This paper presents a new classification methods for Event Related Potentials (ERP) based on an Information geometry framework. Through a new estimation of covariance matrices, this work extend the use of Riemannian geometry, which was previously limited to SMR-based BCI, to the problem of classification of ERPs. As compared to the state-of-the-art, this new method increases performance, reduces the number of data needed for the calibration and features good generalisation across sessions and subjects. This method is illustrated on data recorded with the P300-based game brain invaders. Finally, an online and adaptive implementation is described, where the BCI is initialized with generic parameters derived from a database and continuously adapt to the individual, allowing the user to play the game without any calibration while keeping a high accuracy.
T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs
Huazhong University of Science and Technology（华中科技大学）；School of Artificial Intelligence and Automation（人工智能与自动化学院）；Shenzhen Huazhong University of Science and Technology Research Institute（华中科技大学深圳研究院）；Zhengzhou University（郑州大学）；School of Electrical and Information Engineering（电气工程学院）；School of Civil and Hydraulic Engineering（土木工程与水利工程学院）
Leveraging Foundation Models for Calibration-Free c-VEP BCIs
Department of Biomedical Engineering, University of Calgary（生物医学工程系，卡尔加里大学）；Department of Electrical and Computer Engineering, Queen’s University（电气与计算机工程系，皇后大学）；Department of Pediatric and Clinical Neuroscience, University of Calgary（儿科与临床神经科学系，卡尔加里大学）；Department of Electrical and Software Engineering, University of Calgary（电气与软件工程系，卡尔加里大学）
即插即用（Plug-and-Play，PSTO）框架使得将先进的图像去噪先验集成到优化算法中成为可能，从而有效地解决了通常被公式化为最大后验概率（Maximum A Posteriori，MAP）估计问题的各种图像恢复任务。即插即用交替方向乘法器（ADMM）和去噪正则化（RED）算法是这类方法的两个例子，在图像恢复方面取得了突破。然而，虽然前一种方法只适用于近似算法，但最近已经表明，当去噪器缺乏雅可比对称性时，不存在解释RED算法的正则化，这恰好是大多数实际去噪器的情况。据我们所知，没有一种方法可以训练直接表示正则化器梯度的网络，这可以直接用于即插即用的基于梯度的算法。我们表明，它是可能的训练网络直接建模的MAP正则化梯度，同时共同训练相应的MAP去噪。我们使用这个网络在基于梯度的优化方法，并获得更好的结果相比，其他通用的即插即用的方法。我们还证明了正则化器可以用作展开梯度下降的预训练网络。最后，我们表明，由此产生的去噪器允许一个更好的收敛的即插即用ADMM。
PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation
College of Computer Science and Technology, Harbin Engineering University（哈尔滨工程大学计算机科学与技术学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Department of Computer Science and Engineering, University of Bologna（博洛尼亚大学计算机科学与工程系）
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Technical University of Darmstadt（达姆施塔特工业大学）；Universität der Bundeswehr München（慕尼黑联邦国防军大学）；Centre for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）；Hessian Center for AI (hessian.AI)（黑森人工智能中心（hessian.AI））
Image Restoration using Plug-and-Play CNN MAP Denoisers
Centre Suisse d’Electronique et de Microtechnique (CSEM)（瑞士电子与微技术中心（CSEM））；School of Computer and Communication Sciences, École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院（EPFL）计算机与通信科学学院）
