Implicit Neural Representations (INRs) have previously been used to represent and compress image and video content, demonstrating relatively high decoding speed compared to other methods.

Global Climate Models (GCMs) are critical for simulating large-scale climate dynamics, but their coarse spatial resolution limits their applicability in regional studies. Regional Climate Models (RCMs) refine this through dynamic downscaling, albeit at considerable computational cost and with limited flexibility. While deep learning has emerged as an efficient data-driven alternative, most existing studies have focused on single-variable models that downscale one variable at a time. This approach can lead to limited contextual awareness, redundant computation, and lack of cross-variable interaction. Our study addresses these limitations by proposing a multi-task, multi-variable Vision Transformer (ViT) architecture with a shared encoder and variable-specific decoders (1EMD). The proposed architecture jointly predicts three key climate variables: surface temperature (tas), wind speed (sfcWind), and 500 hPa geopotential height (zg500), directly from GCM-resolution inputs, emulating RCM-scale downscaling over Europe. We show that our multi-variable approach achieves positive cross-variable knowledge transfer and consistently outperforms single-variable baselines trained under identical conditions, while also improving computational efficiency. These results demonstrate the effectiveness of multi-variable modeling for high-resolution climate downscaling.

In recent years, diffusion models have emerged as powerful tools for generating ensemble members in meteorology. In this work, we demonstrate that a Denoising Diffusion Implicit Model (DDIM) can effectively control ensemble variance by varying the number of diffusion steps. Introducing a theoretical framework, we relate diffusion steps to the variance expressed by the reverse diffusion process. Focusing on reanalysis downscaling, we propose an ensemble diffusion model for the full ERA5-to-CERRA domain, generating variance-calibrated ensemble members for wind speed at full spatial and temporal resolution. Our method aligns global mean variance with a reference ensemble dataset and ensures spatial variance is distributed in accordance with observed meteorological variability. Additionally, we address the lack of ensemble information in the CARRA dataset, showcasing the utility of our approach for efficient, high-resolution ensemble generation.

EMANTIC segmentation plays a pivotal role in medical image analysis by differentiating organs and anatomical or introducing Gaussian noise can create uncertainty around structures by assigning a definitive class to each pixel, producing object boundaries. Furthermore, soft labels can stem from hard labels. Despite recent advancements that benefit annotators' disagreements regarding object boundaries in intraand from large datasets and significant computational power, such inter-rater annotations [11]. Averaging or fusing such dependencies pose challenges for researchers with constrained annotations produces soft labels, while the majority voting budgets. The necessity for full-resolution image processing makes hard labels. Empirically, loss functions tend to steer demands considerable computational resources and memory, network predictions towards extreme values (0 or 1) rather limiting broader participation. In response, lightweight networks than closely aligning with target soft labels, affecting class with fewer trainable parameters have been proposed, probability estimations, learning trajectories, and performance facilitating operation on mid-to low-range devices at the metrics.

Teeth localization, segmentation, and labeling in 2D images have great potential in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, general instance segmentation frameworks are incompetent due to 1) the subtle differences between some teeth' shapes (e.g., maxillary first premolar and second premolar), 2) the teeth's position and shape variation across subjects, and 3) the presence of abnormalities in the dentition (e.g., caries and edentulism). To address these problems, we propose a ViT-based framework named TeethSEG, which consists of stacked Multi-Scale Aggregation (MSA) blocks and an Anthropic Prior Knowledge (APK) layer. Specifically, to compose the two modules, we design 1) a unique permutation-based upscaler to ensure high efficiency while establishing clear segmentation boundaries with 2) multi-head self/cross-gating layers to emphasize particular semantics meanwhile maintaining the divergence between token embeddings. Besides, we collect 3) the first open-sourced intraoral image dataset IO150K, which comprises over 150k intraoral photos, and all photos are annotated by orthodontists using a human-machine hybrid algorithm. Experiments on IO150K demonstrate that our TeethSEG outperforms the state-of-the-art segmentation models on dental image segmentation.

Background: Photoacoustic Microscopy (PAM) integrates optical and acoustic imaging, offering enhanced penetration depth for detecting optical-absorbing components in tissues. Nonetheless, challenges arise in scanning large areas with high spatial resolution. With speed limitations imposed by laser pulse repetition rates, the potential role of computational methods is highlighted in accelerating PAM imaging. Purpose: We are proposing a novel and highly adaptable DiffPam algorithm that utilizes diffusion models for speeding up the photoacoustic imaging process. Method: We leveraged a diffusion model trained exclusively on natural images, comparing its performance with an in-domain trained U-Net model using a dataset focused on PAM images of mice brain microvasculature. Results: Our findings indicate that DiffPam achieves comparable performance to a dedicated U-Net model, without the need for a large dataset or training a deep learning model. The study also introduces the efficacy of shortened diffusion processes for reducing computing time without compromising accuracy. Conclusion: This study underscores the significance of DiffPam as a practical algorithm for reconstructing undersampled PAM images, particularly for researchers with limited AI expertise and computational resources.

Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable. Non-integer positions are handled via interpolation. Thanks to this trick, positions have well-defined gradients. The original DCLS used bilinear interpolation, and thus only considered the four nearest pixels. Yet here we show that longer range interpolations, and in particular a Gaussian interpolation, allow improving performance on ImageNet1k classification on two state-of-the-art convolutional architectures (ConvNeXt and Conv\-Former), without increasing the number of parameters. The method code is based on PyTorch and is available at https://github.com/K-H-Ismail/Dilated-Convolution-with-Learnable-Spacings-PyTorch