A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

Parsing-free RAG supported by VLMs

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

"RAG-Anything: All-in-One RAG Framework"

Implement of RoFLIP

😼 优雅地使用基于 clash/mihomo 的代理环境

LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

[Paper][AAAI2024]Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations

This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023).

Repository for the paper: dense and aligned captions (dac) promote compositional reasoning in vl models

[ACM MM25] Official Pytorch implementation of [Decoupled Global-Local Alignment for Improving Compositional Understanding]

[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

Collection of Composed Image Retrieval (CIR) papers.

Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models

[CVPR 2026] OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

Hyperbolic Safety-Aware Vision-Language Models. CVPR 2025

Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.

Toolkit for Elevater Benchmark

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

[WACV 2024] Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining, WACV 2024

An open source implementation of CLIP.