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

Xinyuan Qian

1 indexed paper

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

Publications per year

1
26

Top categories

Crypto×1

Frequent co-authors

Zihan Wang1×
Rui Zhang1×
Qingchuan Zhao1×
Hongwei Li1×
Guowen Xu1×

Research Timeline

2026
FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation

This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.

Highlighted terms show continued research focus across papers

Papers

cs.CREmpiricalRecentSep 25, 2026

FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation

Zihan Wang, Rui Zhang, Xinyuan Qian, Qingchuan Zhao +2 more

This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.

View →