Xingyu Zheng
PhD student at Beihang University, supervised by Prof. Xianglong Liu. My research focuses on making large AIGC models practical, especially through inference acceleration and model quantization for LLMs and diffusion models.
Beihang University, 2024 - now.
Low-bit LLMs, post-training quantization, and fast diffusion sampling.
Training-free diffusion acceleration and accurate LLM quantization compensation.
Publications
2026
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Xingyu Zheng, Xianglong Liu†, Yifu Ding, Weilun Feng, Junqing Lin, Jinyang Guo, Haotong Qin
This paper proposes a training-free multi-resolution strategy, MrFlow, for accelerating image generation, achieving faithful generation with up to 10x end-to-end speedup.
An Empirical Study of Qwen3 Quantization
Xingyu Zheng, Yuye Li, Haoran Chu, Yue Feng, Xudong Ma, Jie Luo, Jinyang Guo, Haotong Qin†, Michele Magno, Xianglong Liu
This paper explores Qwen3's capabilities when quantized to low bit-width, demonstrating its value in advancing future models.
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
Xingyu Zheng*, Haotong Qin*, Yuye Li, Haoran Chu, Jiakai Wang, Jinyang Guo, Michele Magno, Xianglong Liu†
GPTQModel / Github / Hugging Face / PaddlePaddle
This paper proposes FOEM, a novel PTQ method for LLM that explicitly incorporates first-order gradient terms to improve quantization error compensation.
2025
A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms
Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin, Jinyang Guo, Michele Magno, Xianglong Liu†
This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies.
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
Xingyu Zheng, Xianglong Liu†, Haotong Qin, Xudong Ma, Mingyuan Zhang, Haojie Hao, Jiakai Wang, Zixiang Zhao, Jinyang Guo, Michele Magno
This paper proposes BinaryDM, a novel accurate quantization-aware training approach to push the weights of diffusion models towards the limit of 1-bit.
2024
BiDM: Pushing the Limit of Quantization for Diffusion Models
Xingyu Zheng, Xianglong Liu†, Yichen Bian, Xudong Ma, Yulun Zhang, Jiakai Wang, Jinyang Guo, Haotong Qin
This paper proposes a novel method, namely BiDM, for fully binarizing weights and activations of DMs, pushing quantization to the 1-bit limit.
An Empirical Study of LLaMA3 Quantization: From LLMs to MLLMs
Wei Huang*, Xingyu Zheng*, Xudong Ma*, Haotong Qin†, Chengtao Lv, Hong Chen, Jie Luo, Xiaojuan Qi, Xianglong Liu, Michele Magno
This paper explores LLaMA3's capabilities when quantized to low bit-width, demonstrating its value in advancing future models.
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
Haotong Qin*, Xudong Ma*, Xingyu Zheng, Xiaoyang Li, Yang Zhang, Shouda Liu, Jie Luo, Xianglong Liu†, Michele Magno
This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention.
2023
Disolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks
Jun Guo, Xingyu Zheng, Aishan Liu†, Siyuan Liang, Yisong Xiao, Yichao Wu, Xianglong Liu
This paper proposes Isolation and Induction (InI), a novel and effective training framework for model stealing defenses.
Book
Generalizing from Limited Resources in the Open World
Jinyang Guo, Yuqing Ma, Yifu Ding, Ruihao Gong, Xingyu Zheng, Changyi He, Yantao Lu, Xianglong Liu
This book presents the proceedings from the Second International Workshop GLOW 2024, held in conjunction with IJCAI 2024 in Jeju Island, South Korea.
Awards
- 2026, ByteDance Global Frontier Tech Recruitment Program (字节跳动前沿技术领域人才计划; formerly ByteDance Soaring Star Talent Program, 筋斗云人才计划).
- 2025, Tencent Rhino-Bird Elite Training Program (腾讯犀牛鸟精英人才计划).
- 2024, Honor Student of Beihang University.
- 2024, Excellent Undergraduate Graduation Thesis.
- 2024, Excellent Graduate of Beihang University.
- 2022, Lanqiao Cup, National First Prize.
Background
- 2024 - now, PhD student, Beihang University.
- 2020 - 2024, Undergraduate student, Beihang University.
Activities
- 2025.08, Organizer, Practical-DL 2025.
- 2024.08, Publicity Chair, GLOW 2024.
Internships
- 2026.07 - now, ByteDance, Beijing.
- 2025.08 - 2026.07, Tencent, Shanghai.