Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
3
0
7
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.
LLM agents can now achieve a 92% success rate in complex code repository setup by learning from past failures, a 19% improvement over existing methods.
Forget prompt-to-paper pipelines – Claw AI Lab lets you spin up an entire autonomous, collaborative research team from a single prompt, complete with real-time monitoring and artifact inspection.
