Related papers: A Monitoring Language for Run Time and Post-Mortem…
By harnessing fiducial markers as visual landmarks in the environment, Unmanned Aerial Vehicles (UAVs) can rapidly build precise maps and navigate spaces safely and efficiently, unlocking their potential for fluent collaboration and…
We present OPAL (Operant Physical Agent with Language), a novel vision-language-action architecture that introduces topological constraints to flow matching for robotic control. To do so, we further introduce topological attention. Our…
This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents. Despite LLMs'…
Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…
This study presents an inspecting system using real-time control unmanned aerial vehicles (UAVs) to investigate structural surfaces. The system operates under favourable weather conditions to inspect a target structure, which is the…
Large Language models (LLMs) have shown remarkable success in assisting robot learning tasks, i.e., complex household planning. However, the performance of pretrained LLMs heavily relies on domain-specific templated text data, which may be…
The looking-in-looking-out (LILO) framework has enabled intelligent vehicle applications that understand both the outside scene and the driver state to improve safety outcomes, with examples in smart airbag deployment, takeover time…
Facial Expression Recognition (FER) is a fine-grained visual understanding task where reliable predictions require reasoning over localized and meaningful facial cues. Recent vision--language models (VLMs) enable natural language…
Monitoring is the study of a system at runtime, looking for input and output events to discover, check or enforce behavioral properties. Interactive debugging is the study of a system at runtime in order to discover and understand its bugs…
Fault injections are increasingly used to attack/test secure applications. In this paper, we define formal models of runtime monitors that can detect fault injections that result in test inversion attacks and arbitrary jumps in the control…
Pawns is a programming language under development which supports pure functional programming (including algebraic data types, higher order programming and parametric polymorphism) and imperative programming (including pointers, destructive…
In runtime verification, a monitor watches a trace of a system and, if possible, decides after observing each finite prefix whether or not the unknown infinite trace satisfies a given specification. We generalize the theory of runtime…
Binary analysis increasingly relies on large language models (LLMs) to perform semantic reasoning over complex program behaviors. However, existing approaches largely adopt a one-pass execution paradigm, where reasoning operates over a…
Unmanned aerial vehicles (UAVs) have been increasingly utilized in various civilian and military applications such as remote sensing, border patrolling, disaster monitoring, and communication coverage extension. However, there are still…
Objective: realtime monitoring of invasive ventilation (iV) in intensive care units (ICUs) plays a crucial role in ensuring prompt interventions and better patient outcomes. However, conventional methods often overlook valuable insights…
In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle 'off the path' scenarios where an agent veers from a reference…
Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of large vision-language models (VLMs). However, these agents…
Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback. Existing Reinforcement Learning (RL) methods train large reasoning models on a single-turn…
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…
Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as labeling commits, issues, and qualitative artifacts. Yet the reliability and reproducibility of such…