Shijia Kang

ProofRM: A Scalable Pipeline to Train a Generalized Math Proof Reward Model

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

Number Cookbook: Number Understanding of Language Models and How to Improve It

On the Completeness of Invariant Geometric Deep Learning Models