多模态大模型LLaVA与联邦学习结合，在保护隐私同时提升模型性能，已被计算机视觉顶会WACV接收。
arXiv:2409.06067v3 Announce Type: replace Abstract: Previous studies on federated learning (FL) often encounter performance degradation due to data he…
提出一种压缩模型大小与类别数双重带宽瓶颈的联邦蒸馏方法，大幅提升通信效率。
arXiv:2607.00173v1 Announce Type: new Abstract: Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often param…
联邦学习打破带宽瓶颈，让大模型预训练从数据中心走向协作分布式场景
arXiv:2411.02908v2 Announce Type: replace Abstract: Scaling large language models (LLMs) demands extensive data and computing resources, which are tra…
用大模型编码知识指导联邦图推荐，解决分布式非独立同分布客户端的结构嵌入聚合难题。
arXiv:2606.15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--…
联邦学习与大语言模型交叉领域的最新综述，由PAKDD 2026接收，系统梳理进展并展望未来方向。
arXiv:2409.15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their …
联邦学习新范式：让多个智能体在隐私保护下协同进化技能，分布式训练不止于模型参数。
arXiv:2606.03143v1 Announce Type: cross Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evoluti…
联邦学习与大模型结合时如何防御恶意客户端？这篇论文深入剖析了安全挑战与对策。
arXiv:2601.07177v5 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large lang…
联邦学习中的公平共形预测新方法FedCF，解决异质数据下的不确定性量化与公平性挑战。
arXiv:2509.22907v2 Announce Type: replace Abstract: Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learni…
联邦学习场景中，理论推导出非退化条件下带宽-准确率最优匹配率与最优分配策略，为异构带宽蒸馏提供严谨边界。
arXiv:2605.29642v1 Announce Type: cross Abstract: In federated language modeling, $K$ nodes each hold $n$ samples but cannot pool data or exchange ful…
为弱语言模型群组设计的一种任意时刻有效的联邦共形RAG框架，保障每个停止时间下的统计覆盖，突破传统固定时限限制。
arXiv:2605.29139v1 Announce Type: cross Abstract: Federated Conformal RAG (FC-RAG) provides distribution-free coverage for a bandwidth-limited swarm o…
联邦量子学习结合零噪声外推引导校正，有效提升噪声环境下量子模型的鲁棒性与性能。
arXiv:2605.30075v1 Announce Type: new Abstract: Quantum Federated Learning (QFL) offers a promising framework to train quantum models across distribut…
联邦学习新范式：解耦训练结合本地强化微调，有效平衡通信效率与个性化模型性能，被ICML 2026收录。
arXiv:2605.27900v1 Announce Type: new Abstract: Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising para…
联邦学习遇上LoRA新框架，专治大模型在异构设备上协作微调的痛点，方案灵活高效。
arXiv:2501.19389v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on resource-constrained clients remains a challenging pro…
基于区块链的容量感知联邦集成学习框架，专为医学影像中资源不均的医院设计。
arXiv:2605.24418v1 Announce Type: new Abstract: Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard fede…
联邦学习新思路：主动客户端选择算法，在保护隐私前提下实现公平与效率双赢
arXiv:2605.20975v1 Announce Type: new Abstract: Federated Learning enables collaborative model training across decentralized data sources without data…
提出CRAFT方法解决联邦学习中客户端模型更新冲突，通过冲突消解聚合提升训练效率与模型质量。
arXiv:2605.21317v1 Announce Type: new Abstract: The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (…
联邦学习下用合成表格数据自我优化大模型，Concordia框架有望提升隐私与效率。
arXiv:2605.09855v2 Announce Type: replace Abstract: Federated learning (FL) enables training large language models (LLMs) without sharing raw data, bu…
利用本地邻域信息就能高效检测去中心化学习中的后门攻击，无需全局数据，安全性与实用性兼备。
arXiv:2605.19969v1 Announce Type: new Abstract: Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train…
联邦学习新突破：无需本地数据的客户端贡献评估，用Logit最大化实现精准量化，兼顾隐私与效率。
arXiv:2605.18892v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative learning of computer vision models, where privacy and re…
综述探讨基础模型在个性化联邦智能中的应用，汇总当前方法、挑战与未来方向。
arXiv:2505.06907v2 Announce Type: replace-cross Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped th…