Over the past decades, pansharpening has contributed greatly to numerous remote sensing applications, with methods evolving from theoretically grounded models to deep learning approaches and their hybrids. Though promising, existing methods rarely address pansharpening through the lens of underlying physical imaging processes. In this work, we revisit the spectral imaging mechanism and propose a novel physics-informed neural operator framework for pansharpening, termed PINO, which faithfully models the end-to-end electro-optical sensor process. Specifically, PINO operates as: (1) First, a spatial-spectral encoder is introduced to aggregate multi-granularity high-resolution panchromatic (PAN) and low-resolution multispectral (LRMS) features.

Neural Information Processing Systems http://nips.cc/

We present a novel compression algorithm for reducing the storage of LiDAR sensor data streams.

Here,weconsider the problem of learning semantic representations of objects that are invariant to pose and location in a fully unsupervised manner.

Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridging visual plans to actionable control in complex environments. T o address this problem, we propose Spatial Policy (SP), a unified spatial-aware visuomotor robotic manipulation framework via explicit spatial modeling and reasoning. Specifically, we first design a spatial-conditioned embodied video generation module to model spatially guided predictions through the spatial plan table. Then, we propose a flow-based action prediction module to infer executable actions with coordination. Finally, we propose a spatial reasoning feedback policy to refine the spatial plan table via dual-stage replanning. Extensive experiments show that SP substantially outperforms state-of-the-art baselines, achieving over 33% improvement on Meta-W orld and over 25% improvement on iTHOR, demonstrating strong effectiveness across 23 embodied control tasks. W e additionally evaluate SP in real-world robotic experiments to verify its practical viability. SP enhances the practicality of embodied models for robotic control applications.

ABSTRACT Scientific datasets often arise from multiple independent mechanisms such as spati al, categorical or structural effects, whose combined influence obscures their individual contributions. We introduce DIVIDE, a framework that disentangles these influences by integrating mechanism - specific deep encoders with a structured Gaussian Process in a joint latent space. Disentanglement here refers to separating independently acting generative factors . The encoders isolate distinct mechanisms while the Gaussian Process captures their combined effect with calibrated uncertainty. The architecture supports structured priors, enabling interpretable and mechanism - aware prediction as well as efficient active l earning. Across benc hmarks, DIVIDE separates mechanisms, reproduces additive and scaled interactions, and remains robust under noise. The framework extends naturally to multifunctional datasets where mechanical, electromagnetic or optical responses coexist. INTRODUCTION Many real - world systems exhibit behavior driven by the combined influence of multiple independent mechanisms. These mechanisms may represent categorical factors, spatial dependencies, or nonlinear physical responses. While the scalar output of such systems is observable, the individual contributions of these mechanisms are often unknown and unmeasured. Modeling this type of data requires not only accurate predictions but also the ability to attribute variation in the output to specific, distinct sources. In thi s context, we use disentanglement to mean recovering those independently acting generative factors from observational data. Disentangling these contributions is particularly important in scientific and engineering domains where interpretability, causality, and mechanism - aware reasoning are essential. Partial solutions to this challenge have emerged from the field of disentangled representation learning, which seeks to identify independent factors of variation from high - dimensional data.

Accurate and robust indoor localization is critical for smart building applications, yet existing Wi-Fi-based systems are often vulnerable to environmental conditions. This work presents a novel indoor localization system, called LiGen, that leverages the spectral intensity patterns of ambient light as fingerprints, offering a more stable and infrastructure-free alternative to radio signals. To address the limited spectral data, we design a data augmentation framework based on generative adversarial networks (GANs), featuring two variants: PointGAN, which generates fingerprints conditioned on coordinates, and FreeGAN, which uses a weak localization model to label unconditioned samples. Our positioning model, leveraging a Multi-Layer Perceptron (MLP) architecture to train on synthesized data, achieves submeter-level accuracy, outperforming Wi-Fi-based baselines by over 50\%. LiGen also demonstrates strong robustness in cluttered environments. To the best of our knowledge, this is the first system to combine spectral fingerprints with GAN-based data augmentation for indoor localization.

LiDAR point clouds, representing detailed three-dimensional descriptions of natural and built environments, are widely used in applications such as updating digital elevation models, monitoring glaciers and landslides, shoreline analysis, and urban development. A crucial step in these applications is the classification of 3D LiDAR points into semantic categories such as vegetation, man-made structures, and water. In our previous work [5], we introduced product coefficients as measure-theoretic descriptors that enrich LiDAR data with local structural information. Computed on dyadic neighborhoods around each point, these coefficients capture geometric variability beyond raw spatial coordinates.

Neural Information Processing Systems http://nips.cc/