Related papers: Knowledge-Guided Machine Learning Models to Upscal…

Maximum likelihood (ML) learning for energy-based models (EBMs) is challenging, partly due to non-convergence of Markov chain Monte Carlo.Several variations of ML learning have been proposed, but existing methods all fail to achieve both…

Changing climate conditions threaten the natural permafrost thaw-freeze cycle, leading to year-round soil temperatures above 0{\deg}C. In Alaska, the warming of the topmost permafrost layer, known as the active layer, signals elevated…

For effective planning and management of water resources and implementation of the related strategies, it is important to ensure proper estimation of evaporation losses, especially in regions that are prone to drought. Changes in climatic…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Accurate fine-grained tree species classification is critical for forest inventory and biodiversity monitoring. Existing methods predominantly focus on designing complex architectures to fit local data distributions. However, they often…

Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this…

The main goal of machine learning (ML) is to study and improve mathematical models which can be trained with data provided by the environment to infer the future and to make decisions without necessarily having complete knowledge of all…

The large increase in the number of Internet of Things (IoT) devices have revolutionised the way data is processed, which added to the current trend from cloud to edge computing has resulted in the need for efficient and reliable data…

Artificial intelligence (AI) has made significant advances in recent years and opened up new possibilities in exploring applications in various fields such as biomedical, robotics, education, industry, etc. Among these fields, human hand…

Large language models (LLMs) such as ChatGPT, Gemini, LlaMa, and Claude are trained on massive quantities of text parsed from the internet and have shown a remarkable ability to respond to complex prompts in a manner often indistinguishable…

Machine learning (ML) can represent processes unresolved in coarse-resolution Earth system models (ESMs) by learning from high-resolution climate data. Such ML parameterization approaches have been primarily tested in idealized setups where…

Land surface temperature (LST) is vital for land-atmosphere interactions and climate processes. Accurate LST retrieval remains challenging under heterogeneous land cover and extreme atmospheric conditions. Traditional split window (SW)…

Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. Attention is the power-house driving modern deep learning successes, but it lacks clear…

Implicit policies parameterized by generative models, such as Diffusion Policy, have become the standard for policy learning and Vision-Language-Action (VLA) models in robotics. However, these approaches often suffer from high computational…

Modeling real-world phenomena is a focus of many science and engineering efforts, such as ecological modeling and financial forecasting, to name a few. Building an accurate model for complex and dynamic systems improves understanding of…

Machine learning-based hydrological prediction models, despite their high accuracy, face limitations in extrapolation capabilities when applied globally due to uneven data distribution. This study integrates Domain-Adversarial Neural…

The Earth Mover's Distance (EMD) is the measure of choice between point clouds. However the computational cost to compute it makes it prohibitive as a training loss, and the standard approach is to use a surrogate such as the Chamfer…

Aerodynamic performance evaluation is an important part of the aircraft aerodynamic design optimization process; however, traditional methods are costly and time-consuming. Despite the fact that various machine learning methods can achieve…

This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM). Our formulation posits that observed images are the sum of unobserved latent variables passed through the generator network and a…

The prevailing approaches for ET retrievals are either limited in spatiotemporal coverage or largely influenced by choice of input data or simplified model physics, or a combination thereof. Here, using an independent mass conservation…