Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2603. 16351v2 Announce Type: replace-cross Abstract: Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs.
arXiv:2602. 01086v3 Announce Type: replace Abstract: Generative AI can encode substantial medical knowledge, but patient-specific answers remain constrained by the context supplied at inference time.
arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.
arXiv:2607. 15265v1 Announce Type: cross Abstract: We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language.
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
arXiv:2607. 14314v1 Announce Type: new Abstract: Seizure diagnosis from EEG signals is a critical yet persistently challenging task, due to the complicated neural dynamics and the spurious connections in inter-channel modeling.
arXiv:2607. 14113v1 Announce Type: cross Abstract: While many AI-generated text (AIGT) detectors achieve strong performance on clean inputs, their accuracy degrades significantly under light paraphrasing, word substitutions, character edits, and distribution shifts.
arXiv:2607. 15254v1 Announce Type: new Abstract: Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion.
arXiv:2512. 06364v4 Announce Type: replace-cross Abstract: Current mobile health platforms are predominantly individual-centric and lack the support for coordinated, auditable multi-actor workflows.
arXiv:2607. 15094v1 Announce Type: cross Abstract: Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases.
arXiv:2607. 14640v1 Announce Type: new Abstract: Battery health estimation is fundamental for battery management in battery-powered systems, where inaccurate health states may affect control, maintenance, and service life.
arXiv:2607. 14287v1 Announce Type: cross Abstract: Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distribution shifts across scan conditions.
arXiv:2607. 14093v1 Announce Type: new Abstract: This paper presents a novel three level hierarchical learning architecture for autonomous UAV swarms performing search and rescue operations.
arXiv:2604. 23904v3 Announce Type: replace-cross Abstract: Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference.
arXiv:2607. 14346v1 Announce Type: new Abstract: Policy learning methods are increasingly used to inform treatment allocation under budget constraints.
arXiv:2607. 14641v1 Announce Type: new Abstract: Abductive reasoning operates in two directions.
arXiv:2607. 14285v1 Announce Type: cross Abstract: Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict?
arXiv:2607. 14280v1 Announce Type: cross Abstract: Flow-matching-based vision-language-action (VLA) models have emerged as powerful policies for robotic manipulation, yet a critical capability remains underexplored: fine-grained behavioral control, the ability to govern how a robot performs a task by intervening on its internal representations.
arXiv:2607. 14970v1 Announce Type: new Abstract: Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their recommendations.
Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable alignment with the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR), limiting both transparency and downstream model interpretability.