Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models. However, standard LoRA typically assigns a fixed rank profile despite layer- and stage-dependent adaptation needs, while recent adaptive-rank variants often rely on heuristic or first-order signals that provide only an indirect link between rank reallocation and local loss behavior. This leaves the rationale behind each rank reallocation insufficiently interpretable. Motivated by this gap, we propose LIRA (Loss-Informed Rank Allocation), a dynamic-rank LoRA method designed to make online rank reallocation more interpretable. LIRA scores each layer by the estimated magnitude of the local loss perturbation associated with its recent LoRA-factor movements under a second-order approximation, making the basis for each rank change interpretable term by term. By periodically applying DELTA (Displacement-Evaluated Loss-Trajectory Allocation), a displacement-based algorithm for LoRA rank reallocation, LIRA produces discrete effective ranks under matched budgets while remaining compatible with standard (A,B) adapters. On RoBERTa-base GLUE under the La-LoRA/LoRA protocol, LIRA outperforms the uniform-LoRA and adaptive-rank baselines reported under this protocol; Trajectory EMA attains performance competitive with Fixed-point Fisher at lower estimation cost.
Modulated differentiable STFT and balanced spectrum metric for freight train wheelset bearing cross-machine transfer monitoring under speed fluctuations
State Key Laboratory of Advanced Rail Autonomous Operation(先进轨道交通自主运行状态重点实验室);Beijing Jiaotong University(北京交通大学);School of Mechanical, Electronic and Control Engineering(机械电子控制工程学院)
Interpretable Physics-Informed Load Forecasting for U.S. Grid Resilience: SHAP-Guided Ensemble Validation in Hybrid Deep Learning Under Extreme Weather
1Dept. of Computer Science, Midwestern State University, Dallas, TX, USA 2O\&M Analytics, AES Clean Energy, The AES Corporation, Louisville, CO, USA 3Dept. of Information;Communication Engineering, Pabna University of Science
LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs
Department of Civil Engineering, Tsinghua University, Beijing, China(清华大学土木工程系);College of Traffic Management, People's Public Security University of China, Beijing, China(中国人民公安大学交通管理学院);Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing, China(北京理工大学交通工程重点实验室);State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China(清华大学智能绿色车辆与移动国家重点实验室)
Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations
Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);School of Medicine and Health, TUM University Hospital(医学与健康学院,塔尔博恩大学医院);School of Computation, Information and Technology, TUM(计算、信息与技术学院,塔尔博恩大学);Weill Cornell Medicine, Cornell University, New York City(韦尔·科恩医学中心,康奈尔大学,纽约市)
PILA: Physics-Informed Low Rank Augmentation for Interpretable Earth Observation
Department of Computer Science and Technology, University of Cambridge(计算机科学与技术系,剑桥大学);Clare Hall, University of Cambridge(剑桥大学克莱尔学院);Cyclops AI;Department of Earth Sciences, University of Cambridge(地球科学系,剑桥大学)
An Ecologically-Informed Deep Learning Framework for Interpretable and Validatable Habitat Mapping
Gulf of Maine Research Institute(缅因湾研究所);The Institute for Experiential Artificial Intelligence, Northeastern University(东北大学体验式人工智能研究所);Universidad Nacional de Colombia(哥伦比亚国立大学);Universidad Austral de Chile(智利南方大学);Centro FONDAP de Investigación en Dinámica de Ecosistemas Marinos de Altas Latitudes(高纬度海洋生态系统动力学研究中心);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Northeastern University(东北大学)
Cluster-Based Generalized Additive Models Informed by Random Fourier Features
Department of Mathematics and Mathematical Statistics, Umeå University(数学与统计学系,乌梅大学);Department of Statistics, The Pennsylvania State University(统计系,宾夕法尼亚州立大学)
Platform of Bioinformatics (PBI), University Lausanne Hospital (CHUV) and Faculty of Biology and Medicine (FBM), University of Lausanne (UNIL)(生物信息平台(PBI)、日内瓦大学医院(CHUV)和生物医学学院(FBM)、日内瓦大学(UNIL));PBI, CHUV and FBM, UNIL(PBI、CHUV和FBM、UNIL);Department of Biomedical Engineering, University of Basel(生物医学工程系、巴塞尔大学);Roche Diagnostics International Ltd.(罗氏诊断国际有限公司);F. Hoffmann - La Roche Ltd., Roche Information Solutions(F. Hoffmann-La Roche有限公司、罗氏信息解决方案)
BubbleOKAN: A Physics-Informed Interpretable Neural Operator for High-Frequency Bubble Dynamics
Department of Mechanical and Materials Engineering, Worcester Polytechnic Institute(机械与材料工程系,沃斯通理工学院);Department of Aerospace Engineering, Worcester Polytechnic Institute(航空航天工程系,沃斯通理工学院);Department of Mechanical Engineering, University of Maryland(机械工程系,马里兰大学)
AI-informed model-analogs for understanding subseasonal-to-seasonal jet stream and North American temperature predictability
Department of Atmospheric Science, Colorado State University(科罗拉多州立大学大气科学系);Faculty of Computing and Data Sciences, Boston University(波士顿大学计算与数据科学学院);NOAA Physical Sciences Laboratory(美国国家海洋和大气管理局物理科学实验室)
Interpretable Machine Learning for Quantum-Informed Property Predictions in Artificial Sensing Materials
Institute for Materials Science(材料科学研究所);Max Bergmann Center for Biomaterials(生物材料中心);TUD Dresden University of Technology(德累斯顿技术大学);Institute of Physical Chemistry(物理化学研究所);Friedrich Schiller University Jena(耶拿弗里德里希·施莱尔大学);Dresden Center for Computational Materials Science (DCMS)(德累斯顿计算材料科学中心);Cluster of Excellence CARE(卓越中心CARE);Cluster of Excellence CeTI(卓越中心CeTI)