FedICL-KVc: Federated In-Context Learning via KV Cache
Federated In-Context Learning via KV Cache (FedICL-KVc), a novel framework that enables effective utilization of private data without parameter updates, is proposed.
2 papers indexed here
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.
Federated In-Context Learning via KV Cache (FedICL-KVc), a novel framework that enables effective utilization of private data without parameter updates, is proposed.
Large language models (LLMs) are increasingly constrained by the scarcity of high-quality public data, making private data essential for further improvement. However, private data is typically distributed across resource-constrained devices and cannot be shared due to strict privacy requirements, rendering conventional...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.