Back to Rankings返回排行榜
Top 100 · Foundation Models前 100 · 基础模型
100 repositories sorted by foundation models 按 基础模型 排序，共 100 个仓库
| # | Repository仓库 | Stars | Forks | Language语言 | Issues | Description描述 | Last Commit最后提交 |
|---|---|---|---|---|---|---|---|
| 1 | ColossalAI hpcaitech | 41.4k | 4.5k | Python | 443 | Making large AI models cheaper, faster and more accessible使大型人工智能模型更便宜、更快、更容易使用 | 2026-04-27 |
| 2 | OpenVoice myshell-ai | 36.5k | 4.1k | Python | 277 | Instant voice cloning by MIT and MyShell. Audio foundation model.MIT 和 MyShell 的即时语音克隆。音频基础模型。 | 2025-04-19 |
| 3 | claude-code-router musistudio | 33.5k | 2.7k | TypeScript | 788 | Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.使用 Claude Code 作为编码基础设施的基础，让您可以决定如何与模型交互，同时享受 Anthropic 的更新。 | 2026-03-04 |
| 4 | InvokeAI invoke-ai | 27.1k | 2.8k | TypeScript | 372 | Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.Invoke 是稳定扩散模型的领先创意引擎，使专业人士、艺术家和爱好者能够使用最新的人工智能驱动技术生成和创建视觉媒体。该解决方案提供了业界领先的WebUI，并作为多个商业产品的基础。 | 2026-05-05 |
| 5 | LLaVA haotian-liu | 24.8k | 2.8k | Python | 1096 | [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.[NeurIPS'23 Oral] 视觉指令调优 (LLaVA) 旨在实现 GPT-4V 级别及以上的功能。 | 2024-08-12 |
| 6 | Kronos shiyu-coder | 23.0k | 4.0k | Python | 157 | Kronos: A Foundation Model for the Language of Financial MarketsKronos：金融市场语言的基础模型 | 2026-04-13 |
| 7 | unilm microsoft | 22.1k | 2.7k | Python | 641 | Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities跨任务、语言和模式的大规模自监督预训练 | 2026-01-23 |
| 8 | timesfm google-research | 19.4k | 1.9k | Python | 140 | TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.TimesFM（时间序列基础模型）是 Google Research 开发的用于时间序列预测的预训练时间序列基础模型。 | 2026-04-30 |
| 9 | Janus deepseek-ai | 17.7k | 2.2k | Python | 159 | Janus-Series: Unified Multimodal Understanding and Generation ModelsJanus 系列：统一多模态理解和生成模型 | 2025-02-01 |
| 10 | seamless_communication facebookresearch | 11.8k | 1.2k | Jupyter Notebook | 231 | Foundational Models for State-of-the-Art Speech and Text Translation最先进的语音和文本翻译的基础模型 | 2026-04-08 |
| 11 | moshi kyutai-labs | 10.1k | 946 | Python | 67 | Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.Moshi 是一个语音文本基础模型和全双工口语对话框架。它使用 Mimi，一种最先进的流式神经音频编解码器。 | 2026-05-05 |
| 12 | pyod yzhao062 | 9.8k | 1.5k | Python | 196 | A Python library for anomaly detection across tabular, time series, graph, text, and image data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.用于跨表格、时间序列、图形、文本和图像数据进行异常检测的 Python 库。 60 多个检测器、基准支持的 ADEngine 编排以及 AI 代理的代理工作流程。 | 2026-04-16 |
| 13 | notebooks roboflow | 9.4k | 1.4k | Jupyter Notebook | 64 | A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.关于最先进的计算机视觉模型和技术的教程集合。探索从 ResNet 等基础架构到 RF-DETR、YOLO11、SAM 3 和 Qwen3-VL 等尖端模型的一切内容。 | 2026-03-27 |
| 14 | LMFlow OptimalScale | 8.5k | 831 | Python | 76 | An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.用于大型基础模型微调和推理的可扩展工具包。适合所有人的大型型号。 | 2026-04-25 |
| 15 | Depth-Anything LiheYoung | 8.1k | 611 | Python | 127 | [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation[CVPR 2024] 深入一切：释放大规模未标记数据的力量。单目深度估计的基础模型 | 2024-07-17 |
| 16 | Depth-Anything-V2 DepthAnything | 8.0k | 833 | Python | 217 | [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation[NeurIPS 2024] 深度任意 V2。一种更强大的单目深度估计基础模型 | 2026-03-24 |
| 17 | higgs-audio boson-ai | 8.0k | 620 | Python | 89 | Text-audio foundation model from Boson AIBoson AI 的文本音频基础模型 | 2026-01-18 |
| 18 | Qwen-Image QwenLM | 7.9k | 491 | Python | 209 | Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.Qwen-Image是一个强大的图像生成基础模型，能够进行复杂的文本渲染和精确的图像编辑。 | 2026-02-10 |
| 19 | Isaac-GR00T NVIDIA | 6.9k | 1.2k | Python | 193 | NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.NVIDIA Isaac GR00T N1.7 - 通用机器人的基础模型。 | 2026-04-26 |
| 20 | data-juicer datajuicer | 6.4k | 367 | Python | 36 | Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷基础模型的数据处理！ 🍎🍋🌽➡️➡️🍸🍹🍷 | 2026-04-28 |
| 21 | TabPFN PriorLabs | 6.4k | 640 | Python | 25 | ⚡ TabPFN: Foundation Model for Tabular Data ⚡⚡ TabPFN：表格数据的基础模型 ⚡ | 2026-05-05 |
| 22 | YuE multimodal-art-projection | 6.2k | 735 | Python | 84 | YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but openError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2025-06-04 |
| 23 | lingbot-map Robbyant | 5.8k | 545 | Python | 32 | A feed-forward 3D foundation model for reconstructing scenes from streaming data用于从流数据重建场景的前馈 3D 基础模型 | 2026-04-30 |
| 24 | chronos-forecasting amazon-science | 5.3k | 628 | Python | 22 | Chronos: Pretrained Models for Time Series ForecastingChronos：用于时间序列预测的预训练模型 | 2026-04-21 |
| 25 | Kimi-Audio MoonshotAI | 4.6k | 350 | Python | 105 | Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversationKimi-Audio，一个开源音频基础模型，在音频理解、生成和对话方面表现出色 | 2025-06-21 |
| 26 | ACE-Step ace-step | 4.4k | 559 | Python | 136 | ACE-Step: A Step Towards Music Generation Foundation ModelACE-Step：迈向音乐生成基础模型的一步 | 2026-02-15 |
| 27 | llm-foundry mosaicml | 4.4k | 589 | Python | 42 | LLM training code for Databricks foundation modelsError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2026-03-25 |
| 28 | star-vector joanrod | 4.4k | 246 | Python | 48 | StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.StarVector 是 SVG 生成的基础模型，它将矢量化转换为代码生成任务。 StarVector 使用视觉语言建模架构来处理视觉和文本输入，以极高的精度生成高质量的 SVG 代码。 | 2025-11-07 |
| 29 | GLM-4.5 zai-org | 4.3k | 453 | Python | 24 | GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation ModelsGLM-4.5：代理、推理和编码 (ARC) 基础模型 | 2026-02-01 |
| 30 | metavoice-src metavoiceio | 4.2k | 692 | Python | 57 | Foundational model for human-like, expressive TTS类人、富有表现力的 TTS 的基础模型 | 2024-07-30 |
| 31 | DeepSeek-VL deepseek-ai | 4.1k | 592 | Python | 44 | DeepSeek-VL: Towards Real-World Vision-Language UnderstandingDeepSeek-VL：迈向现实世界视觉语言理解 | 2024-04-24 |
| 32 | coobjc alibaba | 4.0k | 523 | Objective-C | 22 | coobjc provides coroutine support for Objective-C and Swift. We added await method、generator and actor model like C#、Javascript and Kotlin. For convenience, we added coroutine categories for some Foundation and UIKit API in cokit framework like NSFileManager, JSON, NSData, UIImage etc. We also add tuple support in coobjc.coobjc 为 Objective-C 和 Swift 提供协程支持。我们添加了await方法、生成器和actor模型，如C#、Javascript和Kotlin。为了方便起见，我们在 cokit 框架中为一些 Foundation 和 UIKit API 添加了协程类别，如 NSFileManager、JSON、NSData、UIImage 等。我们还在 coobjc 中添加了元组支持。 | 2024-06-19 |
| 33 | nixtla Nixtla | 3.9k | 324 | Jupyter Notebook | 48 | TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.TimeGPT-1：生产就绪的预训练时间序列基础模型，用于预测和异常检测。用于在超过 100B 数据点上训练的时间序列的生成式预训练 Transformer。只需几行代码，它就能准确预测零售、电力、金融和物联网等各个领域🚀。 | 2026-05-05 |
| 34 | recognize-anything xinyu1205 | 3.6k | 325 | Jupyter Notebook | 105 | Open-source and strong foundation image recognition models.开源且基础强大的图像识别模型。 | 2025-02-18 |
| 35 | NExT-GPT NExT-GPT | 3.6k | 361 | Python | 81 | Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language ModelError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2025-05-13 |
| 36 | LimiX limix-ldm-ai | 3.4k | 298 | Python | 8 | LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505LimiX：释放通用智能的结构化数据建模能力 https://arxiv.org/abs/2509.03505 | 2026-03-04 |
| 37 | Otter EvolvingLMMs-Lab | 3.4k | 212 | Python | 62 | 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.🦦 Otter，一个基于 OpenFlamingo（DeepMind Flamingo 的开源版本）的多模态模型，在 MIMIC-IT 上进行训练，并展示了改进的指令跟踪和上下文学习能力。 | 2024-03-05 |
| 38 | Ask-Anything OpenGVLab | 3.3k | 269 | Python | 70 | [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.[CVPR2024精彩集锦][VideoChatGPT] ChatGPT带视频理解！还有更多受支持的 LM，例如 miniGPT4、StableLM 和 MOSS。 | 2025-01-18 |
| 39 | Torch-Pruning VainF | 3.3k | 381 | Python | 334 | [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.[CVPR 2023] DepGraph：走向任何结构修剪；法学硕士、视觉基础模型等 | 2025-09-07 |
| 40 | efficientvit mit-han-lab | 3.3k | 242 | Python | 107 | Efficient vision foundation models for high-resolution generation and perception.Error 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2025-09-05 |
| 41 | SuperCLUE CLUEbenchmark | 3.3k | 109 | N/A | 38 | SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese | 2026-02-06 |
| 42 | goku Saiyan-World | 2.9k | 311 | Python | 0 | [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/【CVPR2025亮点】视频生成基础模型：https://saiyan-world.github.io/goku/ | 2025-02-19 |
| 43 | Everlyn-1 Everlyn-Labs | 2.9k | 486 | N/A | 0 | The first open autoregressive foundational video AI model.第一个开放的自回归基础视频 AI 模型。 | 2024-10-14 |
| 44 | InternImage OpenGVLab | 2.8k | 264 | Python | 184 | [CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions【CVPR 2023亮点】InternImage：利用可变形卷积探索大规模视觉基础模型 | 2025-03-25 |
| 45 | pyllama henrywoo | 2.8k | 301 | Python | 61 | LLaMA: Open and Efficient Foundation Language ModelsError 500 (Server Error)!!1500.That’s an error.There was an error. Please try again later.That’s all we know. | 2023-11-08 |
| 46 | helm stanford-crfm | 2.8k | 382 | Python | 48 | Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.语言模型的整体评估 (HELM) 是由斯坦福大学基础模型研究中心 (CRFM) 创建的开源 Python 框架，用于对基础模型进行整体、可重复和透明的评估，包括大语言模型 (LLM) 和多模态模型。 | 2026-05-05 |
| 47 | autodistill autodistill | 2.7k | 213 | Python | 39 | Images to inference with no labeling (use foundation models to train supervised models).无需标记即可进行推理的图像（使用基础模型来训练监督模型）。 | 2025-05-14 |
| 48 | SkyReels-V1 SkyworkAI | 2.7k | 308 | Python | 53 | SkyReels V1: The first and most advanced open-source human-centric video foundation modelSkyReels V1：第一个也是最先进的开源以人为中心的视频基础模型 | 2025-03-10 |
| 49 | EVA baaivision | 2.7k | 187 | Python | 78 | EVA Series: Visual Representation Fantasies from BAAIEVA系列：BAAI的视觉表现幻想 | 2024-08-01 |
| 50 | Painter baaivision | 2.6k | 180 | Python | 55 | Painter & SegGPT Series: Vision Foundation Models from BAAIPainter 和 SegGPT 系列：BAAI 的视觉基础模型 | 2024-12-06 |
| 51 | InternVideo OpenGVLab | 2.3k | 150 | Python | 138 | [ECCV2024] Video Foundation Models & Data for Multimodal Understanding[ECCV2024] 用于多模态理解的视频基础模型和数据 | 2026-03-25 |
| 52 | awesome-llm-powered-agent hyp1231 | 2.2k | 216 | N/A | 10 | Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...由 LLM 提供支持的代理人的很棒的事情。论文/存储库/博客/... | 2025-04-30 |
| 53 | CoOp KaiyangZhou | 2.2k | 234 | Python | 64 | Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)视觉语言模型的快速学习（IJCV'22、CVPR'22） | 2024-05-20 |
| 54 | Metric3D YvanYin | 2.2k | 162 | Python | 80 | The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."“Metric3D：从单个图像进行零样本度量 3D 预测”和“Metric3Dv2：多功能单目几何基础模型......”的存储库 | 2025-03-13 |
| 55 | MambaVision NVlabs | 2.1k | 139 | Python | 14 | [CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone[CVPR 2025] MambaVision 的官方 PyTorch 实现：混合 Mamba-Transformer 视觉主干 | 2026-03-11 |
| 56 | amazon-bedrock-workshop aws-samples | 2.1k | 923 | Jupyter Notebook | 34 | This is a workshop designed for Amazon Bedrock a foundational model service. 这是一个为 Amazon Bedrock 基础模型服务设计的研讨会。 | 2026-04-28 |
| 57 | Awesome-Self-Evolving-Agents EvoAgentX | 2.1k | 150 | N/A | 30 | [Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems[调查]自我进化人工智能代理的全面调查：连接基础模型和终身代理系统的新范式 | 2025-10-11 |
| 58 | JoyAI-Image jd-opensource | 2.1k | 146 | Python | 10 | JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.JoyAI-Image 是用于图像理解、文本到图像生成和指令引导图像编辑的统一多模态基础模型。 | 2026-04-15 |
| 59 | chameleon facebookresearch | 2.1k | 117 | Python | 6 | Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.Meta Chameleon 的存储库，这是 FAIR 的混合模式早期融合基础模型。 | 2024-07-29 |
| 60 | alpaca_eval tatsu-lab | 2.0k | 308 | Jupyter Notebook | 19 | An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.An automatic evaluator for instruction-following language models.经过人工验证、高质量、便宜且快速。 | 2025-08-09 |
| 61 | NitroGen MineDojo | 2.0k | 216 | Python | 21 | A Foundation Model for Generalist Gaming Agents多面手游戏代理的基础模型 | 2026-01-25 |
| 62 | Magma microsoft | 1.9k | 159 | Python | 17 | [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents[CVPR 2025] Magma：多模式 AI 代理的基础模型 | 2026-03-03 |
| 63 | cookbook Liquid4All | 1.9k | 310 | Jupyter Notebook | 2 | Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK使用 Liquid AI 基础模型 (LFM) 和 LEAP SDK 构建的示例、端到端教程和应用程序 | 2026-05-05 |
| 64 | ceval hkust-nlp | 1.8k | 83 | Python | 6 | Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]C-Eval 的官方 github 存储库，中国的基础模型评估套件 [NeurIPS 2023] | 2025-07-27 |
| 65 | graph-fraud-detection-papers safe-graph | 1.8k | 296 | N/A | 0 | A curated list of Graph/Transformer-based fraud, anomaly, and outlier detection papers & resources基于 Graph/Transformer 的欺诈、异常和异常值检测论文和资源的精选列表 | 2026-03-27 |
| 66 | Awesome-Remote-Sensing-Foundation-Models Jack-bo1220 | 1.8k | 163 | N/A | 12 | 2026-03-13 | |
| 67 | Emu baaivision | 1.8k | 83 | Python | 46 | Emu Series: Generative Multimodal Models from BAAIEmu 系列：BAAI 的生成多模态模型 | 2026-01-12 |
| 68 | MarS microsoft | 1.7k | 180 | Python | 9 | MarS: a Financial Market Simulation Engine Powered by Generative Foundation ModelMarS：由生成基础模型提供支持的金融市场模拟引擎 | 2026-04-21 |
| 69 | RoboticsDiffusionTransformer thu-ml | 1.7k | 156 | Python | 38 | RDT-1B: a Diffusion Foundation Model for Bimanual ManipulationRDT-1B：用于双手操作的扩散基础模型 | 2026-01-21 |
| 70 | lag-llama time-series-foundation-models | 1.6k | 199 | Python | 62 | Lag-Llama: Towards Foundation Models for Probabilistic Time Series ForecastingLag-Llama：走向概率时间序列预测的基础模型 | 2025-06-06 |
| 71 | Seed1.5-VL ByteDance-Seed | 1.6k | 66 | Jupyter Notebook | 24 | Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.Seed1.5-VL 是一种视觉语言基础模型，旨在促进通用多模式理解和推理，在 60 个公共基准测试中的 38 个上实现了最先进的性能。 | 2025-06-14 |
| 72 | evo evo-design | 1.5k | 178 | Python | 39 | Biological foundation modeling from molecular to genome scale从分子到基因组规模的生物基础建模 | 2026-03-20 |
| 73 | skforecast skforecast | 1.5k | 187 | Python | 9 | Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models使用 scikit-learn 兼容模型、统计方法和基础模型进行时间序列预测的 Python 库 | 2026-05-05 |
| 74 | php-sdk modelcontextprotocol | 1.5k | 136 | PHP | 24 | The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation.适用于模型上下文协议服务器和客户端的官方 PHP SDK。与 PHP 基金会合作维护。 | 2026-04-26 |
| 75 | mmengine open-mmlab | 1.5k | 446 | Python | 174 | OpenMMLab Foundational Library for Training Deep Learning Models用于训练深度学习模型的 OpenMMLab 基础库 | 2025-12-23 |
| 76 | machine-learning-list elicit | 1.5k | 125 | N/A | 0 | A curriculum for learning about foundation models, from scratch to the frontier学习基础模型的课程，从头到尾 | 2025-11-27 |
| 77 | amazon-bedrock-samples aws-samples | 1.4k | 680 | Jupyter Notebook | 38 | This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models此存储库包含客户开始使用 Amazon Bedrock Service 的示例。这包含所有可用基础模型的示例 | 2026-04-09 |
| 78 | awesome-japanese-llm llm-jp | 1.4k | 46 | TypeScript | 7 | 日本語LLMまとめ - Overview of Japanese LLMs日本法学硕士概述 | 2026-05-05 |
| 79 | Awesome-Robotics-Foundation-Models robotics-survey | 1.4k | 118 | N/A | 1 | 2024-10-07 | |
| 80 | MiMo-V2-Flash XiaomiMiMo | 1.3k | 59 | N/A | 18 | MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation ModelMiMo-V2-Flash：高效推理、编码和代理基础模型 | 2026-01-08 |
| 81 | granite-code-models ibm-granite | 1.2k | 84 | N/A | 3 | Granite Code Models: A Family of Open Foundation Models for Code IntelligenceGranite 代码模型：一系列用于代码智能的开放基础模型 | 2025-06-25 |
| 82 | KnowledgeEditingPapers zjunlp | 1.2k | 81 | N/A | 2 | Must-read Papers on Knowledge Editing for Large Language Models.关于大型语言模型知识编辑的必读论文。 | 2025-07-12 |
| 83 | Awesome-TimeSeries-SpatioTemporal-LM-LLM qingsongedu | 1.2k | 90 | N/A | 2 | A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.时间序列、时空和事件数据的大型（语言）模型和基础模型（LLM、LM、FM）的专业列表。 | 2024-12-22 |
| 84 | visualnav-transformer robodhruv | 1.2k | 184 | Python | 33 | Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.移动机器人基础模型的官方代码和检查点发布：GNM、ViNT 和 NoMaD。 | 2024-09-15 |
| 85 | CoCa-pytorch lucidrains | 1.2k | 90 | Python | 5 | Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in PytorchCoCa 的实现，对比字幕是图像文本基础模型，在 Pytorch 中 | 2023-12-12 |
| 86 | FireRed-Image-Edit FireRedTeam | 1.2k | 71 | Python | 28 | FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity consistency, and seamless multi-element fusion.FireRed-Image-Edit 是一个功能强大的图像编辑基础模型，通过精确的指令遵循、高保真生成、卓越的身份一致性和无缝多元素融合，实现了开源的最先进的性能。 | 2026-04-03 |
| 87 | GLEE FoundationVision | 1.2k | 76 | Python | 45 | [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale[CVPR2024亮点]GLEE：大规模图像和视频的通用对象基础模型 | 2024-10-21 |
| 88 | Awesome-Foundation-Models uncbiag | 1.2k | 60 | N/A | 0 | A curated list of foundation models for vision and language tasks视觉和语言任务基础模型的精选列表 | 2026-04-20 |
| 89 | VideoLLaMA3 DAMO-NLP-SG | 1.1k | 86 | Jupyter Notebook | 68 | Frontier Multimodal Foundation Models for Image and Video Understanding图像和视频理解的前沿多模态基础模型 | 2025-08-14 |
| 90 | cosmos-predict2.5 nvidia-cosmos | 1.1k | 152 | Python | 20 | Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.Cosmos-Predict2.5是Cosmos世界基础模型（WFM）系列的最新版本，专门用于以视频形式模拟和预测世界的未来状态。 | 2026-05-04 |
| 91 | torchxrayvision mlmed | 1.1k | 248 | Jupyter Notebook | 25 | TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.TorchXRayVision：胸部 X 射线数据集和模型库。分类器、分割和自动编码器。 | 2025-09-18 |
| 92 | lingbot-vla Robbyant | 1.1k | 103 | Python | 22 | A Pragmatic VLA Foundation Model务实的VLA基础模型 | 2026-04-30 |
| 93 | ONE-PEACE OFA-Sys | 1.1k | 71 | Python | 8 | A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities跨视觉、音频、语言模式的通用表示模型。论文：ONE-PEACE：探索一种面向无限模态的通用表示模型 | 2024-10-06 |
| 94 | RecFM ustcllm | 1.0k | 677 | N/A | 0 | Comprehensive tools and frameworks for developing foundation models tailored to recommendation systems.用于开发适合推荐系统的基础模型的综合工具和框架。 | 2025-09-16 |
| 95 | python-apple-fm-sdk apple | 1.0k | 60 | Python | 2 | Python bindings for access to the on-device model at the core of Apple Intelligence through the Foundation Models frameworkPython 绑定，用于通过基础模型框架访问 Apple Intelligence 核心的设备上模型 | 2026-03-08 |
| 96 | PointLLM InternRobotics | 1.0k | 56 | Python | 9 | [ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds[ECCV 2024 最佳候选论文 & TPAMI 2025] PointLLM：赋予大型语言模型理解点云的能力 | 2026-03-17 |
| 97 | Foundation-Models-Framework-Example rudrankriyam | 1.0k | 65 | Swift | 0 | Example apps for Foundation Models Framework in iOS 26 and macOS 26iOS 26 和 macOS 26 中基础模型框架的示例应用程序 | 2026-04-28 |
| 98 | Large-Time-Series-Model thuml | 971 | 103 | Python | 6 | Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and subsequent works“Timer: Generative Pre-trained Transformers Are Large Time Series Models”（ICML 2024）及后续作品的官方代码、数据集和检查点 | 2026-03-22 |
| 99 | Time-MoE Time-MoE | 957 | 112 | Python | 15 | [ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"【ICLR 2025聚焦】《Time-MoE：专家混合的十亿级时间序列基础模型》正式落地 | 2026-03-21 |
| 100 | groundingLMM mbzuai-oryx | 953 | 54 | Python | 35 | [CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.[CVPR 2024 🔥] 奠定了大型多模态模型 (GLaMM) 的基础，这是第一个能够生成与对象分割掩模无缝集成的自然语言响应的模型。 | 2025-08-05 |
No repositories match your search
没有匹配的仓库