Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.10340v1 Announce Type: cross Abstract: We consider online learning in non-stationary environments, where the goal is to track an unknown parameter that switches abruptly between a finite s...
arXiv:2610.10393v1 Announce Type: cross Abstract: Models can be retrained as new data arrive, but deploying every new version risks replacing a good policy with a worse one. We study how to plan poli...
arXiv:2602.07144v3 Announce Type: replace Abstract: Bayesian optimization (BO) is a popular technique for sample-efficient optimization of black-box functions. In many applications, the parameters be...
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process...
arXiv:2610.10286v1 Announce Type: new Abstract: Medical vision-language models (VLMs) have shown increasing potential for radiological image interpretation. Medical VLMs encode radiological images in...
arXiv:2610.10436v1 Announce Type: new Abstract: Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity p...
arXiv:2604.01989v4 Announce Type: replace Abstract: While multimodal large language models demonstrate strong entity-level perception, faithfully grounding relational interactions between objects rem...
arXiv:2610.10390v1 Announce Type: new Abstract: Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a funda...
arXiv:2610.09695v1 Announce Type: cross Abstract: Visual foundation models (VFMs) are increasingly integrated into end-to-end autonomous driving for their powerful representations, yet it remains unc...
arXiv:2605.24928v2 Announce Type: replace Abstract: Sonar imaging is the primary modality for underwater target detection, yet small targets remain difficult to detect due to insufficient pixel cover...
arXiv:2610.10301v1 Announce Type: new Abstract: Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transpa...
arXiv:2610.09087v1 Announce Type: cross Abstract: Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to...
arXiv:2610.09509v1 Announce Type: cross Abstract: Latent actions supervise robot policies with action-like codes inferred from visual transitions, and their usefulness hinges on two questions: what a...
arXiv:2610.09691v1 Announce Type: cross Abstract: We study online learning in market making, where, at each round, a market maker posts bid and ask prices before observing the market price and the pr...
arXiv:2610.09703v1 Announce Type: cross Abstract: Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work,...
arXiv:2610.09118v1 Announce Type: new Abstract: Topology reasoning jointly detects 3D lanes and traffic elements from multi-view images and infers their structural connectivity. Current methods model...
arXiv:2610.10429v1 Announce Type: new Abstract: Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions....
arXiv:2610.09502v1 Announce Type: new Abstract: Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with...
arXiv:2610.09633v1 Announce Type: new Abstract: The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engine...
arXiv:2610.09800v1 Announce Type: new Abstract: Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with re...