Xu Han
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.
The paper proposes a staged training procedure to improve the performance of hybrid language models by suppressing the learning of recurrence layers during training.
The paper introduces JustGoal, a goal-only baseline that outperforms open-source libraries and specialized-agent kernels in GPU kernel development.
Papers
JustGoal: With Only a Goal, the AI Baseline Is Above the Expert Kernels
Yaojian Chen, Dazhi Peng, Zhui Zhu, Leshan Li +12 more
The paper introduces JustGoal, a goal-only baseline that outperforms open-source libraries and specialized-agent kernels in GPU kernel development.