Jiatong Li

Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models

am-ELO: A Stable Framework for Arena-based LLM Evaluation

Visual Instruction Bottleneck Tuning

LINA: An LLM-driven Neuro-Symbolic Approach for Faithful Logical Reasoning