Conversational AI (CoAI) group from Tsinghua University

AI & ML interests

Dialogue Systems, Language Generation

Recent Activity

chujiezheng  authored a paper 1 day ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

yangjunxiao2021  new activity 17 days ago

thu-coai/Syncred-Bench:Add task categories, paper and code links

yangjunxiao2021  authored a paper 20 days ago

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

View all activity

Papers

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning

View all Papers

Team members 24