Stars
[ACL‘25] The official implementation of our ACL 2025 Findings paper "Chain of Attack: Hide Your Intention through Multi-Turn Interrogation"
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
阅读3服务器版，桌面端，iOS可用。后端 Kotlin + Spring Boot + Vert.x + Coroutine ；前端 Vue.js + Element。麻烦点点star，关注一下公众号【假装大佬】❗️
Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"
Making large AI models cheaper, faster and more accessible
Acceptance rates for the major AI conferences
Sky-T1: Train your own O1 preview model within $450
OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用. Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and depl…
[ArXiv 2024] Denial-of-Service Poisoning Attacks on Large Language Models
[ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
Xiaomi Home Integration for Home Assistant
The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models
Research into how collaborative language models can result in more robust moral alignment.
[ICML 2024] Official code repository for 3D embodied generalist agent LEO
[ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
Open-Sora: Democratizing Efficient Video Production for All
Enhancing LLM Jailbreak: A Dual-Strategy Approach of Token Suppression and Induction
Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens
FauxPilot - an open-source alternative to GitHub Copilot server
✨✨Latest Advances on Multimodal Large Language Models
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
Must-read Papers on Textual Adversarial Attack and Defense