Skip to main content

🏢 Ant Group

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
·3986 words·19 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 Ant Group
AUTO-RT automates LLM vulnerability discovery by using reinforcement learning to optimize complex attack strategies, achieving faster detection and higher success rates than existing methods.
Mimir: Improving Video Diffusion Models for Precise Text Understanding
·3398 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Video Understanding 🏢 Ant Group
Mimir: A novel framework harmonizes LLMs and video diffusion models for precise text understanding in video generation, producing high-quality videos with superior text comprehension.