Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics
ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz, Austria（ELLIS单位、LIT AI实验室、机器学习研究所、JKU林茨，奥地利）；Emmi AI GmbH, Linz, Austria（Emmi AI公司、林茨，奥地利）
Anna Zimmel, Paul Setinek, Gianluca Galletti, Johannes Brandstetter, Werner Zellinger
Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks.
DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Science, VNU-HCM（胡志明市国家大学科学大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）；Trivita AI
Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
ELLIS Unit Linz, LIT AI Lab；Institute for Machine Learning, Johannes Kepler University Linz, Austria；Medical University Vienna；Clinical Research Center for Medical AI, Johannes Kepler University Linz, Austria
Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation
Intelligent Software Research Center, Institute of Software, CAS, Beijing, China（软件研究所智能软件研究中心，中国科学院，北京）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京）
Test-Time Adaptation in Optical Coherence Tomography Using Trajectory-Aligned Time-Independent Flow
Institute of Artificial Intelligence, Center for Medical Data Science, Medical University of Vienna, Austria（人工智能研究所、医学数据科学中心、维也纳医学大学，奥地利）；Comprehensive Center for Artificial Intelligence in Medicine, Medical University of Vienna, Austria（医学人工智能综合中心、维也纳医学大学，奥地利）；Department of Ophthalmology and Optometry, Medical University of Vienna, Austria（眼科与视光学部、维也纳医学大学，奥地利）；Laboratory for Ophthalmic Image Analysis, Medical University of Vienna, Austria（眼科图像分析实验室、维也纳医学大学，奥地利）
Advanced Computing, Mathematics and Data Division, Pacific Northwest National Laboratory（太平洋西北国家实验室先进计算、数学和数据 division）；Pacific Northwest National Laboratory（太平洋西北国家实验室）；Atmospheric Sciences and Global Change Division, Pacific Northwest National Laboratory（太平洋西北国家实验室大气科学与全球变化 division）
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
National College for Excellent Engineers, Beihang University, Beijing, China（北京航空航天大学优秀工程师学院）；School of Artificial Intelligence, Beihang University, Beijing, China（北京航空航天大学人工智能学院）；School of Electronic and Information Engineering, Beihang University, Beijing, China（北京航空航天大学电子与信息工程学院）；King Abdullah University of Science and Technology, Saudi Arabia（沙特国王 Abdullah 科学技术大学）；Huawei Noah’s Ark Lab, China（华为诺亚实验室）
SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts
LIT AI Lab（LIT人工智能实验室）；Institute for Machine Learning, JKU Linz, Austria（机器学习研究所，JKU林茨，奥地利）；Linz Center of Mechatronics GmbH, Linz, Austria（林茨机电研究中心有限公司，林茨，奥地利）；Emmi AI GmbH, Linz, Austria（Emmi人工智能有限公司，林茨，奥地利）
AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage
Faculty of Civil Engineering；Geosciences, TU Delft, Stevinweg 1, 2628 CN Delft, Netherlands；Centrum Wiskunde \& Informatica, Science Park 123, 1098 XG Amsterdam, Netherlands；Mathematical Institute, Utrecht University, Utrecht, Netherlands；Department of Earth Science；Engineering, Imperial College London, London, United Kingdom；Department of Energy Resources Engineering, Stanford University, CA, USA
Generalized Incremental Learning under Concept Drift across Evolving Data Streams
Australian Artificial Intelligence Institute (AAII), \ of Technology Sydney Sydney NSW Australia；Australian Artificial Intelligence Institute (AAII), \ of Technology Sydney
XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations
Division of Advanced Nuclear Engineering, Pohang University of Science and Technology（浦项国立科学技术大学先进核工程系）；Division of Applied Mathematics, Brown University（布朗大学应用数学系）；Graduate School of Integrated Energy-AI, Jeonbuk National University（全北国立大学整合能源-人工智能研究生院）
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
Booz Allen Hamilton（博思艾伦汉密尔顿公司）；Harvard University（哈佛大学）；Stanford University（斯坦福大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Laboratory for Physical Sciences（物理科学实验室）
Towards Spatio-Temporal Extrapolation of Phase-Field Simulations with Convolution-Only Neural Networks
Sandia National Laboratories（桑迪亚国家实验室）；Lawrence Berkeley National Laboratory（伯克利劳伦斯国家实验室）；University of California, Berkeley（加州大学伯克利分校）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
