AI.info

Xiaojun Jia

Explore Xiaojun Jia on AI.info.

• Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge
• Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
• GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
• AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
• SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG