Author

Yunsheng Ni

Observed name: Ni, Yunsheng

Institution: Huawei Technologies (China)

Observed institution: Huawei Technologies (China)

OpenAlex ID: A5113207970

Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting

2024 · Fangcheng Liu, Yehui Tang, et al. · neural information processing systems · 5

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

2025 · Yunsheng Ni, Chuanjian Liu, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 1

PDF

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

2024 · Liu, Fangcheng, Tang, Yehui, et al. · arXiv (Cornell University) · 1

PDF

PanGu-$π$ Pro:Rethinking Optimization and Architecture for Tiny Language Models

2024 · Tang, Yehui, Han, Kai, et al. · arXiv (Cornell University) · 1

PDF

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

2024 · Ni, Yunsheng, Liu, Chuanjian, et al. · arXiv (Cornell University)

PDF

Works count: 7

Citation count: 8

H-index: 1

I10-index: