Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 11847v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) integrate visual perception with language generation, enabling responses that span image understanding and complex reasoning.
arXiv:2608. 11335v1 Announce Type: cross Abstract: Clinical text can narrow down what to segment, but recent text-guided designs emphasize spatial alignment while overlooking frequency content that governs texture and boundaries.
arXiv:2608. 12166v1 Announce Type: cross Abstract: Algorithm registers have been championed as a means of providing transparency on the use of algorithms in public services.
arXiv:2608. 11495v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS).
arXiv:2608. 11324v1 Announce Type: cross Abstract: This paper proposes a contextual quality-diversity evolutionary reinforcement-learning controller, CQD-ERL, for the supervisory control of a tropical, water-cooled chiller plant and its associated air side.
arXiv:2608. 11613v1 Announce Type: new Abstract: In this paper, we propose a local Sinkhorn divergence framework for conditional distribution reconstruction of multidimensional random fields.
arXiv:2608. 11638v1 Announce Type: new Abstract: Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable.
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.
arXiv:2608. 11532v1 Announce Type: cross Abstract: In recent research on the Digital Twin-based Vehicular Ad hoc Network(DT-VANET), Federated Learning (FL) has shown its ability to provide data privacy.
arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
arXiv:2608. 11291v1 Announce Type: cross Abstract: Intrusion detection systems (IDS) and automated systems for detecting and reporting cyber threats, are commonly handled via supervised machine learning methods.
arXiv:2608. 11244v1 Announce Type: new Abstract: Construction standards are critical for building safety and sustainability.
arXiv:2608. 11283v1 Announce Type: cross Abstract: Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity.
arXiv:2506. 17332v2 Announce Type: replace-cross Abstract: By 2050, people aged 65 and over are projected to make up 16% of the global population.
arXiv:2510. 21112v3 Announce Type: replace-cross Abstract: High-definition 3D city maps enable city planning and change detection, which is essential for municipal compliance, map maintenance, and asset monitoring, including both built structures and urban greenery.
arXiv:2608. 11580v1 Announce Type: cross Abstract: Autonomous driving simulation requires diverse and scalable lane-level HD maps to support long-horizon evaluation across complex road networks.
arXiv:2608. 11698v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher.
arXiv:2608. 11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.
arXiv:2608. 11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks with no deterministic answer.