arXiv：cs.LG· Yubo Wang, Jingying Ma, Xinliang Zhou, Yangxuan Zhou, Jiquan Wang, Sha Zhao, Yiyuan Yang, Yi Ding, Ziyu Jia, Chenyu Liu, Cuntai Guan·· 3 小时前AI 评分35
ZeroMAG：面向即插即用 EEG 基础模型的零样本多模态适配器生成
ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models
AI 导读
ZeroMAG 是一个零样本多模态适配器生成框架，可在不微调、不使用目标标签的情况下，为冻结的 EEG 基础模型扩展伴随生理模态。在六个留出目标数据集和三个 EFM 骨干上，其平衡准确率比纯 EEG 推理提升 7.22 个百分点，比直接权重回归高 4.89 个百分点，平均仅落后有监督多模态适配 0.50 个百分点。消融实验显示，去除表示学习或条件生成中的功能监督都会降低生成适配器性能。
正文
Authors:Yubo Wang, Jingying Ma, Xinliang Zhou, Yangxuan Zhou, Jiquan Wang, Sha Zhao, Yiyuan Yang, Yi Ding, Ziyu Jia, Chenyu Liu, Cuntai Guan
Abstract:EEG foundation models (EFMs) capture reusable knowledge from large-scale EEG data, while many EEG recordings also include companion physiological signals that provide complementary information beyond the EEG-only interface. The challenge is to preserve this pretrained knowledge while extending the EFM to heterogeneous multimodal recordings through an adaptation inferred from unlabeled target data. We introduce ZeroMAG, a zero-shot multimodal adapter generation framework that extends a frozen EEG encoder and prediction head using unlabeled target recordings, without target labels or target-side optimization. The target datasets are held out from all model training and selection in the ZeroMAG pipeline. ZeroMAG organizes companion modalities around a configuration-invariant adapter, constructs a modality-subject-task condition from unlabeled recordings and task context, and generates adapter weights in a function-constrained latent space learned from source adapters. Across six held-out target datasets and three EFM backbones, ZeroMAG improves balanced accuracy by 7.22 percentage points over EEG-only inference and 4.89 points over direct weight regression, while coming within 0.50 points of supervised multimodal adaptation on average. Ablations further show that removing functional supervision from either representation learning or conditional generation degrades generated-adapter performance, confirming the contribution of both components.
| Comments: | 41 pages |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03546 [cs.LG] |
| (or arXiv:2610.03546v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03546 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yubo Wang [view email]
[v1]
Fri, 2 Oct 2026 16:29:42 UTC (5,683 KB)
来源：arXiv：cs.LG · arxiv.org