← authors · overview

• Autodan: Generating Stealthy Jailbreak Prompts On Aligned Large Language Models
  2023 · 698 citations
• Deepedit: Knowledge Editing As Decoding With Constraints
  2024 · 42 citations
• Rlhfpoison: Reward Poisoning Attack For Reinforcement Learning With Human Feedback In Large Language Models
  2023 · 35 citations
• mDPO: Conditional Preference Optimization for Multimodal Large Language Models
  2024 · 2 citations
• FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration
  2025
• OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas
  2025
• Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration
  2025
• False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
  2025
• Teaching Language Models To Gather Information Proactively
  2025
• RedCoder: Automated Multi-Turn Red Teaming for Code LLMs