Zhiyong Shu — accepted AI-conference papers

2026

DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery

Qianxin Xia, Zhiyong Shu, Wenbo Jiang, Jiawei Du, Jielei Wang, Guoming Lu

ICML 2026poster

Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highly efficient learning. However, previous approaches typically adopt a single-stage distillation paradigm, which suffers from learning specific patter…

Cited by 0 Source ↗Scholar ↗

2025

BDCKD: Unlocking the Power of Brownian Distance Covariance in Knowledge Distillation

Guoming Lu, Heng Yin, Zhiyong Shu, Jielei Wang, Guangchun Luo

ICASSP 2025accepted

Knowledge distillation has been proven to be an effective method for enhancing model performance, particularly in the domain of model compression. In this study, we propose a comprehensive approach that utilizes Brownian Distance Covariance (BDC) to measure the discrepancy between the logits produce…

Cited by 0 Source ↗Scholar ↗