Related papers: LEPA: Learning Geometric Equivariance in Satellite…
Exploiting internal spatial geometric constraints of sparse LiDARs is beneficial to depth completion, however, has been not explored well. This paper proposes an efficient method to learn geometry-aware embedding, which encodes the local…
Reliable subnational population estimates are essential for applications, yet remain difficult where censuses are sparse, outdated or spatially coarse. Existing population-mapping workflows rely on hand-built geospatial covariates, such as…
Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the…
World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the…
The aim of this paper is to show that spatial coupling can be viewed not only as a means to build better graphical models, but also as a tool to better understand uncoupled models. The starting point is the observation that some asymptotic…
Autoencoders are a widespread tool in machine learning to transform high-dimensional data into a lowerdimensional representation which still exhibits the essential characteristics of the input. The encoder provides an embedding from the…
We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the…
Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, reduce adaptation cost by injecting low-rank updates into pretrained weights. However, LoRA's down-projection is randomly initialized and data-agnostic, discarding potentially…
Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be 'smeared'. To address this, we…
Self-supervised learning has emerged as a major technique for the task of learning from unlabeled data, where the current methods mostly revolve around alignment of representations and input recon struction. Although such approaches have…
Self-supervised learning has achieved remarkable empirical success in learning robust representations without explicit labels, most recently demonstrated within the framework of Joint-Embedding Predictive Architectures (JEPA). However, a…
In this paper, we aim at tackling a general but interesting cross-modality feature learning question in remote sensing community --- can a limited amount of highly-discrimin-ative (e.g., hyperspectral) training data improve the performance…
We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…
This paper introduces an approach for detecting differences in the first-order structures of spatial point patterns. The proposed approach leverages the kernel mean embedding in a novel way by introducing its approximate version tailored to…
Image-to-point cross-modal learning has emerged to address the scarcity of large-scale 3D datasets in 3D representation learning. However, current methods that leverage 2D data often result in large, slow-to-train models, making them…
We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label…
Applying AI foundation models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of…
Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires reasoning about both semantic preferences…
Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal…
Joint Embedding Predictive Architectures (JEPA) offer a promising approach to self-supervised speech representation learning, but suffer from representation collapse without explicit grounding. We propose GMM-Anchored JEPA, which fits a…