Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.07383v1 Announce Type: cross Abstract: Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learni...
arXiv:2610.07426v1 Announce Type: cross Abstract: Accent classifiers are typically trained with a fixed label inventory and cannot accommodate new accent categories as new data becomes available. Mor...
arXiv:2610.07712v1 Announce Type: cross Abstract: Existing molecular and materials learning approaches often rely on a limited set of structural representations, which may capture only selected aspec...
arXiv:2610.07737v1 Announce Type: cross Abstract: We study fair multi-armed bandits under the Nash Social Welfare (NSW) objective, which measures performance via the geometric mean of accumulated rew...
arXiv:2610.07966v1 Announce Type: cross Abstract: Neural audio synthesis models like the Realtime Audio Variational autoEncoder (RAVE) achieve impressive genera tion quality, yet how their internal r...
arXiv:2610.08159v1 Announce Type: cross Abstract: COMET reports translation quality as a single number, and that number is routinely compared across target languages written in different scripts. Suc...
arXiv:2610.08715v1 Announce Type: cross Abstract: The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent tim...
arXiv:2610.08717v1 Announce Type: cross Abstract: We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the veloci...
arXiv:2401.09918v2 Announce Type: replace Abstract: Rule set learning has recently been frequently revisited because of its interpretability. Existing methods have several shortcomings though. First,...
arXiv:2510.01264v2 Announce Type: replace Abstract: Progress in adversarial multi-agent reinforcement learning (MARL) for robotics has been hampered by a lack of shared, extensible infrastructure tha...
arXiv:2511.11500v3 Announce Type: replace Abstract: Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accurac...
arXiv:2512.01917v2 Announce Type: replace Abstract: Eddy-covariance (EC) flux towers provide in situ measurements of $CO_2$ flux and serve as the ground-truth data for predictive `upscaling' models d...
arXiv:2512.03579v2 Announce Type: replace Abstract: Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregatin...
arXiv:2605.05660v3 Announce Type: replace Abstract: Multi-objective optimization (MOO) has received growing attention in applications that require learning under multiple criteria. However, most exis...
arXiv:2608.26877v3 Announce Type: replace Abstract: We classify when ordinary fixed-size volume sampling followed by unweighted least squares attains its sharp coefficient-covariance ceiling on a fix...
arXiv:2610.04142v2 Announce Type: replace Abstract: Modern training on a new task often starts from a previously trained model rather than from scratch, raising the question of how this initializatio...
arXiv:2602.06869v3 Announce Type: replace-cross Abstract: We study a persistent failure mode in multi-objective alignment for large language models (LLMs), in which scalarized training improves only...
arXiv:2610.06897v1 Announce Type: new Abstract: Localizing latent structures in the activation space of language models (LMs) is central to understanding and controlling their behavior. Yet, localize...
arXiv:2610.06956v1 Announce Type: new Abstract: Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especi...
arXiv:2610.07365v1 Announce Type: new Abstract: As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contribu...