Related papers: Deep neural network enabled corrective source term…

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant…

This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming. Unlike classical approximate dynamic programming approaches, we first approximate the optimal policy by means of…

Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is…

As a promising 6G enabler beyond conventional bit-level transmission, semantic communication can considerably reduce required bandwidth resources, while its combination with multiple access requires further exploration. This paper proposes…

Text-to-image models like stable diffusion and DALLE-3 still struggle with multi-turn image editing. We decompose such a task as an agentic workflow (path) of tool use that addresses a sequence of subtasks by AI tools of varying costs.…

In this paper, we propose a novel deep coherence model (DCM) using a convolutional neural network architecture to capture the text coherence. The text coherence problem is investigated with a new perspective of learning sentence…

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective,…

3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and…

The robotic systems continuously interact with complex dynamical systems in the physical world. Reliable predictions of spatiotemporal evolution of these dynamical systems, with limited knowledge of system dynamics, are crucial for…

Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic parameterizations with calibrated…

Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations, they might fail catastrophically in unseen sites. Although…

While domain adaptation methods address data shifts, most assume target populations align with at least one source population, neglecting mixtures that combine sources influenced by factors like demographics. Additional challenges in…

Process-based models (PBMs) and deep learning (DL) are two key approaches in agricultural modelling, each offering distinct advantages and limitations. PBMs provide mechanistic insights based on physical and biological principles, ensuring…

Despite the remarkable success of the end-to-end paradigm in deep learning, it often suffers from slow convergence and heavy reliance on large-scale datasets, which fundamentally limits its efficiency and applicability in data-scarce…

Accurate and efficient climate simulations are crucial for understanding Earth's evolving climate. However, current general circulation models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection.…

Supply chain resilience and efficiency are vital in industries characterized by volatile demand and uncertain supply, such as textiles and personal protective equipment (PPE). Traditional forecasting and optimization approaches often…

Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However, due to the autoregressive, step-by-step generation paradigm, existing CoT methods suffer from…

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that…

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…