Xianzhi Yu

Researcher, Huawei Technologies Ltd.

Joined

May 2022

Names

Xianzhi Yu (Preferred)

Emails

****@163.com (Confirmed)

****@ncic.ac.cn (Confirmed)

****@huawei.com (Confirmed)

Personal Links

Career & Education History

Researcher

Huawei Technologies Ltd. (huawei.com)

2019 – Present

MS student

University of the Chinese Academy of Sciences (ucas.ac.cn)

2016 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Guangming Tan

2016 – 2019

Expertise

hpc

2019 – Present

Publications

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
- ACL 2026 Industry Track Oral
- Readers: Everyone
TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time Scaling
Weizhe Lin, Xing Li, Zhiyuan Yang, Xiaojin Fu, Hui-Ling Zhen, Yaoyuan Wang, Xianzhi Yu, Wulong Liu, Xiaosong Li, Mingxuan Yuan
- ICLR 2026 Poster
- Readers: Everyone
Benchmarking and Advancing Quantization-Aware Training for Reasoning Models
Keyu Lv, Manyi Zhang, Xiaobo Xia, Jingchen Ni, Shannan Yan, Xianzhi Yu, Lu Hou, Chun Yuan, Haoli Bai
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
Shengyin Sun, Yiming Li, Xing Li, Yingzhao Lian, Weizhe Lin, Hui-Ling Zhen, Zhiyuan Yang, Xianzhi Yu, Chen Chen, Mingxuan Yuan, Chen Ma
- ICLR 2026 Poster
- Readers: Everyone
BoundaryDPT: Pushing the Boundaries of Depth Pruning for Vision Transformers
Zhenfeng Su, Kang Zhao, Han Bao, Tao Yuan, Xianzhi Yu
- Submitted to ICLR 2026
- Readers: Everyone
E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models
Tao Yuan, Haoli Bai, PanYinfei, Xuyang Cao, Tianyu Zhang, Lu Hou, Ting Hu, Xianzhi Yu
- Submitted to ICLR 2026
- Readers: Everyone
FuseGPT: Prune-and-Fuse Knowledge Redistribution for Efficient Transformers
Zehua Pei, Hui-Ling Zhen, Xianzhi Yu, Sinno Jialin Pan, Mingxuan Yuan, Bei Yu
- Submitted to ICLR 2026
- Readers: Everyone
Analytical Restructuring of Feed-Forward Networks for Accelerated LLM Inference
Zehua Pei, Hui-Ling Zhen, Lancheng Zou, Xianzhi Yu, Wulong Liu, Sinno Jialin Pan, Mingxuan Yuan, Bei Yu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Behavioral Fingerprinting of Large Language Models
Zehua Pei, Hui-Ling Zhen, Ying Zhang, Zhiyuan Yang, Xing Li, Xianzhi Yu, Mingxuan Yuan, Bei Yu
- Agents4Science
- Readers: Everyone
Large Reasoning Models Know How to Think Efficiently
Zeyu XING, Xing Li, Huiling Zhen, Xianzhi Yu, Mingxuan Yuan, Sinno Jialin Pan
- ES-FoMo III
- Readers: Everyone

View all 19 publications

Co-Authors

View all 83 co-authors