← authors · overview

• Survey Of Vulnerabilities In Large Language Models Revealed By Adversarial Attacks
  2023 · 256 citations
• Pyramidkv: Dynamic KV Cache Compression Based On Pyramidal Information Funneling
  2024 · 236 citations
• Illusionvqa: A Challenging Optical Illusion Dataset For Vision Language Models
  2024 · 30 citations
• Cross-modal Safety Alignment: Is Textual Unlearning All You Need?
  2024 · 25 citations
• Safety Alignment In NLP Tasks: Weakly Aligned Summarization As An In-context Attack
  2023 · 11 citations