Related papers: Task Aware Modulation Using Representation Learnin…

Can we improve the modeling of urban land surface processes with machine learning (ML)? A prior comparison of urban land surface models (ULSMs) found that no single model is 'best' at predicting all common surface fluxes. Here, we develop…

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt…

Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and…

Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predictive models, but often overlook rich local transition geometry…

Tactile representation learning (TRL) equips robots with the ability to leverage touch information, boosting performance in tasks such as environment perception and object manipulation. However, the heterogeneity of tactile sensors results…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

Natural climate solutions (NCS) offer an approach to mitigating carbon dioxide (CO2) emissions. However, monitoring the carbon drawdown of ecosystems over large geographic areas remains challenging. Eddy-flux covariance towers provide…

Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud. In recent works, Reinforcement…

Geological carbon and energy storage are pivotal for achieving net-zero carbon emissions and addressing climate change. However, they face uncertainties due to geological factors and operational limitations, resulting in possibilities of…

Reinforcement Learning (RL) in Traffic Signal Control (TSC) faces significant hurdles in real-world deployment due to limited generalization to dynamic traffic flow variations. Existing approaches often overfit static patterns and use…

Network representation learning (NRL) methods have received significant attention over the last years thanks to their success in several graph analysis problems, including node classification, link prediction, and clustering. Such methods…

The growing deployment of large language models (LLMs) makes per-request routing essential for balancing response quality and computational cost across heterogeneous model pools. Current routing methods rarely consider sustainable energy…

Offline reinforcement learning (RL) is an attractive tool for unmanned aerial vehicle (UAV) systems, where online exploration is costly and raises safety concerns. In terrain-aware UAV relaying, agents may observe high-dimensional inputs…

Accurate workload forecasting is critical for efficient resource management in cloud computing systems, enabling effective scheduling and autoscaling. Despite recent advances with transformer-based forecasting models, challenges remain due…

Transmission interface power flow adjustment is a critical measure to ensure the security and economy operation of power systems. However, conventional model-based adjustment schemes are limited by the increasing variations and…

The rapid growth of the digital economy and artificial intelligence has transformed cloud data centers into essential infrastructure with substantial energy consumption and carbon emission, necessitating effective energy management.…

Boreal forests store 30-40\% of terrestrial carbon, much in climate-vulnerable permafrost soils, making their management critical for climate mitigation. However, optimizing forest management for both carbon sequestration and permafrost…

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that…

Traffic forecasting is a challenging task due to the complex spatio-temporal correlations among traffic series. In this paper, we identify an underexplored problem in multivariate traffic series prediction: extreme events. Road congestion…

Urban flooding is expected to increase in frequency and severity as a consequence of climate change, causing wide-ranging impacts that include a decrease in urban Quality of Life (QoL). Meanwhile, policymakers must devise adaptation…