Home
Publication
Miao's Group

SELECTED PUBLICATIONS

Codes for our publications can be found in Our Group Github.

  • Jiaqi Zhao, Miao Zhang#, Ming Wang, Yuzhang Shang, Kaihao Zhang, Weili Guan, Yaowei Wang, Min Zhang, PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models. (ACL 2025, CCF A)

  • Li Wang*, Chao Zeng*, Miao Zhang#, Jianlong Wu, Liqiang Nie, Domain Aware Post Training Quantization for Vision Transformers in Deployment. (Pattern Recognition 2025, CCF B)

  • Hongyi Wan*, Shiyuan Ren*, Wei Huang#, Miao Zhang#, Xiang Deng, Yixin Bao, Liqiang Nie，Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters. (ICML 2025, CCF A)

  • Lexiao Zou, Gongwei Chen, Yanda Chen,Miao Zhang#, Enhancing Diffusion-based Dataset Distillation via Adversary-Guided Curriculum Sampling. (ICME 2025, CCF B)

  • Kai Zhao*, Zhihao Zhuang*, Miao Zhang#, Chenjuan Guo, Yang Shu, Bin Yang, Enhancing Diversity for Data-free Quantization. (CVPR 2025, CCF A).

  • Yanda Chen*, Gongwei Chen*, Miao Zhang#, Weili Guan, Liqiang Nie, Curriculum Coarse-to-Fine Selection for High-IPC Dataset Distillation. (Accepted by CVPR 2025).

  • Qianlong Xiang, Miao Zhang#, Yuzhang Shang, Jianlong Wu, Yan Yan, Liqiang Nie#, DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture. (CVPR 2025, CCF A).

  • Jiarui Jiang, Wei Huang, Miao Zhang#, Taiji Suzuki, Liqiang Nie, Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization. (Accepted by NeurIPS 2024). [ Paper and Code]

  • Hongrong Cheng, Miao Zhang#, Javen Qinfeng Shi, A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations. (Accepted by IEEE TPAMI 2024). [ Paper and Code]

  • Hongrong Cheng, Miao Zhang#, Javen Qinfeng Shi, Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes For Pruning Is Possible Without Retraining. (Accepted by IEEE TPAMI 2024). [ Paper and Code]

  • Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie, LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models. (ACL 2024, Main, Oral, CCF A). [ Paper and Code]

  • David Campos, Bin Yang, Tung Kieu, Miao Zhang, Chenjuan Guo, Christian S. Jensen, QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models. (VLDB 2024, CCF A). [ Paper and Code]

  • Xin Zheng, Miao Zhang, Chunyang Chen, Quoc Viet Hung Nguyen, Xingquan Zhu, Shirui Pan, Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data. (Spotlight, NeurIPS 2023, CCF A). [ Paper and Code]

  • Xin Zheng, Miao Zhang, Chunyang Chen, Soheila Molaei, Chuan Zhou, Shirui Pan, GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels. (NeurIPS 2023, CCF A). [ Paper and Code]

  • David Campos, Miao Zhang, Bin Yang, Tung Kieu, Chenjuan Guo, and Christian S. Jensen, LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation. (SIGMOD 2023, CCF A). [ Paper and Code]

  • Xin Zheng, Miao Zhang, Chunyang Chen, Qin Zhang, Chuan Zhou, Shirui Pan, Auto-HeG: Automated Graph Neural Network on Heterophilic. (WWW 2023, CCF A). [ Paper and Code]

  • Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Bin Yang, Christian Jensen, Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting. (SIGMOD 2023, CCF A). [ Paper and Code]

  • Wei Huang, Yayong Li, Weitao Du, Richard Xu, Jie Yin, Ling Chen, Miao Zhang, Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective. (ICLR 2022, ). [ Paper and Code]

  • Miao Zhang, Wei Huang, Bin Yang, Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations. (Accepted by NeurIPS2022, CCF A). [ Paper and Code]

  • Miao Zhang, Li Wang, David Gonzalo Chaves Campos, Wei Huang, Chenjuan Guo, Bin Yang, Weighted Mutual Learning with Diversity-Driven Model Compression. (Accepted by NeurIPS2022, CCF A). [ Paper and Code]

  • Miao Zhang, Shirui Pan, Xiaojun Chang, Steven Su, Jilin Hu, Gholamreza Haffari, Bin Yang, Differentiable Neural Architecture Search via Bayesian Learning Rule. (Accepted by CVPR2022 , CCF A). [ Paper and Code]

  • Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Ehsan Abbasnejad, Reza Haffari, iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients. (Accepted by ICML2021, CCF A). [ Paper and Code]

  • Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Zongyuan Ge, and Steven Su, One-Shot Neural Architecture Search: Maximising Diversity to Overcome Catastrophic Forgetting. (Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF A, JCR Q1, Top Journal, IF: 17.8) . [ Paper and Code]

  • Miao Zhang, Huiqi Li, Shirui Pan, Juan Lyu, Steve Ling, Steven Su, Hyperparameter Optimization with Non-stationary Kernel for CNN based Lung Nodule Classification. (Accepted by IEEE Transaction on Evolutionary Computing (TEvC), JCR Q1, Top Journal, IF: 11.17) . [ Paper and Code]

  • Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Zongyuan Ge, Steven Su, Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement. (Accepted by Annual Conference on Neural Information Processing Systems(NeurIPS2020), CCF A.). [ Paper and Code]

  • Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Steven Su, Overcoming Multi-Model Forgetting in One-Shot NAS with Diversity Maximization. (Accepted by CVPR2020, CCF A). [ Paper and Code]

  • Miao Zhang, Huiqi Li, Shirui Pan, Taoping Liu, Steven Su, One-Shot Neural Architecture Search via Novelty Driven Sampling. (Accepted by IJCAI2020, CCF A). [ Paper and Code]

  • Miao Zhang, Huiqi Li, Steven Su, High Dimensional Bayesian Optimization via Supervised Dimension Reduction. (Accepted by IJCAI2019, CCF A.). [ Paper and Code]




    		•