Related papers: LWM-Temporal: Sparse Spatio-Temporal Attention for…
The performance of wireless networks is fundamentally limited by the aggregate interference, which depends on the spatial distributions of the interferers, channel conditions, and user traffic patterns (or queueing dynamics). These factors…
Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream methods are dominated by…
Traffic forecasting in cellular networks is a challenging spatiotemporal prediction problem due to strong temporal dependencies, spatial heterogeneity across cells, and the need for scalability to large network deployments. Traditional…
We introduce Latent Particle World Model (LPWM), a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object…
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensor inputs becomes highly beneficial. Although several methods have been proposed to address different morphologies, it remains a…
Effective management of environmental resources and agricultural sustainability heavily depends on accurate soil moisture data. However, datasets like the SMAP/Sentinel-1 soil moisture product often contain missing values across their…
Video prediction yields future frames by employing the historical frames and has exhibited its great potential in many applications, e.g., meteorological prediction, and autonomous driving. Previous works often decode the ultimate…
Optimization-based approaches dominate infrared small target detection as they leverage infrared imagery's intrinsic low-rankness and sparsity. While effective for single-frame images, they struggle with dynamic changes in multi-frame…
Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…
One of the major task of sensor nodes in wireless sensor networks is to transmit a subset of sensor readings to the sink node estimating a desired data accuracy. Therefore in this paper, we propose an accuracy model using Steepest Decent…
Optical-flow-based and kernel-based approaches have been extensively explored for temporal compensation in satellite Video Super-Resolution (VSR). However, these techniques are less generalized in large-scale or complex scenarios,…
We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-based planners suffer…
Accurate spatiotemporal traffic forecasting is vital for intelligent resource management in 5G and beyond. However, conventional AI approaches often fail to capture the intricate spatial and temporal patterns that exist, due to e.g., the…
Service-level mobile traffic prediction for individual users is essential for network efficiency and quality of service enhancement. However, current prediction methods are limited in their adaptability across different urban environments…
Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…
Effective water resource management requires information on water availability, both in terms of quality and quantity, spatially and temporally. In this paper, we study the methodology behind Transfer Learning (TL) through fine-tuning and…
Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…
In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person re-identification task in videos. Different from the most existing methods, which simply compute representations of video clips…
Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…
Spatial-temporal forecasting and imputation are important for real-world intelligent systems. Most existing methods are tailored for individual forecasting or imputation tasks but are not designed for both. Additionally, they are less…