All Stories

  1. Self-Speculative Decoding for On-device MoE Acceleration

    Article • April 2026, ACM (Association for Computing Machinery)

    Peirong Zheng

  2. Poster: Coda: Context-aware Acceleration for Distributed LLM Decoding in Edge

    Article • November 2025, ACM (Association for Computing Machinery)

    Peirong Zheng

  3. FedNLR: Federated Learning with Neuron-wise Learning Rates

    Article • August 2024, ACM (Association for Computing Machinery)

    XINGSHUO HAN, Peirong Zheng