Profile image

Zhiteng Li

I am a second-year master student at the Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University (SJTU), advised by Prof. Yulun Zhang and Prof. Linghe Kong. Previously, I received my B.E. degree from SJTU in 2023.

My research interests lie in LLM/VLM/DiT model compression and acceleration, including techniques such as binarization and post-training quantization. Additionally, I focus on synthetic data augmentation and AI-generated content (AIGC), encompassing text-to-image and text-to-video generative models.

I interned at Amazon ASAIL, Sony AI, Xiaohongshu, and Bytedance Seed-LLM.

News

May 01, 2025 1 paper accepted to ICML 2025.
Apr 22, 2025 I will join ByteDance Seed-LLM Team as a research intern.
Jan 23, 2025 Our papers ARB-LLM and GenDataAgent are accepted by ICLR 2025.

Publications

* Corresponding Author(s)

  1. ICLR
    ARB-LLM: Alternating Refined Binarizations for Large Language Models
    Zhiteng Li, Xianglong Yan, Tianao Zhang, Haotong Qin, Dong Xie, Jiang Tian, Zhongchao Shi, Linghe Kong*, Yulun Zhang*, and Xiaokang Yang
    In International Conference on Learning Representations, 2025
    PDF Code
  2. ICLR
    GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data
    Zhiteng Li, Lele Chen, Jerone Andrews*, Yunhao Ba, Yulun Zhang, and Alice Xiang
    In International Conference on Learning Representations, 2025
    PDF Code
  3. ICML
    BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
    Kai Liu, Kaicheng Yang, Zheng Chen, Zhiteng Li, Yong Guo, Wenbo Li, Linghe Kong*, and Yulun Zhang*
    In International Conference on Machine Learning, 2025
    PDF Code
  4. arXiv
    DVD-Quant: Data-free Video Diffusion Transformers Quantization
    Zhiteng Li, Hanxuan Li, Junyi Wu, Kai Liu, Linghe Kong, Guihai Chen, Yulun Zhang, and Xiaokang Yang
    arXiv preprint arXiv:2505.18663, 2025
    PDF Code
  5. arXiv
    AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
    Zhiteng Li, Mingyuan Xia, Jingyuan Zhang, Zheng Hui, Linghe Kong*, Yulun Zhang*, and Xiaokang Yang
    arXiv preprint arXiv:2502.01403, 2025
    PDF Code
  6. arXiv
    BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
    Zhiteng Li, Yulun Zhang*, Jing Lin, Haotong Qin, Jinjin Gu, Xin Yuan, Linghe Kong*, and Xiaokang Yang
    arXiv preprint arXiv:2311.14323, 2025
    PDF Code
  7. arXiv
    ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration
    Xianglong Yan, Zhiteng Li, Tianao Zhang, Linghe Kong, Yulun Zhang, and Xiaokang Yang
    arXiv preprint arXiv:2505.24357, 2025
    PDF Code
  8. arXiv
    QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation
    Junyi Wu, Zhiteng Li, Zheng Hui, Yulun Zhang*, Linghe Kong, and Xiaokang Yang
    arXiv preprint arXiv:2503.06545, 2025
    PDF Code
  9. arXiv
    Progressive Binarization with Semi-Structured Pruning for LLMs
    Xianglong Yan, Tianao Zhang, Zhiteng Li, and Yulun Zhang*
    arXiv preprint arXiv:2502.01705, 2025
    PDF Code
  10. arXiv
    CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
    Kai Liu, Dehui Wang, Zhiteng Li, Zheng Chen, Yong Guo, Wenbo Li, Linghe Kong*, and Yulun Zhang*
    arXiv preprint arXiv:2502.15478, 2025
    PDF Code
  11. arXiv
    Low-bit Model Quantization for Deep Neural Networks: A Survey
    Kai Liu, Qian Zheng, Kaiwen Tao, Zhiteng Li, Haotong Qin, Wenbo Li, Yong Guo, Xianglong Liu, Linghe Kong, Guihai Chen, and  others
    arXiv preprint arXiv:2505.05530, 2025
    PDF Code