Reproduce “CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tianqi Zong, Baosheng Li, Nuocheng Yang, Binbin Chen, Marie Siew
CARE-FL selects clients for federated multimodal disaster-response classification by estimating long-term client utility and enforcing bandwidth and latency limits during selection. It approximates group value as the sum of client values. In a 50-client emulation, it reaches about 80% late-round accuracy under moderate constraints, while keeping resource use within imposed limits; results come from one CrisisMMD task.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.