Related papers: Introducing Context Awareness in Unmodified, Conte…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…

The ability to automatically recognize a person's behavioral context can contribute to health monitoring, aging care and many other domains. Validating context recognition in-the-wild is crucial to promote practical applications that work…

Bounded rational agents often make decisions by evaluating a finite selection of choices, typically derived from a reference point termed the $`$default policy,' based on previous experience. However, the inherent rigidity of the static…

Detecting mixed-critical events through computer vision is challenging due to the need for contextual understanding to assess event criticality accurately. Mixed critical events, such as fires of varying severity or traffic incidents,…

Objects, in the real world, rarely occur in isolation and exhibit typical arrangements governed by their independent utility, and their expected interaction with humans and other objects in the context. For example, a chair is expected near…

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly…

The recent apparition of mobile wireless sensor aware to their physical environment and able to process information must allow proposing applications able to take into account their physical context and to react according to the changes of…

Is it possible to understand the intricacies of a dynamical system not solely from its input/output pattern, but also by observing the behavior of other systems within the same class? This central question drives the study presented in this…

Explainability is crucial for complex systems like pervasive smart environments, as they collect and analyze data from various sensors, follow multiple rules, and control different devices resulting in behavior that is not trivial and,…

Copy-paste-modify is a widespread and pragmatic practice in software development, where developers adapt reused code snippets, sourced from platforms such as Stack Overflow, GitHub, or LLM outputs, into their local codebase. A critical yet…

Continuous Integration (CI) is widely adopted in modern software development, yet adoption decisions are often made without systematic consideration of project context. Platforms such as GitHub Actions lower the barrier to CI adoption but…

Physical environment understanding is vital in delivering immersive and interactive mobile augmented reality (AR) user experiences. Recently, we have witnessed a transition in the design of environment understanding systems, from visual…

Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…

Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the…

LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt…

Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural…

Context modeling and recognition represent complex tasks that allow mobile and ubiquitous computing applications to adapt to the user's situation. Current solutions mainly focus on limited context information generally processed on…

With the rapid advancement of large language models (LLMs), intelligent conversational assistants have demonstrated remarkable capabilities across various domains. However, they still mainly rely on explicit textual input and do not know…

Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most…