Publications

• Xuewen Liu, Zhikai Li✉, Minhao Jiang, Mengjuan Chen, Jianquan Li, and Qingyi Gu. DilateQuant: Accurate and efficient quantization-aware training for diffusion models via weight dilation. ACM International Conference on Multimedia (ACM MM), 2025.
• Pan Du, Wangbo Zhao, Xinai Lu, Nian Liu, Zhikai Li, Chaoyu Gong, Suyun Zhao, Hong Chen, Cuiping Li, Kai Wang, Yang You. Unsupervised learning for class distribution mismatch. International Conference on Machine Learning (ICML), 2025.
• Zhikai Li, Mengjuan Chen, Junrui Xiao, and Qingyi Gu. CoLeQ: Improving data-free quantization via contrastive learning. IEEE Transactions on Multimedia (TMM), 2025.
• Zhikai Li, Xuewen Liu, Dongrong Fu, Jianquan Li, Qingyi Gu, Kurt Keutzer, and Zhen Dong. K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
• Xuewen Liu, Zhikai Li✉, and Qingyi Gu. CacheQuant: Comprehensively accelerated diffusion models. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
• Wangbo Zhao, Yizeng Han, Jiasheng Tang, Zhikai Li, Yibing Song, Kai Wang, Zhangyang Wang, Yang You. A stitch in time saves nine: Small VLM is a precise guidance for accelerating large VLMs. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
• Zhikai Li, Mengjuan Chen, Junrui Xiao, and Qingyi Gu. PSAQ-ViT V2: Towards accurate and general data-free quantization for vision transformers. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024.
• Zhikai Li, Xianlei Long, Junrui Xiao, and Qingyi Gu. HTQ: Exploring the high-dimensional trade-Off of mixed-precision quantization. Pattern Recognition (PR), 2024.
• Zhihang Yuan, Yuzhang Shang, Yang Zhou, Zhen Dong, Zhe Zhou, Chenhao Xue, Bingzhe Wu, Zhikai Li, Qingyi Gu, Yong Jae Lee, Yan Yan, Beidi Chen, Guangyu Sun, and Kurt Keutzer. Llm inference unveiled: Survey and roofline model insights. arXiv preprint arXiv:2402.16363, 2024.
• Junrui Xiao, Zhikai Li, Lianwei Yang, and Qingyi Gu. Binaryvit: Towards efficient and accurate binary vision transformers. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.
• Zhikai Li and Qingyi Gu. I-ViT: Integer-only quantization for efficient vision transformer inference. International Conference on Computer Vision (ICCV), 2023.
• Zhikai Li, Junrui Xiao, Lianwei Yang, and Qingyi Gu. RepQ-ViT: Scale reparameterization for post-training quantization of vision transformers. International Conference on Computer Vision (ICCV), 2023.
• Junrui Xiao, Zhikai Li, Lianwei Yang, and Qingyi Gu. Patch-wise mixed-precision quantization of vision transformer. International Joint Conference on Neural Networks (IJCNN), 2023.
• Junrui Xiao, He Jiang, Zhikai Li, and Qingyi Gu. DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection. IET Image Processing, 2023.
• Zhikai Li, Liping Ma, Mengjuan Chen, Junrui Xiao, and Qingyi Gu. Patch similarity aware data-free quantization for vision transformers. European conference on computer vision (ECCV), 2022.
• Zhikai Li, Liping Ma, Xianlei Long, Junrui Xiao, and Qingyi Gu. Dual discriminator adversarial framework for data-free quantization. Neurocomputing, 2022.
• Xianlei Long, Mengjuan Chen, Zhikai Li, and Qingyi Gu. Region probability map-guided fast wide-area multiobject detection. IEEE Transactions on Instrumentation and Measurement (TIM), 2022.
• Xianlei Long, Liping Ma, He Jiang, Zhikai Li, Yunze Chen, and Qingyi Gu. Mechanical particle filter-based active vision system for fast wide-area multiobject detection. IEEE Transactions on Instrumentation and Measurement (TIM), 2022
• Junrui Xiao, He Jiang, Zhikai Li, and Qingyi Gu. Rethinking prediction alignment in one-stage object detection. Neurocomputing, 2022.
• Zhikai Li, Liping Ma, Xianlei Long, Yunze Chen, Haitao Deng, Fengxia Yan, and Qingyi Gu. Hardware-oriented algorithm for high-speed laser centerline extraction based on Hessian matrix. IEEE Transactions on Instrumentation and Measurement (TIM), 2021.