Related papers: Get Rid of Isolation: A Continuous Multi-task Spat…
Future projection of climate is typically obtained by combining outputs from multiple Earth System Models (ESMs) for several climate variables such as temperature and precipitation. While IPCC has traditionally used a simple model output…
Next Point-of-Interest (POI) recommendation is a research hotspot in business intelligence, where users' spatial-temporal transitions and social relationships play key roles. However, most existing works model spatial and temporal…
Spatiotemporal data is increasingly available due to emerging sensor and data acquisition technologies that track moving objects. Spatiotemporal clustering addresses the need to efficiently discover patterns and trends in moving object…
In multi-agent reinforcement learning (MARL), coordination plays a crucial role in enhancing agents' performance beyond what they could achieve through cooperation alone. The interdependence of agents' actions, coupled with the need for…
Representation learning has proven to be a powerful methodology in a wide variety of machine learning applications. For atmospheric dynamics, however, it has so far not been considered, arguably due to the lack of large-scale, labeled…
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework. However, most existing keypoint trackers are incapable of…
Structural magnetic resonance imaging (sMRI) provides accurate estimates of the brain's structural organization and learning invariant brain representations from sMRI is an enduring issue in neuroscience. Previous deep representation…
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling,…
Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract…
Recent advances in robotics have been largely driven by imitation learning, which depends critically on large-scale, high-quality demonstration data. However, collecting such data remains a significant challenge-particularly for mobile…
Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks together in order to…
Spatio-temporal forecasting is pivotal in numerous real-world applications, including transportation planning, energy management, and climate monitoring. In this work, we aim to harness the reasoning and generalization abilities of…
A key aspect of driving a road vehicle is to interact with other road users, assess their intentions and make risk-aware tactical decisions. An intuitive approach to enabling an intelligent automated driving system would be incorporating…
Recent progress in robotics and embodied AI is largely driven by Large Multimodal Models (LMMs). However, a key challenge remains underexplored: how can we advance LMMs to discover tasks that assist humans in open-future scenarios, where…
Human spatiotemporal behavior simulation is critical for urban planning research, yet traditional rule-based and statistical approaches suffer from high computational costs, limited generalizability, and poor scalability. While large…
Traversability estimation is the foundation of path planning for a general navigation system. However, complex and dynamic environments pose challenges for the latest methods using self-supervised learning (SSL) technique. Firstly, existing…
Accurate traffic forecasting is challenging due to the complex dependency on road networks, various types of roads, and the abrupt speed change due to the events. Recent works mainly focus on dynamic spatial modeling with adaptive graph…
Spatio-temporal prediction is crucial in numerous real-world applications, including traffic forecasting and crime prediction, which aim to improve public transportation and safety management. Many state-of-the-art models demonstrate the…
Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained with the complete multitude of ground-truths for all tasks…
Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…