从0到1多模态大模型 · 理论与实战学习记录 From0to1-MLLM-StudyLog 是一个个人从零自学多模态大模型（MLLM）的系统记录仓库，覆盖约 24 周的学习与实践过程。 仓库按 Week1–Week24 组织，每周包含： 精简的理论理解与知识梳理 关键论文/概念的个人笔记 对应的代码实现、实验脚本与踩坑记录 各类 mini 多模态模型的微调与实践案例 目标是形成一套“可复现的个人学习路径”，既方便自己回顾，也方便他人参考或在此基础上继续拓展。
☆190Sep 10, 2026Updated last month
Alternatives and similar repositories for From0to1-MLLM-StudyLog
Users that are interested in From0to1-MLLM-StudyLog are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 本项目提供一个从零开始构建多模态大模型（MLLM）的完整实践路径，使用纯 PyTorch 手写 Transformer、Vision Transformer 和 GPT-style LLM，并通过 Connector 融合成可“看图说话”的多模态模型。同时，项目支持基于 S…☆36May 12, 2026Updated 5 months ago
- ☆12Aug 16, 2026Updated 2 months ago
- ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3☆21Oct 5, 2026Updated 3 weeks ago
- Large scale Aerial Person detection Dataset for Search and Rescue☆21Aug 9, 2024Updated 2 years ago
- This is the public repository of AAAI 2024 paper "Is a Large Language Model a Good Annotator for Event Extraction"☆10Feb 16, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- MiniMind-V 多模态面试学习指南 - 20节课程 + 278道面试题 + STAR面试稿 + 哆啦A梦漫画☆165Apr 2, 2026Updated 6 months ago
- 丁立中的大模型算法工程作品集。聚焦 LLM / VLM 全链路的复现与优化，涵盖：① 预训练与微调（Pretrain / SFT / MoE / 多模态对齐）；② 强化学习对齐（PPO / GRPO / DAPO，含多奖励函数与 GAE）；③ 知识蒸馏（离线 KL 蒸馏、在…☆18May 26, 2026Updated 5 months ago
- LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction (ACL 2…☆15Aug 12, 2024Updated 2 years ago
- PCB model☆19Dec 19, 2018Updated 7 years ago
- ☆38Oct 20, 2023Updated 3 years ago
- 🎓从0开始训练一个大模型Minimind项目的超详细解析，包括但不限于用到的架构，算法，以及大模型面试经验☆1,827May 25, 2026Updated 5 months ago
- StrainNet is a deep neural network for measuring deformation from images☆12Aug 12, 2025Updated last year
- DeepLab v3+ model in PyTorch. Support different backbones.☆22Dec 7, 2019Updated 6 years ago
- 本赛题面向可穿戴睡眠监测场景，通过分析患者的血氧和心率信息，实现呼吸暂停和低通气异常事件的检测，帮助预警患者的健康风险。☆24Aug 21, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆10Dec 5, 2024Updated last year
- 面向长程购物 Agent 的可复现后训练☆582Oct 19, 2026Updated last week
- TailNG UI is a signal-first Angular component library with Material-like components, framework-agnostic styling, and support for Angular …☆16Oct 9, 2026Updated 3 weeks ago
- Continual Detection Transformers (ECCV'24)☆11Oct 25, 2024Updated 2 years ago
- 基于ResNet的垃圾分类智能识别系统☆12Apr 17, 2024Updated 2 years ago
- Inference SAM in C # based on OpenVINO, ONNX runtime, TensorRT☆19Jun 6, 2024Updated 2 years ago
- Official code implementation of the AAAI 2025 paper: [CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Objec…☆12Feb 10, 2025Updated last year
- Midwave Infrared Small Target Detection Dataset☆14Jun 23, 2026Updated 4 months ago
- OpenRSD: Towards Open-Prompt Object Detection in Remote Sensing☆43Aug 18, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- fish-kong/Yolov5-Instance-Seg-Tensorrt-CPP☆58Nov 8, 2022Updated 3 years ago
- Resource for cross-species primate facial analysis.☆17Mar 23, 2026Updated 7 months ago
- Official implementation for "CONVIQT: Contrastive Video Quality Estimator"☆24Jun 14, 2022Updated 4 years ago
- This project aims to replicate mainstream open-source model architectures with limited computational resources, implementing mini models …☆296Aug 24, 2026Updated 2 months ago
- ☆10Aug 8, 2024Updated 2 years ago
- A re-implementation of PFLD, https://arxiv.org/abs/1902.10859☆45Aug 27, 2019Updated 7 years ago
- [AAAI 2024] SiMA-Hand: Boosting 3D Hand-Mesh Reconstruction by Single-to-Multi-view Adaptation, Pytorch implementation.☆11Feb 6, 2024Updated 2 years ago
- A gesture recognition module trained from scratch using Pytorch, deployed with ncnn and TensorRT.☆14May 1, 2022Updated 4 years ago
- Awesome Multimodal Modeling [Covers MLLM, UMM, and NMM]☆551Oct 18, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Source code for "Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions" (ECCV 2024)☆12Sep 27, 2024Updated 2 years ago
- T-GCN交通流量动态预测，需要研究如何把流速转化为流量☆10Oct 17, 2019Updated 7 years ago
- Official code for the paper "BECAME: BayEsian Continual Learning with Adaptive Model MErging" (ICML 2025).☆12Jul 4, 2025Updated last year
- 基于YOLOv5s+CBAM注意力机制的危险驾驶行为识别系统☆12May 21, 2024Updated 2 years ago
- ☆12Jul 26, 2022Updated 4 years ago
- [CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detectio…☆773Updated this week
- algorithm-cpp projects☆81Sep 25, 2022Updated 4 years ago