Author

Can Peng

h-index 3 View on Semantic Scholar

We have 2 of 13 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 Aug 2026

Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation

FedRepRAG is proposed, a decentralized RAG framework that keeps raw documents at their owning clients and exchanges only compact latent representations during cross-client retrieval, and provides an effective and efficient framework for federated RAG without transferring raw retrieved content.

Can Peng, Yu Liu, Ying-Yu Yang et al. · 0 citations

Jul 2026

DECAF: De-Clustering for Adaptive Representational Unlearning

DECAF (DE-Clustering for Adaptive Forgetting), a post-hoc method that operates only on the forget set and is designed to break the cluster, is proposed, which attains performance comparable to that of unlearning methods that use the full training set, while being significantly more efficient.

Anjie Le, Can Peng, Hongcheng Guo et al. · arXiv.org · 0 citations