Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 06609v1 Announce Type: new Abstract: Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testing of the items under evaluation.
arXiv:2608. 07063v1 Announce Type: cross Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images.
arXiv:2608. 06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.
arXiv:2608. 06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability.
arXiv:2608. 06776v1 Announce Type: new Abstract: A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions.
arXiv:2608. 07139v1 Announce Type: new Abstract: Uncertainty quantification is essential when deploying machine learning models in safety-critical applications.
arXiv:2604. 16009v2 Announce Type: replace Abstract: Most large language model benchmarks evaluate final-answer quality but reveal little about how models revise beliefs under disagreement or conflicting evidence.
arXiv:2608. 07463v1 Announce Type: cross Abstract: Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis.
arXiv:2608. 06536v1 Announce Type: cross Abstract: Nonadiabatic dynamics needs an excited-state gradient and an interstate nonadiabatic coupling matrix element (NACME) at every nuclear geometry, and a double-hybrid functional's accuracy has been unavailable for the coupling.
arXiv:2605. 18079v2 Announce Type: replace Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice.
arXiv:2608. 06993v1 Announce Type: cross Abstract: Large-scale pretrained time-series models achieve strong results through large-scale pretraining and task-agnostic representation learning, but they rely on abundant, diverse data that industrial and scientific domains often lack.
arXiv:2509. 16462v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities.
arXiv:2608. 07378v1 Announce Type: cross Abstract: Early diagnosis of Alzheimer's disease (AD) is critical for enabling timely interventions that may slow disease progression and improve patient outcomes.
arXiv:2608. 06427v1 Announce Type: new Abstract: Generative models can reproduce an observational distribution while encoding an incorrect causal structure.
arXiv:2608. 07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy.
arXiv:2608. 06378v1 Announce Type: cross Abstract: Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions.
arXiv:2608. 06510v1 Announce Type: cross Abstract: Agentic AI promises a more flexible form of digital agency: systems that can act on users' behalf, from filtering content to negotiating prices to selecting services.
arXiv:2608. 06690v1 Announce Type: cross Abstract: Most language-model access controls regulate behavior while leaving the same computation available to every request.
arXiv:2604. 00310v2 Announce Type: replace-cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.
arXiv:2608. 06650v1 Announce Type: cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot control.