Related papers: Learning to Factorize and Adapt: A Versatile Appro…

Forecasting high-resolution land subsidence is a critical yet challenging task due to its complex, non-linear dynamics. While standard architectures like ConvLSTM often fail to model long-range dependencies, we argue that a more fundamental…

In recent years, test-time adaptive object detection has attracted increasing attention due to its unique advantages in online domain adaptation, which aligns more closely with real-world application scenarios. However, existing approaches…

Modern IoT deployments for environmental sensing produce high volume spatiotemporal data to support downstream tasks such as forecasting, typically powered by machine learning models. While existing filtering and strategic deployment…

Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional models offer superior…

Traffic flow forecasting is essential and challenging to intelligent city management and public safety. Recent studies have shown the potential of convolution-free Transformer approach to extract the dynamic dependencies among complex…

Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safety-critical applications, where deep-neural-network-based systems must perform reliably under…

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference…

Recommender Systems (RS) pervade many aspects of our everyday digital life. Proposed to work at scale, state-of-the-art RS allow the modeling of thousands of interactions and facilitate highly individualized recommendations. Conceptually,…

Advances in time-series forecasting are driving a shift from conventional machine learning models to foundation models (FMs) that are trained with generalized knowledge. However, existing FMs still perform poorly in the energy fields, such…

Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is not memorization itself, but its target: vanilla SFT drives…

Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain…

Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although…

Fine-grained remote sensing image segmentation is essential for accurately identifying detailed objects in remote sensing images. Recently, vision transformer models (VTMs) pre-trained on large-scale datasets have demonstrated strong…

Recent studies have indicated that vision models pre-trained on images can serve as time series foundation models (TSFMs) by reformulating time series forecasting (TSF) as image reconstruction. However, effective cross-modal transfer from…

We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens to the input embeddings in the spatial domain, in this paper,…

Mobile devices and the Internet of Things (IoT) devices nowadays generate a large amount of heterogeneous spatial-temporal data. It remains a challenging problem to model the spatial-temporal dynamics under privacy concern. Federated…

Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to real-world scenarios due to the data distribution gap.…

Computed tomography (CT) imaging could be very practical for diagnosing various diseases. However, the nature of the CT images is even more diverse since the resolution and number of the slices of a CT scan are determined by the machine and…

Spatio-temporal data, prevalent in real-world applications such as traffic monitoring, financial transactions, and ride-share demands, represents a specialized case of multivariate time series characterized by high dimensionality. This high…

Pre-trained foundation models (FMs) have shown exceptional performance in univariate time series forecasting tasks. However, several practical challenges persist, including managing intricate dependencies among features and quantifying…