Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2510. 07074v2 Announce Type: replace-cross Abstract: Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts.
arXiv:2607. 23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others.
arXiv:2606. 25365v2 Announce Type: replace-cross Abstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair.
arXiv:2607. 23977v1 Announce Type: cross Abstract: Acoustic biomarkers show promise for detecting Alzheimer's Disease (AD), yet whether the cues driving diagnostic AI align with those salient to human listeners is underexplored across languages and genders, where pathological markers and perceptual strategies differ.
arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.
arXiv:2607. 24672v1 Announce Type: new Abstract: In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks.
arXiv:2607. 24522v1 Announce Type: new Abstract: While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored.
arXiv:2607. 22575v1 Announce Type: new Abstract: Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the limited mechanistic accessibility in long-term memory experiments in humans.
arXiv:2605. 14108v2 Announce Type: replace-cross Abstract: Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness, and automated screening can help extend specialist capacity in resource-constrained clinical workflows.
arXiv:2607. 22712v1 Announce Type: cross Abstract: Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity pose challenges to high-throughput automated analysis.
arXiv:2602. 19349v2 Announce Type: replace-cross Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode.
arXiv:2607. 22854v1 Announce Type: new Abstract: AI agents are enabling a new paradigm of agent-augmented real-time communication (RTC), where humans focus on high-level collaboration, while agents autonomously retrieve, analyze, and generate information in real time to support their interactions.
arXiv:2607. 23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.
arXiv:2607. 23524v1 Announce Type: new Abstract: Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy.
arXiv:2607. 23927v1 Announce Type: new Abstract: A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts.
arXiv:2607. 23944v1 Announce Type: new Abstract: Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions.
arXiv:2607. 24063v1 Announce Type: new Abstract: On standard factuality tasks, frontier models now cluster near the top of the scale.
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
arXiv:2607. 22758v1 Announce Type: cross Abstract: The integration of iterative LLMs within multi-agent diagnostic frameworks requires a rigorous quantitative reevaluation of underlying communication topologies.
arXiv:2607. 22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against physical reality before it is acted upon.