Related papers: Resonance: Replacing Software Constants with Conte…

In this work, we describe practical lessons we have learned from successfully using contextual bandits (CBs) to improve key business metrics of the Microsoft Virtual Agent for customer support. While our current use cases focus on single…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Contextual memory integration remains a high challenge in the development of language models, particularly in tasks that require maintaining coherence over extended sequences. Traditional approaches, such as self-attention mechanisms and…

Context: Context-aware contemporary software systems (CACSS) are mainstream. Furthermore, they present challenges for current engineering practices. These challenges are distinctively present when testing CACSS, as the variation of context…

Contextual bandit algorithms provide principled online learning solutions to balance the exploitation-exploration trade-off in various applications such as recommender systems. However, the learning speed of the traditional contextual…

Modern software systems are built to be used in dynamic environments using configuration capabilities to adapt to changes and external uncertainties. In a self-adaptation context, we are often interested in reasoning about the performance…

Multi-sensor fusion is central to robust robotic perception, yet most existing systems operate under static sensor configurations, collecting all modalities at fixed rates and fidelity regardless of their situational utility. This rigidity…

Service-Oriented Computing delivers the promise of configuring and reconfiguring software systems to address user's needs in a dynamic way. Context-aware computing promises to capture the user's needs and hence the requirements they have on…

Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on…

Virtual support agents have grown in popularity as a way for businesses to provide better and more accessible customer service. Some challenges in this domain include ambiguous user queries as well as changing support topics and user…

Message passing algorithms, whose iterative nature captures well complicated interactions among interconnected variables in complex systems and extracts information from the fixed point of iterated messages, provide a powerful toolkit in…

This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach. By harnessing the power of these models, the proposed approach…

Intent Classification (IC) and Slot Labeling (SL) models, which form the basis of dialogue systems, often encounter noisy data in real-word environments. In this work, we investigate how robust IC/SL models are to noisy data. We collect and…

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

This paper demonstrates that Semantic Context (SC), leveraging descriptive tool information, is a foundational component for robust tool orchestration. Our contributions are threefold. First, we provide a theoretical foundation using…

Being able to automatically and quickly understand the user context during a session is a main issue for recommender systems. As a first step toward achieving that goal, we propose a model that observes in real time the diversity brought by…

This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning. Previous methods primarily rely on hand-engineering or learning generators for specific constraint…

Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…

Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains,…

Software tends to be highly configurable, but most applications are hardly context aware. For example, a web browser provides many settings to configure printers and proxies, but nevertheless it is unable to dynamically adapt to a new…