This paper proposes DAPGNet, a dynamic adaptive physics-guided graph diffusion network for hyperspectral image classification, which achieves state-of-the-art performance on four datasets.

A fully automated, calibration-free pipeline is presented to align 2D hyperspectral information with the 3D shape of ex-vivo lumpectomy specimens using consumer-camera RGB images and a single top-down…

TailLoR is a new parameter-efficient finetuning method that uses the singular bases of pre-trained weights to learn low-rank updates, specifically penalizing updates along dominant directions to impro…

FLORO is a multimodal geospatial foundation model that learns transferable remote sensing representations from a small, diverse corpus, achieving strong performance across various sensor types and res…

This paper derives deterministic limits for transfer learning performance of linear discriminant analysis in high-dimensional two-class classification under spiked covariance models.

This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.

This paper introduces MonoIR-RS, a large-scale infrared remote-sensing vision-language dataset and benchmark for understanding infrared imagery.

The paper proposes an attention-enhanced deep learning framework using EfficientNet and CBAM to achieve high accuracy (93.3%) in classifying peach leaf damage, demonstrating improved robustness under…

This paper introduces HySpecPro, a single-level hypergraph partitioner that performs end-to-end optimization in a spectral embedding space, delivering cut quality comparable to multilevel methods with…

This paper develops a unified spectral analysis framework to explain how knowledge transfer (KT) works across different machine learning regimes, such as Knowledge Distillation and Weak-to-Strong gene…

This paper identifies scattering network architectures that maximize separation capacity for data with low intrinsic dimension by characterizing and bounding the separation capacity of general feature…

This paper proposes an ensemble of two source separators, FTRNN and TF-Locoformer, trained with mixture invariant training (MixIT), and introduces mixture-constrained max pooling (MCM) to improve bird…

This paper introduces a structural theorem for the sparsifiability of real-valued codes, which generalizes both combinatorial and continuous notions of sparsification.

This paper provides the first algorithmic separation between constant-depth and logarithmic-depth networks, identifying a class of Boolean functions that logarithmic-depth networks can learn efficient…

The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…

The paper advocates for a paradigm shift toward joint Spatial Representation Learning (SRL) that unifies raster imagery and structured vector data into a single embedding space for developing more sem…

This paper introduces a method to automatically determine the optimal learning period ($ au$) for the Random Gradient hyper-heuristic, enabling it to optimally solve Pseudo-Boolean Problems without ma…