Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 05910v1 Announce Type: new Abstract: Student mobility programs such as Erasmus+ enable students to take courses at other universities, broadening their academic and cultural horizons.
arXiv:2608. 05242v1 Announce Type: new Abstract: In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training.
arXiv:2604. 21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops.
arXiv:2608. 05478v1 Announce Type: cross Abstract: Graphical Abstracts (GAs) visually summarize the key findings of academic papers, playing a crucial role in facilitating the understanding of research content.
arXiv:2605. 13894v2 Announce Type: replace-cross Abstract: In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus operators, inducing a piecewise-linear structure aligned with dynamic programming formulations.
arXiv:2608. 05839v1 Announce Type: cross Abstract: Deep neural networks have shown great empirical success in the solution of a wide variety of ill-posed inverse problems in imaging.
arXiv:2608. 05471v1 Announce Type: cross Abstract: Prenatal ultrasound imaging is key for assessing fetal health, but AI progress is limited by scarce, privacy-restricted, and hard-to-annotate datasets.
arXiv:2608. 05166v1 Announce Type: cross Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings.
arXiv:2608. 06020v1 Announce Type: new Abstract: Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their beliefs and actions, and the market and institutional mechanisms through which their interactions produce aggregate outcomes.
arXiv:2608. 05313v1 Announce Type: cross Abstract: Service robots operate in household environments shared with humans, pets, and everyday objects, where they are highly susceptible to failures such as software crashes, hardware degradation, or unpredictable interactions.
arXiv:2608. 06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
arXiv:2603. 27117v2 Announce Type: replace-cross Abstract: This paper investigates how gender shapes privacy decision-making in youth smart voice assistant (SVA) ecosystems.
arXiv:2608. 05439v1 Announce Type: new Abstract: Translating natural language instructions into machine-interpretable formal specifications enables robots and autonomous systems to plan, reason, and formally verify their behavior.
arXiv:2608. 05790v1 Announce Type: new Abstract: General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments.
arXiv:2608. 05867v1 Announce Type: new Abstract: The use of ontologies and knowledge graphs is becoming increasingly widespread in the defence and national security domain.
arXiv:2607. 08219v2 Announce Type: replace-cross Abstract: The privacy requirements of medical data and its substantial variations across organs and modalities hinder the clinical implementation of medical AI.
arXiv:2502. 14671v4 Announce Type: replace-cross Abstract: Large Language Model (LLM) representations are known to align with brain activity during language processing, but it remains unclear what drives this alignment.
arXiv:2608. 05734v1 Announce Type: new Abstract: Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.
arXiv:2608. 06115v1 Announce Type: new Abstract: Predicting how a population will answer a new question is a long-standing goal.
arXiv:2606. 23472v2 Announce Type: replace-cross Abstract: Time series classification involves learning a mapping from a continuous, temporally ordered sequence of real-valued observations to discrete response variables, like class labels.