publications

2026

1. arxiv

   EVAR: Edge Visual Autoregressive Models via Principled Pruning

   Zefang Wang, Yanyu Li, Mingluo Su, Simin Xu, Guanzhong Tian, and Huan Wang

   In arxiv, 2026

   Abs Code Website

   We propose a principled OBS-based structured pruning method for visual autoregressive models. Our approach introduces a progressive scale-aware distillation method to address gradient imbalance during next-scale autoregressive fine-tuning. The method achieves 1.8× speedup with only 10% quality loss on single-image generation scenarios on edge devices.

2. arxiv

   OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

   Junhan Zhu, Hesong Wang, Mingluo Su, Zefang Wang, and Huan Wang

   In arxiv, 2026

   Abs arXiv Website

   We propose an OBS-based training-free multi-granularity pruning method adapted for diffusion models. Our approach introduces a timestep-aware Hessian construction with logarithmically decreasing weights to mitigate error accumulation and optimize group pruning efficiency. The method achieves accelerated inference while minimizing visual quality degradation.

2024

1. TNNLS

   An Effective Information Theoretic Framework for Channel Pruning

   Yihao Chen and Zefang Wang

   IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024

   TNNLS Abs arXiv

   IEEE TNNLS

   We use a fusion function combining entropy and rank to obtain the information concentration of each layer, which serves as the pruning rate. We propose an explainable Shapley value-based contribution evaluation method as the intra-layer pruning criterion. The method achieves good results in image classification and object detection, demonstrating its effectiveness.

2. Network Binarization via Contrastive Deep Supervision

   Zefang Wang and others

   In NCAA Conference, 2024

   Abs

   We propose BNN-CDS, a binary network optimization method based on the fusion of deep supervision and contrastive learning. We introduce a scaling factor strategy for BNN-CDS suitable for binary networks.