Stars
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation.
The evaluation code for A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
A list of backdoor learning resources
This is the code for the FSE26 paper: Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking, the research paper can be referred at https://arxiv.org/pdf/2512.21236
[NDSS 2026] Official repo for Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
从无名小卒到大模型（LLM）大英雄~ 欢迎关注后续！！！
Official Implementation for "Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning" (NeurIPS 2025).
Official implementation for "DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling" (IEEE S&P 2026)
A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
A PyTorch native platform for training generative AI models
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
A collection of resources that investigate social agents.
🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测。支持 Docker 一键部署，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。⭐
A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.
✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images
A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.
基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
Awesome Unified Multimodal Models
An active model protection strategy - Lock your model
[ArXiv 2025] Imperceptible Jailbreaking against Large Language Models