Author

Zhenglun Kong

Harvard University

h-index 19 Homepage View on Semantic Scholar

We have 2 of 63 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models

UniMoMo, a post-training compression framework formulated as a constrained graph coarsening problem, is introduced, and a layer-adaptive protection mechanism that restricts the merging of high-traffic experts based on their routing exposure is introduced.

Lei Xin, Bin Gu, Peize Li et al. · 3 citations

FedLDCS: Adaptive Divergence-Based Client Selection for Federated Learning

This paper proposes a novel Largest Distance Client Selection (LDCS) method that prioritizes clients based on the divergence of their local models from the global model, as quantified by the Frobenius norm, thereby improving training efficiency and model performance while overcoming the limitations of existing random o...

Shiyue Hou, Zhenglun Kong · 2 citations