LlamaIndex is the leading framework for building LLM-powered agents over your data.

Generalizable Deepfake Detection via Pattern-Aware Reasoning.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

[CVPR 2025] FineVQ: Fine-Grained User Generated Content Video Quality Assessment

The offical implementation of 'FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant'

[CVPR2025] Official implementation of RAM

C2P-CLIP-DeepfakeDetection

Official implementation of "Why are Visually-Grounded Language Models Bad at Image Classification?" (NeurIPS 2024)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

ACL 2024 Findings: LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation

ACL 2024 Findings: Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge

⛽️「算法通关手册」：从零开始的「算法与数据结构」学习教程，200 道「算法面试热门题目」，1000+ 道「LeetCode 题目解析」，持续更新中！

Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 50+ HF models, 20+ benchmarks

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

Implementation of training LLava with LLama3, supporting pre-training and finetuning

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

[CVPR 2024] The official repo for Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection

Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions (NeurIPS 2024)

Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"

[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"