- 👋 Hi, I’m @HeartyHaven,
- 👀 I’m interested in (Multi-modal) Large Language Models & eXplainable AI.
- 🌱 I’m currently at IDC-Lab of Hust and VLAA Lab of UCSC.
- 💞️ I’m looking to collaborate on any open-source LLM,MLLM and XAI project.
- 📫 Contact me at [email protected]
[1] Attacking for Inspection and Instruction: Recognizing Trivial Patterns as Trivial in Self-Rationalization
Wei Liu, Zhiying Deng, Jun Wang, Haozhao Wang, Ruixuan Li, Lang Gao, Zhongyu Niu
Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Lang Gao