Publications

• Deterministic Differentiable Structured Pruning for Large Language Models [arXiv] [Project page]

  Weiyu Huang, Pengle Zhang, Xiaolu Zhang, Jun Zhou, Jun Zhu, Jianfei Chen

  International Conference on Machine Learning (ICML), 2026

• Pruning large language models with semi-structural adaptive sparse training [arXiv] [PDF] [Project page]

  Weiyu Huang, Yuezhou Hu, Guohao Jian, Jun Zhu, Jianfei Chen

  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025

• Accelerating Transformer Pre-training with 2:4 Sparsity [arXiv] [OpenReview] [PDF] [Project page]

  Yuezhou Hu, Kang Zhao, Weiyu Huang, Jianfei Chen, Jun Zhu

  International Conference on Machine Learning (ICML), 2024

Preprints

• CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models [arXiv]

  Weiyu Huang, Yuezhou Hu, Jun Zhu, Jianfei Chen

  In submission to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)