Latest AI Resources

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...

The MCP Registry is a centralized platform from GitHub that helps developers discover and install MCP servers more easily.The MCP Registry is here to help developers quickly find the AI tools they need in one place, greatly simplifying...

Comprehensive Introduction Meiman is an online platform specializing in home design and marketing negotiation. The site provides a wealth of design materials, soft furnishings and proposal PPT templates, poster templates, etc. to help designers and homeowners quickly generate high-quality design solutions. Meiman's online soft furnishing design tool can be used in as little as 10 seconds...

Hunyuan-MT-7B is a lightweight translation model introduced by Tencent's Mixed Meta Team, with 7 billion references, supporting the mutual translation of 33 languages and 5 folk-Chinese languages/dialects, including Cantonese, Uyghur, and Tibetan. In the International Association for Computational Linguistics (ACL) WMT2025 competition...

MobiAgent is an open source mobile intelligent body toolchain from IPADS Lab of Shanghai Jiaotong University, which helps users to build their own mobile intelligent assistants. By recording the user's operation trajectory and generating high-quality data, it trains an intelligent body that can understand natural language commands. Core features include efficient...

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...

olmOCR 2 is an open source multimodal document parsing model from the Allen Institute for Artificial Intelligence (AI2) and is an upgraded version of olmOCR. The digitized printed documents (e.g. PDF) will be high...

XTuner V1 is a new generation of large model training engine open-sourced by Shanghai Artificial Intelligence Laboratory (SAL), designed for ultra-large scale sparse Mixed Expert (MoE) model training. Developed based on PyTorch FSDP, it achieves high performance through multi-dimensional optimization of memory, communication and load ...

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...

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...

rStar2-Agent is an advanced AI mathematical reasoning model open-sourced by Microsoft that demonstrates strong mathematical problem solving capabilities by achieving an accuracy of 80.61 TP3T in the AIME24 test. The model is equipped with scientific reasoning capabilities, achieving in the GPQA-Diamond benchmark...

DeepSeek-V3.2-Exp is a DeepSeek open source experimental AI model that significantly improves the efficiency of long text processing by introducing the DeepSeek Sparse Attention (DSA) mechanism. The model is based on DeepSeek...

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...

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...

SongBloom is an open source song generation model developed by Tencent AI Lab in collaboration with The Chinese University of Hong Kong (Shenzhen) and Nanjing University, which solves the problem of "plasticity" in AI music generation, and realizes high-quality, structurally complete song generation. Simply enter 10 seconds of reference audio and corresponding lyrics, and you can...

Ouro is a new type of Looped Language Models (LLMs) developed by the ByteDance Seed team, with the core innovation of directly building inference capabilities in the pre-training phase through a parameter-sharing recurrent computation structure. The model uses 24 layers as the base block through...

DiaMoE-TTS is a multi-dialect speech synthesis framework jointly open-sourced by Tsinghua University and Giant Network, based on the International Phonetic Alphabet (IPA), to solve the problems of dialect data scarcity, orthographic inconsistency, and complex phonological changes. Through a unified IPA front-end standardized phoneme representation to eliminate cross-dialect differences ...

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 .

Ask White o4 is an innovative parallel thinking model that opens 8 thinking paths at the same time, analyzes the problem from multiple perspectives and automatically filters out the optimal solution. The model incorporates advanced Long-CoT reinforcement learning and process reward learning techniques, has powerful deep reasoning capabilities, and performs well in complex tasks.

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...

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...

VibeVoice-ASR是微软开源的统一语音转文本（ASR）模型，专为处理长音频设计，可一次性处理长达60分钟的连续音频，确保语义连贯性和说话人追踪的一致性。支持自定义热词功能，用户可输入特定词汇或...

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.

Wan2.2-Animate is an open source action generation model , support for action imitation and role-playing mode . Users only need to input a character picture and a reference video , the model can migrate the video character's movements and expressions to the picture character , giving the picture character dynamic expression ...

DeepSeek-V3.1-Terminus is an upgraded version of DeepSeek-V3.1, an artificial intelligence language model from the DeepSeek team. The model is optimized in terms of language consistency, code generation, and search capabilities to more accurately...

DreamOmni2 is a multimodal AI image editing and generation model open-sourced by Jiajia's team at HKUST. Can handle both text and image commands, supports multiple reference images, providing creators with more flexible ways of creation. The model is trained using a three-stage data synthesis process , joint training generation/editing...

MiniCPM 4.1 is an ultra-efficient end-side large language model introduced by Facade Intelligence. With InfLLM v2 sparse attention architecture, each lexeme only needs to calculate the relevance to less than 5% lexemes, which significantly reduces the processing overhead of long text. In a 128K long text scenario...

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...

Lynx is a high-fidelity personalized video generation model open-sourced by ByteDance that can generate identity-consistent videos with only a single portrait photo. Built on the diffusion Transformer (DiT) base model , the introduction of ID-adapter and Ref-adapte...

Ming-UniAudio is Ant Group's open source unified audio multimodal generation model that supports mixed input and output of text, audio, image and video. Using multi-scale Transformer and hybrid expert (MoE) architecture , through modality-aware routing mechanism to efficiently handle cross-modal ...

Vibe Kanban是开源的AI编程代理任务管理工具，专为同时使用多个AI编程助手（如Claude Code、Gemini CLI、Codex等）的开发者设计。通过看板形式统一管理任务进度，支持并行...

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...

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...

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...

Qwen3.5是阿里巴巴通义千问团队开源的最新一代大语言模型，属于千问（Qwen）系列的升级版本。Qwen3.5突破了传统文本模型的限制，实现了真正的原生多模态理解，可直接处理文本、图像、视频等多种模...

10Kh RealOmni-Open是简智机器人开源的具身智能数据集，是行业内规模最大的开源具身智能数据集。数据集累计拥有超10000小时数据、100万+片段，覆盖10大场景任务、超过30项技能。数据...

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...

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...

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...

Ming-flash-omni 2.0是蚂蚁集团开源的全模态大模型，集成了视觉、语音和生成能力的AI模型，在多项基准测试中性能领先。支持同时生成语音、环境音效和音乐，能通过自然语言指令精细控制音色、语...

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...

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...

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 ...

Clawra是一个基于OpenClaw框架开发的AI女友程序，由韩国开发者David Im制作，具有完整人设和交互功能。通过Persona Engineering技术赋予AI“18岁亚裔女性练习生”的...

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...

GLM-OCR 是智谱开源的 0.9B 轻量级专业 OCR 模型，在 OmniDocBench V1.5 以 94.6 分刷新 SOTA。兼顾“小体积”与“全场景”，扫描、手写、印章、多语混排、复杂表...

SCAIL (Studio-Grade Character Animation via In-Context Learning) is a film and television grade character animation generation framework proposed by Smart Spectrum in collaboration with Prof. Liu Yongjin's group at Tsinghua University. Through...

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...

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...

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...

MiniCPM-o 4.5 是面壁智能开源的 9B 全模态旗舰模型，以“边看边听主动说”的端到端架构，在手机端即可跑出 GPT-4o 级体验：支持单图、多图、高帧率长视频、实时语音双工对话，首 tok...

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.

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.

XVERSE-Ent是元象科技推出的专注于泛娱乐领域的开源大模型，包含中英文双版本，支持社交互动、游戏叙事和文化创作等场景。模型通过角色一致性强化、长剧情理解等技术优化，能在虚拟角色人设稳定性、复杂故...

PersonaPlex是英伟达开源的全双工语音对话模型，拥有70亿参数。摒弃了传统的语音识别→语言模型→文本到语音的级联流程，采用统一的Transformer架构，能同步处理语音理解与生成。模型支持全...

Xiaomi-Robotics-0 是小米开源的首代具身智能大模型，拥有47亿参数，采用"大脑+小脑"混合架构设计。视觉语言大脑基于多模态大模型，负责理解人类模糊指令与空间推理；动作执行小脑则通过Di...

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...

Protenix-v1是字节跳动ByteDance Seed团队推出的首个开源蛋白质结构预测模型，性能在严格对齐训练数据和模型规模后超越AlphaFold 3。模型具备显著的推理时扩展特性：通过增加采...

Ming-Omni-tts 是蚂蚁集团与Inclusion AI联合开源的多模态音频生成模型，包含0.5B和16.8B-A3B两个版本。模型首次实现了语音、环境音和音乐的统一自回归生成，支持语速、音量...

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.

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...

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...

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...

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...

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.

Kimi K2.5 是月之暗面发布的开源旗舰模型，采用 1T MoE 架构、激活 32B、上下文 256K token，原生支持图文视频多模态输入。在 Agent、代码、视觉理解三大基准均列开源第一...

Mistral Vibe is an open source command line coding assistant from Mistral AI, developed based on the Devstral model, which supports natural language interaction to complete code search, file manipulation, version control and other tasks. Can automatically scan the project structure and Git status through the @ symbol...

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 ...

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 ...

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...

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...

Chatterbox-Turbo 是 Resemble AI 推出的开源文本到语音（TTS）模型，专为高效、低延迟的语音合成而设计。基于350M参数的精简架构，单步推理生成音频，时间延迟极低，在150...

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.

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...

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...

UltraEval-Audio是清华大学NLP实验室、OpenBMB和面壁智能联合开发的音频模型评测框架，最新版本为v1.1.0。专注于解决音频模型复现难、依赖冲突等问题，提供一键复现热门模型（如Vo...

SoulX-FlashTalk是Soul App AI团队开源的实时数字人生成模型，拥有140亿参数量，实现了0.87秒超低延迟和32帧/秒的高帧率。模型通过双向蒸馏技术解决了传统数字人延迟高、画面易...

Ring-2.5-1T 是蚂蚁集团百灵大模型团队开源的全球首个万亿参数混合线性架构思考模型，采用1:7 MLA与Lightning Linear Attention混合设计，激活参数量达63B。模型在...

Chroma 1.0是FlashLabs发布的全球首个开源的实时端到端语音对话模型，兼具低延迟交互、高保真个性化语音克隆和强对话能力。通过紧密耦合语音理解与生成，采用1:2文本-音频token调度策略...

New API是基于Go语言开发的开源AI聚合网关工具，可统一管理30+种主流大模型（如OpenAI、Claude、Midjourney等），将不同模型接口转换为标准化OpenAI格式。

ClawWork是香港大学数据科学实验室开发的AI经济压力测试框架，允许AI在模拟经济环境中完成真实工作任务并获得报酬。核心逻辑是让初始资金仅10美元的AI通过完成220个专业任务（覆盖制造、金融、医...

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.

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.

LingBot-VA 是蚂蚁灵波开源的全球首个“自回归视频-动作世界模型”，把视频生成与机器人控制塞进同一 Transformer，每一步同时输出下一帧世界画面和对应动作，实现“边想边干”。

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.

Qwen3-VL-Reranker是阿里巴巴推出的多模态重排序模型，专门用于提升跨模态检索的精准度。与Qwen3-VL-Embedding协同工作：前者负责快速召回候选结果，后者通过深度跨模态交互（如...

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...

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...

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...

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...

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...

SkyReels-V3是昆仑万维Skywork AI开源的多模态视频生成模型，被誉为视频生成领域的"全能型"标杆。模型基于"一核多支"的统一架构，在单一建模框架内集成三大核心能力：参考图像转视频、智能...

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...

LingBot-World 是蚂蚁集团旗下具身智能公司灵波科技（Robbyant）开源的交互式世界模型，专为具身智能、自动驾驶及游戏开发打造高保真“数字演练场”。模型通过可扩展数据引擎从大规模游戏环境...

RealVideo is an open-source real-time streaming video generation system from Smart Spectrum AI that can quickly generate natural and smooth video responses in 2 to 3 seconds. Users only need to upload a photo and enter text, and the system can generate corresponding voice and video, realizing real-time conversations with AI characters...

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...

PaperBanana是北大与谷歌团队联合开源的AI学术插图自动生成框架，专门解决科研人员绘制方法示意图和统计图表的痛点。框架通过五个智能体协作（检索、规划、造型、渲染和批评），实现从文本描述到Neu...

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...