Xun Wu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
BITEMBED presents a low-bit framework for efficient LLM-based text embedding that balances encoding efficiency and vector storage.
The paper proposes FedLAB, a traceable semantic codebook framework for federated multimodal graph foundation learning, which organizes multimodal graph knowledge into hierarchical codebooks and refines them through federated semantic barycenter pre-training.
Papers
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li +3 more
The paper proposes FedLAB, a traceable semantic codebook framework for federated multimodal graph foundation learning, which organizes multimodal graph knowledge into hierarchical codebooks and refine…