Mingjie Li
- Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
- CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
- CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding
- Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms