Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University, Cloud Computing Research Institute
2
0
6
Federated RAG systems can now be practical: this work achieves a 62x speedup over prior secure methods, while maintaining model utility, by decoupling attention from data localization.
Forget static pipelines: SLMs can learn to dynamically seek help from LLMs, leading to better performance and transferability.
