a wide range of data types, including text and images, and is capable of handling very long contexts (up to 128K) in generating...

TalkCody is a free and open source AI programming assistant desktop application , built on Rust + Tauri 2 , support for Windows, macOS and Linux three platforms , with native performance , fast startup and low resource consumption advantages . Supports more than 50 mainstream A...

Qwen3-Coder-Next是阿里巴巴通义千问团队开源的专为编程智能体设计的高效混合模型，基于80B总参数的Qwen3-Next架构，推理时仅激活3B参数。核心创新在于采用环境交互和强化学习训练方...

SceneGen is an open source method for generating 3D scenes from a single image at Shanghai Jiao Tong University. From a single scene image and a target resource mask, a complete scene containing multiple 3D resources is efficiently generated, including the geometric structure of the resources, texture and relative spatial location.

Astron Agent is an open source enterprise-grade intelligent workflow development platform of KDDI , focusing on helping enterprises quickly build a landable AI agent application . Using Java + Spring Boot technology stack , support for lightweight private deployment (minimum 2-core 4G configuration) , built-in ...

Qwen3-VL-Embedding是阿里通义团队开源的多模态嵌入模型，属于Qwen3-VL系列，主要用于跨模态检索任务。模型将文本、图像、视频等不同模态数据映射到同一语义空间，通过双塔架构生成向量表...

Omnilingual ASR is a multilingual speech recognition framework introduced by Meta, covering 1600+ languages, with 78% language character error rate lower than 10%. its 7 billion parameter wav2vec 2.0 encoder combined with CTC and Transformer decoder, support...

MemMachine is an open source AI memory system developed by MemVerge, designed for AI models and intelligences, which can store and recall interaction data like the human brain, solving the problem of AI "stateless memory loss". It adopts a layered architecture (short-term memory, long-term memory, user image...

DeepSeek-Math-V2 is an open source mathematical reasoning model by DeepSeek, an AI company under Phantom Cube, and the latest version is based on DeepSeek-V3.2-Exp-Base improvement, with performance surpassing that of Gemini DeepThink to reach the international number...

TurboDiffusion is a video generation acceleration framework jointly open-sourced by Tsinghua University, BioDigital Technology, and UC Berkeley, which is able to improve video generation speed by 100-200 times while maintaining nearly lossless picture quality. Through sparse linear attention, sample step distillation and 8-bit...