EEG-VID：面向 EEG 解码与辅助目标选择的任务引导潜在预测预训练框架
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection
AI 导读
研究者提出 EEG-VID，一种面向 EEG 解码的任务引导潜在预测预训练框架，通过指数滑动平均目标编码器预测未来潜在 EEG 状态，再进行监督微调。
正文 · 原文
Abstract:We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.00566 [cs.LG] |
| (or arXiv:2609.00566v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.00566 arXiv-issued DOI via DataCite |
Submission history
From: Guanzhong Sun [view email]
[v1]
Tue, 1 Sep 2026 02:00:58 UTC (4,575 KB)
[v2]
Wed, 2 Sep 2026 01:36:15 UTC (4,575 KB)
[v3]
Tue, 8 Sep 2026 06:00:16 UTC (4,575 KB)
[v4]
Mon, 26 Oct 2026 08:47:16 UTC (4,575 KB)
来源：arXiv cs.AI · arxiv.org