Search papers, labs, and topics across Lattice.
2
1
5
1
Achieve centralized-level performance in federated LLM fine-tuning without compromising IP, privacy, or performance on heterogeneous data by using a compressed "proxy" model.
A 7B language model, distilled from multiple larger LLMs using a federated Chain-of-Thought approach, can achieve surprisingly strong performance on financial reasoning tasks.
