Related papers: JPResUnet: A Joint Probability Density Function Tr…

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…

Laminar premixed flame profiles of methane/air free flames and strained flames at different fuel/air ratios and strain rates are analysed using detailed chemistry with Lewis numbers equal to one. It is shown that the detailed chemistry…

Large-eddy simulations (LES) require closures for filtered production rates because the resolved fields do not contain all correlations that govern chemical source terms. We develop a graph neural network (GNN) that predicts filtered…

This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a…

Diffusion world models have recently become competitive for online model-based reinforcement learning, but current approaches expose a tension: pixel diffusion is effective but computationally expensive while the latest latent diffusion…

Machine learning (ML) can facilitate efficient thermoelectric (TE) material discovery essential to address the environmental crisis. However, ML models often suffer from poor experimental generalizability despite high metrics. This study…

Despite the rapid evolution of semantic segmentation for land cover classification in high-resolution remote sensing imagery, integrating multiple data modalities such as Digital Surface Model (DSM), RGB, and Near-infrared (NIR) remains a…

BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to…

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e.g., financial costs…

In probability density function (PDF) methods a transport equation is solved numerically to compute the time and space dependent probability distribution of several flow variables in a turbulent flow. The joint PDF of the velocity…

Dusty plasmas are ubiquitous throughout the universe, spanning laboratory and industrial plasmas, fusion devices, planetary environments, cometary comae, and interstellar media. Despite decades of research, many aspects of their behavior…

In the realm of deploying Machine Learning-based Advanced Driver Assistance Systems (ML-ADAS) into real-world scenarios, adverse weather conditions pose a significant challenge. Conventional ML models trained on clear weather data falter…

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited…

Modeling complex dynamical systems with only partial knowledge of their physical mechanisms is a crucial problem across all scientific and engineering disciplines. Purely data-driven approaches, which only make use of an artificial neural…

Multi-tasking machine learning (ML) models exhibit prediction abilities in domains with little to no training data available (few-shot and zero-shot learning). Over-parameterized ML models are further capable of zero-loss training and…

Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new…

Formula recognition is an important task in document intelligence. It involves converting mathematical expressions from document images into structured symbolic formats that computers can easily work with. LaTeX is the most common format…

Large-eddy simulations (LES) of a planar turbulent lean hydrogen-air jet flame at Re = 11000 are performed using a tabulated flamelet model based on mixture-averaged diffusion that incorporates detailed transport, including differential and…

Satellite-derived data products and climate model simulations of geophysical variables like precipitation, often exhibit systematic biases compared to in-situ measurements. Bias correction and spatial downscaling are fundamental components…

Ultra-lean premixed hydrogen combustion is a possible solution to decarbonize industry, while limiting flame temperatures and thus nitrous oxide emissions. These lean hydrogen/air flames experience strong preferential diffusion effects,…