Related papers: OCEAN: Online Task Inference for Compositional Tas…
A lot of real-world phenomena are complex and cannot be captured by single task annotations. This causes a need for subsequent annotations, with interdependent questions and answers describing the nature of the subject at hand. Even in the…
Successful Human-Robot collaboration requires a predictive model of human behavior. The robot needs to be able to recognize current goals and actions and to predict future activities in a given context. However, the spatio-temporal sequence…
Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories are created dynamically to serve specific goals. We study open ad-hoc…
This work focuses on the setting of dynamic regret in the context of online learning with full information. In particular, we analyze regret bounds with respect to the temporal variability of the loss functions. By assuming that the…
Location- and context-aware services are emerging technologies in mobile and desktop environments, however, most of them are difficult to use and do not seem to be beneficial enough. Our research focuses on designing and creating a…
As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing…
Nowadays, machine learning plays a key role in developing plenty of applications, e.g., smart homes, smart medical assistance, and autonomous driving. A major challenge of these applications is preserving high quality of the training and…
A major goal of computer vision is to enable computers to interpret visual situations---abstract concepts (e.g., "a person walking a dog," "a crowd waiting for a bus," "a picnic") whose image instantiations are linked more by their common…
Modern computer systems are highly configurable, with the total variability space sometimes larger than the number of atoms in the universe. Understanding and reasoning about the performance behavior of highly configurable systems, over a…
Humans possess the cognitive ability to comprehend scenes in a compositional manner. To empower AI systems with similar capabilities, object-centric learning aims to acquire representations of individual objects from visual scenes without…
A big challenge in environmental monitoring is the spatiotemporal variation of the phenomena to be observed. To enable persistent sensing and estimation in such a setting, it is beneficial to have a time-varying underlying environmental…
With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a…
Offline policy learning (OPL) leverages existing data collected a priori for policy optimization without any active exploration. Despite the prevalence and recent interest in this problem, its theoretical and algorithmic foundations in…
Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable…
In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…
Computing becomes increasingly mobile and pervasive today; these changes imply that applications and services must be aware of and adapt to their changing contexts in highly dynamic environments. Today, building context-aware systems is a…
Online Temporal Action Localization (On-TAL) aims to immediately provide action instances from untrimmed streaming videos. The model is not allowed to utilize future frames and any processing techniques to modify past predictions, making…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object…
In this work, we explore the mechanism of in-context learning (ICL) on out-of-distribution (OOD) tasks that were not encountered during training. To achieve this, we conduct synthetic experiments where the objective is to learn OOD…