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

Shuai Yuan

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Info Theory×1NLP×1

Frequent co-authors

Zhicheng Liu1×
Liuquan Yao1×
Zhongjun Yang1×
Guiying Yan1×
Zhiming Ma1×
Li Chen1×

Research Timeline

2026
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

The paper proposes Speculative Pipeline Decoding (SPD), a novel framework that uses pipeline parallelism to accelerate LLM inference by processing multiple tokens in parallel, achieving higher speedup and zero latency bubbles.

Perturbation Power Selection for First-Error Delay Maximization in Enhanced SC Decoding

This paper analyzes the non-monotonic relationship between perturbation power and the probability of delaying the first error position in finite-length PE-SC decoding. It proposes an efficient perturbation power selection algorithm to maximize the delay probability.

Highlighted terms show continued research focus across papers

Papers

cs.ITTheoreticalRecentJul 17, 2026

Perturbation Power Selection for First-Error Delay Maximization in Enhanced SC Decoding

Zhicheng Liu, Liuquan Yao, Shuai Yuan, Zhongjun Yang +4 more

This paper analyzes the non-monotonic relationship between perturbation power and the probability of delaying the first error position in finite-length PE-SC decoding. It proposes an efficient perturb…

View →
cs.CLRecentMay 29, 2026

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

Yijiong Yu, Huazheng Wang, Shuai Yuan, Ruilong Ren +1 more

The paper proposes Speculative Pipeline Decoding (SPD), a novel framework that uses pipeline parallelism to accelerate LLM inference by processing multiple tokens in parallel, achieving higher speedup…

View →