LLM Digest

Story

arxiv_cs_ai · Nov 5, 2026 · paper

Source brief

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning

arxiv.orgNov 5, 2026
original source linked

In brief

Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on

Read the original at arxiv.org →Open in live feed Read that day’s brief

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning

Earlier in this thread 4 items

When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning

FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models

Show HN: MoEShift - Faster large MoE inference with half the RAM