Author

Wei Ren

h-index 2 View on Semantic Scholar

We have 1 of 5 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.

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