Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiongcai Luo

Xiongcai Luo

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

AI×1

Frequent co-authors

Jian Yao1×
Ran Cheng1×
Kay Chen Tan1×

Research Timeline

2026
SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning

The paper proposes SLAT, a segment-level adaptive trimming framework, which efficiently reduces redundant reasoning in large language model CoT outputs by selectively suppressing segments with low marginal utility.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 29, 2026

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning

Jian Yao, Xiongcai Luo, Ran Cheng, Kay Chen Tan

The paper proposes SLAT, a segment-level adaptive trimming framework, which efficiently reduces redundant reasoning in large language model CoT outputs by selectively suppressing segments with low mar…

View →