← Search

Haijia Gui

2 accepted papers

2026

Revisiting Long-context Modeling from Context Denoising Perspective

ICLR 2026poster

Long-context models (LCMs) have demonstrated great potential in processing long sequences, facilitating many real-world applications. The success of LCMs can be attributed to their ability to locate implicit critical information within the context for further prediction. However, recent research rev…

Cited by 0SourcecodeScholar
2025

Improving Rationality in the Reasoning Process of Language Models through Self-playing Game

ICML 2025poster

Large language models (LLMs) have demonstrated considerable reasoning abilities in various tasks such as mathematics and coding. However, recent studies indicate that even the best models lack true comprehension of their reasoning processes. In this paper, we explore how self-play can enhance the ra…

Cited by 0SourcePDFScholar