Caiqi Zhang

Visual Planning: Let's Think Only with Images

Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models

Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation

When Should AI Ask: Decision-theoretic Adaptive Communication for LLM Agents

Supposedly Equivalent Facts That Aren’t? Entity Frequency in Pre-training Induces Asymmetry in LLMs