LAUNCH Lab

AI & ML interests

Factuality, reasoning, alignment, LLM applications

Recent Activity

mkhalifa  submitted a paper about 4 hours ago

Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation

xinliucs  authored a paper about 1 month ago

Answer Convergence as a Signal for Early Stopping in Reasoning

xinliucs  published a Space about 1 month ago

launch/reasoning_earlystop

View all activity

Papers

Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation

View all Papers

Team members 16