Yihong Dong

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

PSC: Efficient Grammar-Constrained Decoding via Parser Stack Classification

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs

Benchmarking Large Language Model Benchmarks: Popular Benchmarks vs. Human Perception

Improving Formal Reasoning of Transformer with State Stack

Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling

Fourier Analysis Network

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning

FAN: Fourier Analysis Networks

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code