Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 13213v2 Announce Type: replace Abstract: Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing.
arXiv:2607. 06344v1 Announce Type: cross Abstract: While personalisation is becoming a defining capability in human-robot interaction (HRI), the existing literature on responsible personalisation remains fragmented, offering isolated accounts of ethical risks without a structured understanding of how they emerge across interaction contexts.
arXiv:2607. 05441v1 Announce Type: cross Abstract: Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks.
arXiv:2603. 21046v2 Announce Type: replace-cross Abstract: UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection.
arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.
arXiv:2607. 06254v1 Announce Type: cross Abstract: Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors.
arXiv:2607. 05536v1 Announce Type: cross Abstract: Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers.
arXiv:2607. 06531v1 Announce Type: new Abstract: - Objective: Multimodal deep learning models in oncology are currently limited by monolithic designs that rigidly couple data ingestion, clinical routing, and artificial intelligence (AI) inference.
arXiv:2607. 06326v1 Announce Type: new Abstract: Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation.
arXiv:2607. 05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''.
arXiv:2512. 19458v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly embedded in agentic frameworks for scientific discovery.
arXiv:2410. 11378v3 Announce Type: replace-cross Abstract: Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust.
arXiv:2607. 06013v1 Announce Type: new Abstract: Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventually changes the update geometry again.
arXiv:2605. 18419v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can couple visual perception with open-ended clinical reasoning, making them attractive for computational histopathology.
arXiv:2508. 01109v3 Announce Type: replace Abstract: We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and roads) and Internet-sourced text (reflecting historical, cultural, and narratives of neighborhoods).
arXiv:2607. 06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning.
arXiv:2607. 06495v1 Announce Type: cross Abstract: Live sports commentary is grounded generation under a deadline: statements concern real, named athletes, the grounding state changes every few seconds, and no reference text exists at generation time.
arXiv:2603. 28553v2 Announce Type: replace-cross Abstract: Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale.
arXiv:2607. 05735v1 Announce Type: cross Abstract: Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-theoretic inductive bias as large finite networks.
arXiv:2607. 05806v1 Announce Type: new Abstract: Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered.