New generation of CLIP with fine grained discrimination capability, ICML2025

An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.

An Arena-style Automated Evaluation Benchmark for Detailed Captioning

MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Collection of AWESOME vision-language models for vision tasks

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Implementation for Describe Anything: Detailed Localized Image and Video Captioning

RethinkFun大模型个人学习笔记

A powerful tool for creating fine-tuning datasets for LLM

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！

LAVIS - A One-stop Library for Language-Vision Intelligence

「大模型」3小时从0训练27M参数的视觉多模态VLM，个人显卡即可推理训练！

Efficient and lightweight Vision-Language model for Visual Question Answering in autonomous driving scenarios. The approach replaces images in BLIP's architecture with spatio-temporal BEV feature maps

LLM Course；

[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

A comprehensive collection of open world papers from top tier conferences and journals

A curated list of resources dedicated to table recognition

This is the pytorch implementation of 3DAL proposed by Qi et. al, "Offboard 3D Object Detection from Point Cloud Sequences", CVPR 2021.

DetZero

A curated, but incomplete, list of data-centric AI resources.

[CVPR'23] Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation

Semi-supervised learning for object detection

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)