Author

Jinshan Zeng

h-index 2 View on Semantic Scholar

We have 2 of 7 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.

#machine learning Preprint Sep 2026

Predicting Block-Coordinate Performance via Cross-Curvature

Simultaneous and sequential block updates are two basic optimization strategies used across machine learning, such as neural-network training, federated learning, and low-rank adaptation. Choosing between them is difficult because their relative advantage depends on both the objective geometry and the number of iterati...

Sheng-Kun Zhu, Jin-Shan Zeng, Zhi Kou et al. · 0 citations

Jul 2026

Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients

FedSLM, a parameter-centric framework for federated fine-tuning with heterogeneous compressed clients, is proposed, which provides theoretical guarantees for adapter-level aggregation, subspace-alignment bounds for cross-group fusion, and a characterization of how the confidence loss mitigates weak-supervision noise.

Shengkun Zhu, Jinshan Zeng, Zhihua Allen-Zhao et al. · arXiv.org · 0 citations