NObSP (Nonlinear Oblique Subspace Projections) is a framework that decomposes neural network predictions into explicit per‑feature contribution functions and an interaction residual, leveraging the linear final layer and oblique projections to avoid double counting when feature subspaces overlap. It connects to functional ANOVA and the Kolmogorov‑Arnold representation theorem, and introduces an efficient partial regression algorithm for out‑of‑sample evaluation. For convolutional networks, NObSP‑CAM generates class activation maps without backward passes after a single calibration, and experiments on tabular and vision datasets show faithfulness comparable to established attribution methods, with high function reproduction scores and improved class purity on TinyImageNet.
By Alexander Caicedo, V\'ictor De La Hoz, Santiago Alf\'erez
arXiv:2607. 19378v1 Announce Type: new Abstract: Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while recurrent models require rasterizing data such as images, volumes, and partial differential equation (PDE) into an ad-hoc $1\rm D$ scan order that violates their spatial structure.
By David R. Wessels, Farhad Ramezanghorbani, David W. Romero, Alireza Moradzadeh, Olivia Viessmann, Maksim Zhdanov, John St. John, Ken Janik, David M Knigge, Yucheng Tang, Erik J Bekkers, Saee Gopal Paliwal
arXiv:2609.22807v1 Announce Type: new
Abstract: Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weigh...
By Jinglei Shi, Xinran Chang, Jiaqi Cui, Yingjie Xia, Zhaolin Xiao, Chongyi Li
arXiv:2609.38348v1 Announce Type: new
Abstract: Many forms of data, including physical fields, geometric shapes, and visual signals, are naturally described by functions over continuous domains but a...
By Guorui Sang, Pedram Rooshenas
arXiv:2608.30720v1 Announce Type: new
Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied...
By Kieran Murphy
The paper introduces three algorithms—NTK-KIP, MetaQuill, and MetaQuill-KIP—to enhance neural fields (NFs) for reconstructing signals from sparse data. NTK-KIP distills a support set of coordinates to enable non‑linear inpainting with a finite NTK, while MetaQuill meta‑learns a shared initialization that allows quick adaptation to new scenes via a small weight offset. MetaQuill-KIP combines both approaches, achieving high‑quality, semantically plausible reconstructions with lightweight per‑instance adaptation, outperforming diffusion‑style baselines that rely on large pretrained generative models.
By Amir Mallak, Alaa Maalouf, Lior Wolf, Daniela Rus, Dan Rosenbaum
arXiv:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.
By Anirudh Thatipelli, Jeffrey Sam, Mathias Louboutin, Ali Siahkoohi, Rongrong Wang, Felix J. Herrmann
arXiv:2606. 19538v1 Announce Type: new Abstract: Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- and have remained mathematically distinct since their inception.
By Ashim Dhor, Rasel Mondal, Pin Yu Chen
arXiv:2505. 21736v2 Announce Type: replace-cross Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision.
By Siqi Fang, Zachary Schlamowitz, Andrew Bennecke, Daniel J. Tward
AdaKerNet is a task‑adaptive neural kernel decoder that operates on frozen multimodal representations from large foundation models, without requiring access to the models’ parameters. It learns Lipschitz‑controlled multimodal features, a reference kernel providing a soft structural prior, and a lightweight nonlinear predictor that deforms this structure. Experiments on four multimodal large language models and diverse input modalities show consistent improvements over baseline decoders, achieving up to 41% error reduction in scarce‑label settings.
By Konstantinos D. Polyzos, Eleni Oikonomou, Tara Javidi
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig
arXiv:2606. 01954v1 Announce Type: new Abstract: Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling.
By Luis A. Ortega, Andr\'es R. Masegosa, Thomas D. Nielsen