Related papers: How to Embed Matters: Evaluation of EO Embedding D…

With 5G deployment and the evolution toward 6G, mobile networks must make decisions in highly dynamic environments under strict latency, energy, and spectrum constraints. Achieving this goal, however, depends on prior knowledge of…

Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and…

Embedding-based entity alignment (EEA) has recently received great attention. Despite significant performance improvement, few efforts have been paid to facilitate understanding of EEA methods. Most existing studies rest on the assumption…

Estimating uncertainty in text-to-image diffusion models is challenging because of their large parameter counts (often exceeding 100 million) and operation in complex, high-dimensional spaces with virtually infinite input possibilities. In…

Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost of training and evaluating models. Efficient Pareto front…

In autonomous driving, high-definition (HD) maps and semantic maps in bird's-eye view (BEV) are essential for accurate localization, planning, and decision-making. This paper introduces an enhanced End-to-End model named MapFM for online…

Graph Neural Networks (GNNs) have become the state-of-the-art method for many applications on graph structured data. GNNs are a model for graph representation learning, which aims at learning to generate low dimensional node embeddings that…

Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned representations. Recent EEG foundation models have demonstrated promising transfer capabilities…

We tackle the challenge of feature embedding for the purposes of improving the click-through rate prediction process. We select three models: logistic regression, factorization machines and deep factorization machines, as our baselines and…

Pretrained detectors perform well on benchmarks but often suffer performance degradation in real-world deployments due to distribution gaps between training data and target environments. COCO-like benchmarks emphasize category diversity…

Metasurfaces constitute effective media for manipulating and transforming impinging EM waves. Related studies have explored a series of impactful MS capabilities and applications in sectors such as wireless communications, medical imaging…

Delay embedding---a method for reconstructing dynamical systems by delay coordinates---is widely used to forecast nonlinear time series as a model-free approach. When multivariate time series are observed, several existing frameworks can be…

Latent representations are used extensively for downstream tasks, such as visualization, interpolation or feature extraction of deep learning models. Invariant and equivariant neural networks are powerful and well-established models for…

The Massive Text Embedding Benchmark (MTEB) has become a standard evaluation platform for text embedding models. While previous work has established the core benchmark methodology, this paper focuses on the engineering aspects that ensure…

Large-scale foundation models (FMs) in remote sensing (RS) are developed based on the paradigms established in computer vision (CV) and have shown promise for various Earth observation applications. However, the direct transfer of scaling…

Modeling environmental ecosystems is essential for effective resource management, sustainable development, and understanding complex ecological processes. However, traditional methods frequently struggle with the inherent complexity,…

We consider low-distortion embeddings for subspaces under \emph{entrywise nonlinear transformations}. In particular we seek embeddings that preserve the norm of all vectors in a space $S = \{y: y = f(x)\text{ for }x \in Z\}$, where $Z$ is a…

Energy-Based Models (EBMs) have proven to be a highly effective approach for modelling densities on finite-dimensional spaces. Their ability to incorporate domain-specific choices and constraints into the structure of the model through…

Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets and fixed sensor configurations, limiting their suitability for ecological and…

Task embeddings in multi-layer perceptrons for multi-task learning and inductive transfer learning in renewable power forecasts have recently been introduced. In many cases, this approach improves the forecast error and reduces the required…