Profile image

Zhixiong Zhao

I am a first-year Ph.D. student at the School of Integrated Circuits, Peking University, advised by Prof. Guangyu Sun and Prof. Lifeng Liu. I am also a research intern at HOUMO.AI, mentored by Dr. Dawei Yang.

My research interests lie in Efficient AI for edge computing, with a particular focus on model compression, efficient inference, and hardware-software co-design. I am always open to academic exchanges and interdisciplinary collaborations. Please feel free to reach out if you would like to discuss research or potential collaborations!

News

Sep 01, 2026 I joined the School of Integrated Circuits, Peking University to pursue my Ph.D. degree. 🚀🚀🚀
Aug 21, 2026 Our paper All for 1-Bit (Main Conference) is accepted by EMNLP 2026. 🎉🎉🎉
Jul 30, 2026 I graduated with a Master’s degree from the School of Electrical and Electronic Engineering (EEE), Nanyang Technological University (NTU), Singapore. 🎓🎓🎓
May 01, 2026 Our paper TWLA is accepted by ICML 2026. 🎉🎉🎉
Apr 08, 2026 Our paper BWLA (Main Conference) is accepted by ACL 2026. 🎉🎉🎉
Jan 26, 2026 Our paper KBVQ-MoE is accepted by ICLR 2026. 🎉🎉🎉
Nov 08, 2025 Our paper SpecQuant is accepted by AAAI 2026. 🎉🎉🎉
Jul 02, 2025 Our paper QUARK is accepted by ICCAD 2025. 🎉🎉🎉
May 27, 2025 I joined the HOUMO.AI as a research intern. 🚀🚀🚀

Publications

† Equal Contribution, * Corresponding Author(s)


  1. All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs
    Zhixiong Zhao† , Zukang Xu† , Guangyu Sun , Lifeng Liu* , and Dawei Yang*
    In Conference on Empirical Methods in Natural Language Processing, 2026 (Top Conf. in NLP) CCF-B
  2. TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
    Zhixiong Zhao† , Zukang Xu† , Zhixuan Chen , Xing Hu , Zhe Jiang , and Dawei Yang*
    In International Conference on Machine Learning, 2026 (Top Conf. in ML) CCF-A
  3. BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs
    Zhixiong Zhao† , Zukang Xu† , and Dawei Yang*
    In Annual Meeting of the Association for Computational Linguistics, 2026 (Top Conf. in NLP) CCF-A
  4. KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
    Zukang Xu† , Zhixiong Zhao† , Xing Hu , Zhixuan Chen , and Dawei Yang*
    In International Conference on Learning Representations, 2026 (Top Conf. in ML) CCF-A
  5. SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
    Zhixiong Zhao† , Fangxin Liu† , Junjie Wang , Chenyang Guan , Zongwu Wang , Li Jiang , and Haibing Guan*
    In Association for the Advancement of Artificial Intelligence, 2026 (Top Conf. in AI) CCF-A
  6. QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations
    Zhixiong Zhao† , Haomin Li† , Fangxin Liu , Yuncheng Lu , Zongwu Wang , Tao Yang , Li Jiang , and Haibing Guan*
    In International Conference on Computer-Aided Design, 2025 (Top Conf. in EDA) CCF-B