Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zhizhen, Luo, Xuanhao, Ge, Xueren, Zhou, Longyu, Lin, Xingqin, Liu, Yuchen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.12305
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915620590714880
author Li, Zhizhen
Luo, Xuanhao
Ge, Xueren
Zhou, Longyu
Lin, Xingqin
Liu, Yuchen
author_facet Li, Zhizhen
Luo, Xuanhao
Ge, Xueren
Zhou, Longyu
Lin, Xingqin
Liu, Yuchen
contents Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives, overlooking the broader potential of large foundation models for unified wireless sensing. To bridge this gap, we propose MMSense, a multi-modal, multi-task foundation model that jointly addresses channel-centric, environment-aware, and human-centered sensing. Our framework integrates image, radar, LiDAR, and textual data by transforming them into vision- compatible representations, enabling effective cross-modal align- ment within a unified feature space. A modality gating mecha- nism adaptively fuses these representations, while a vision-based large language model backbone enables unified feature align- ment and instruction-driven task adaptation. Furthermore, task- specific sequential attention and uncertainty-based loss weighting mechanisms enhance cross-task generalization. Experiments on real wireless scenario datasets show that our approach outper- forms both task-specific and large-model baselines, confirming its strong generalization across heterogeneous sensing tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12305
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MMSense: Adapting Vision-based Foundation Model for Multi-task Multi-modal Wireless Sensing
Li, Zhizhen
Luo, Xuanhao
Ge, Xueren
Zhou, Longyu
Lin, Xingqin
Liu, Yuchen
Machine Learning
Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives, overlooking the broader potential of large foundation models for unified wireless sensing. To bridge this gap, we propose MMSense, a multi-modal, multi-task foundation model that jointly addresses channel-centric, environment-aware, and human-centered sensing. Our framework integrates image, radar, LiDAR, and textual data by transforming them into vision- compatible representations, enabling effective cross-modal align- ment within a unified feature space. A modality gating mecha- nism adaptively fuses these representations, while a vision-based large language model backbone enables unified feature align- ment and instruction-driven task adaptation. Furthermore, task- specific sequential attention and uncertainty-based loss weighting mechanisms enhance cross-task generalization. Experiments on real wireless scenario datasets show that our approach outper- forms both task-specific and large-model baselines, confirming its strong generalization across heterogeneous sensing tasks.
title MMSense: Adapting Vision-based Foundation Model for Multi-task Multi-modal Wireless Sensing
topic Machine Learning
url https://arxiv.org/abs/2511.12305