paper-with-me

Papers

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

2025-06-06 · Fardis Nadimi, Payam Abdisarabshali, Kasra Borazjani, Jacob Chakareski, Seyyedali Hosseinalipour

Extended reality (XR) systems, which consist of virtual reality (VR), augmented reality (AR), and mixed reality (XR), offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task (M3T) federated foundation models (FedFMs) can offer transformative capabilities for XR systems through integrating the representational strength of M3T foundation models (FMs) with the privacy-preserving model training principles of federated learning (FL). We present a modular architecture for FedFMs, which entails different coordination paradigms for model training and aggregations. Central to our vision is the codification of XR challenges that affect the implementation of FedFMs under the SHIFT dimensions: (1) Sensor and modality diversity, (2) Hardware heterogeneity and system-level constraints, (3) Interactivity and embodied personalization, (4) Functional/task variability, and (5) Temporality and environmental variability. We illustrate the manifestation of these dimensions across a set of emerging and anticipated applications of XR systems. Finally, we propose evaluation metrics, dataset requirements, and design tradeoffs necessary for the development of resource-aware FedFMs in XR. This perspective aims to chart the technical and conceptual foundations for context-aware privacy-preserving intelligence in the next generation of XR systems.

📄 PDF Abstract BibTeX arXiv:2506.05683

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningMixed RealityPrivacy Preserving

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models

2024-08-17 · Xiaochen Wang, Jiaqi Wang, Houping Xiao, Jinghui Chen 외

Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are highly task-specific and modality-reliant.…

Federated LearningMixture-of-Experts

FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

2026-06-30 · Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li 외 arxiv

Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In prac…

Representation Learning

TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning

2025-09-30 · Seohyun Lee, Wenzhi Fang, Dong-Jun Han, Seyyedali Hosseinalipour 외 arxiv

In federated learning (FL), local personalization of models has received significant attention, yet personalized fine-tuning of foundation models remains underexplored. In particular, there is a lack of understanding in …

Federated Learning

Hierarchical Federated Foundation Models over Wireless Networks for Multi-Modal Multi-Task Intelligence: Integration of Edge Learning with D2D/P2P-Enabled Fog Learning Architectures

2025-09-03 · Payam Abdisarabshali, Fardis Nadimi, Kasra Borazjani, Naji Khosravan 외 arxiv

The rise of foundation models (FMs) has reshaped the landscape of machine learning. As these models continued to grow, leveraging geo-distributed data from wireless devices has become increasingly critical, giving rise t…

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

2026-07-17 · Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu 외 arxiv

Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offerin…

Federated LearningFew-Shot LearningGraph Learning