{"total":50,"rows":[{"id":"2502.07855","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","created":"2025-02-11","cited_by_count":29,"area":"mllm"},{"id":"2405.09771","title":"Harmonizing Generalization and Personalization in Federated Prompt Learning","created":"2024-05-16","cited_by_count":27,"area":"mllm"},{"id":"2409.19610","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","created":"2024-09-29","cited_by_count":22,"area":"mllm"},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2310.06123","title":"Text-driven Prompt Generation for Vision-Language Models in Federated Learning","created":"2023-10-09","cited_by_count":17,"area":"mllm"},{"id":"2410.10114","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","created":"2024-10-14","cited_by_count":17,"area":"mllm"},{"id":"2404.15182","title":"FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning","created":"2024-04-12","cited_by_count":16,"area":"mllm"},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2503.12897","title":"Federated Continual Instruction Tuning","created":"2025-03-17","cited_by_count":12,"area":"mllm"},{"id":"2501.02461","title":"FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Models","created":"2025-01-05","cited_by_count":11,"area":"mllm"},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2507.21494","title":"Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning","created":"2025-07-29","cited_by_count":9,"area":"mllm"},{"id":"2408.01228","title":"The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models","created":"2024-08-02","cited_by_count":8,"area":"mllm"},{"id":"2411.14717","title":"FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data","created":"2024-11-22","cited_by_count":7,"area":"mllm"},{"id":"2404.11046","title":"Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model","created":"2024-04-17","cited_by_count":5,"area":"mllm"},{"id":"2503.05776","title":"FAA-CLIP: Federated Adversarial Adaptation of CLIP","created":"2025-02-26","cited_by_count":5,"area":"mllm"},{"id":"2411.11912","title":"F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics","created":"2024-11-17","cited_by_count":4,"area":"mllm"},{"id":"2504.20860","title":"FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models","created":"2025-04-29","cited_by_count":4,"area":"mllm"},{"id":"2507.05394","title":"pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models","created":"2025-07-07","cited_by_count":4,"area":"mllm"},{"id":"2409.06067","title":"MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning","created":"2024-09-09","cited_by_count":3,"area":"mllm"},{"id":"2505.23024","title":"An Empirical Study of Federated Prompt Learning for Vision Language Model","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"id":"2310.03103","title":"Learning to Prompt Your Domain for Vision-Language Models","created":"2023-10-04","cited_by_count":2,"area":"mllm"},{"id":"2506.16218","title":"FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models","created":"2025-06-19","cited_by_count":2,"area":"mllm"},{"id":"2404.03854","title":"Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity","created":"2024-04-05","cited_by_count":1,"area":"mllm"},{"id":"2410.08478","title":"Federated Vision-Language-Recommendation with Personalized Fusion","created":"2024-10-11","cited_by_count":1,"area":"mllm"},{"id":"2503.06993","title":"CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model","created":"2025-03-10","cited_by_count":1,"area":"mllm"},{"id":"2504.04772","title":"Feedback-Enhanced Hallucination-Resistant Vision-Language Model for Real-Time Scene Understanding","created":"2025-04-07","cited_by_count":1,"area":"mllm"},{"id":"2505.01743","title":"An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding","created":"2025-05-03","cited_by_count":1,"area":"mllm"},{"id":"2509.06992","title":"FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models","created":"2025-09-03","cited_by_count":1,"area":"mllm"},{"id":"2511.16423","title":"TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models","created":"2025-11-20","cited_by_count":1,"area":"mllm"},{"id":"2602.04937","title":"Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture Optimization","created":"2026-02-04","cited_by_count":1,"area":"mllm"},{"id":"2603.26786","title":"A Step Toward Federated Pretraining of Multimodal Large Language Models","created":"2026-03-25","cited_by_count":1,"area":"mllm"},{"id":"2503.22263","title":"FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning","created":"2025-03-28","cited_by_count":0,"area":"mllm"},{"id":"2505.01851","title":"Mitigating Group-Level Fairness Disparities in Federated Visual Language Models","created":"2025-05-03","cited_by_count":0,"area":"mllm"},{"id":"2508.08040","title":"BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2508.12399","title":"Federated Cross-Modal Style-Aware Prompt Generation","created":"2025-08-17","cited_by_count":0,"area":"mllm"},{"id":"2510.17651","title":"Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs","created":"2025-10-20","cited_by_count":0,"area":"mllm"},{"id":"2511.00480","title":"FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts","created":"2025-11-01","cited_by_count":0,"area":"mllm"},{"id":"2511.07171","title":"Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use","created":"2025-11-10","cited_by_count":0,"area":"mllm"},{"id":"2512.04305","title":"How (Mis)calibrated is your Federated CLIP and what to do about it?","created":"2025-12-03","cited_by_count":0,"area":"mllm"},{"id":"2602.00485","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-01-31","cited_by_count":0,"area":"mllm"},{"id":"2602.08590","title":"SDFed: Bridging Local Global Discrepancy via Subspace Refinement and Divergence Control in Federated Prompt Learning","created":"2026-02-09","cited_by_count":0,"area":"mllm"},{"id":"2602.18439","title":"Replication Study: Federated Text-Driven Prompt Generation for Vision-Language Models","created":"2025-11-24","cited_by_count":0,"area":"mllm"},{"id":"2604.05375","title":"DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2605.03426","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2605.28347","title":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2607.12112","title":"Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning","created":"2026-07-13","cited_by_count":0,"area":"mllm"},{"id":"2609.07455","title":"Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2609.15671","title":"Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.22162","title":"Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation","created":"2026-08-26","cited_by_count":0,"area":"mllm"}],"next_cursor":null}