Dawei Yang

Researcher, Houmo

Joined

November 2022

Names

Dawei Yang (Preferred)

Emails

****@qq.com (Confirmed)

,

****@houmo.ai (Confirmed)

Personal Links

Career & Education History

Researcher

Houmo (houmo.ai)

2021 – Present

PhD student

Fudan University (fudan.edu.cn)

2018 – 2022

MS student

University of York (york.ac.uk)

2013 – 2015

Advisors, Relations & Conflicts

PhD Advisor

wenqiang zhang

2010 – Present

Expertise

Deep Learning

2015 – Present

Publications

PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling
Yuxuan Yue, Zukang Xu, Zhihang Yuan, Dawei Yang, Jianlong Wu, Liqiang Nie
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
QuantGen: Parameter Generation for Controllable Model Quantization
Mengxuan Wu, Xinhao Zhong, Penghao Wang, Ziheng Qin, Jimeng Zhang, Wangbo Zhao, Mingjia Shi, Zekai Li, Hao Ye, Panpan Zhang, Shuo Wang, Yang You, Kai Wang, Dawei Yang
- Submitted to ICLR 2026
- Readers: Everyone
DLLMQuant: A Post-Training Quantization Framework Tailored for Diffusion-Based Large Language Models
Chen Xu, Dawei Yang
- Submitted to ICLR 2026
- Readers: Everyone
CMQuant: A Quantization-Aware Parameter-Efficient Fine-Tuning Framework for 4-Bit Consistency Models
Chen Xu, Dawei Yang, Mingjia Shi, Xing Hu, Jiangyong Yu
- Submitted to ICLR 2026
- Readers: Everyone
NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
Jiangyong Yu, Xiaomeng Han, Xing Hu, Chen Xu, Zhe jiang, Dawei Yang
- ICLR 2026 Poster
- Readers: Everyone
Towards W2A4 LLM Inference: Hybrid SQ-VQ Framework with Adaptive Error Compensation
Yuan Cheng, Xing Hu, Zukang Xu, Hui Wang, Xiaomeng Han, Zhe jiang, Dawei Yang
- Submitted to ICLR 2026
- Readers: Everyone
SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
Xing Hu, Dawei Yang, Yuan Cheng, Zhixuan Chen, Zukang Xu
- ICLR 2026 Poster
- Readers: Everyone
BiMoE：Pushing the Limit of Post-Training Quantization for MoE-based LLMs
Zhixiong Zhao, Zukang Xu, Zhixuan Chen, Fangxin Liu, Li Jiang, Dawei Yang
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
MSAVQ: Multi-dimensional Sensitivity-Aware Vector Quantization for Ultra-Low-Bit Vision-Language Models
Wang Zhong, Zukang Xu, Xing Hu, Chen Hao, Dawei Yang
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, Dawei Yang
- ICLR 2026 Poster
- Readers: Everyone

View all 19 publications

Co-Authors

View all 47 co-authors