Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 31268v1 Announce Type: cross Abstract: The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows.
arXiv:2509. 15443v2 Announce Type: replace-cross Abstract: Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abundant, large-scale human motion collections.
arXiv:2510. 19600v2 Announce Type: replace-cross Abstract: In the quest for scientific progress, communicating research is as vital as the discovery itself.
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
arXiv:2606. 30821v1 Announce Type: new Abstract: Probabilistic downscaling is the task of modeling the conditional distribution of high-resolution fields given coarse inputs, and is a central challenge to atmospheric science, climate modeling, and other multiscale physical systems.
arXiv:2606. 30836v1 Announce Type: new Abstract: Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between high-dimensional decision variables and objective outcomes increasingly opaque.
arXiv:2606. 31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints.
arXiv:2606. 31272v1 Announce Type: cross Abstract: AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents.
arXiv:2606. 31589v1 Announce Type: cross Abstract: Organisations designing, developing, and deploying machine learning systems (MLS) need to be able to check that these systems are trustworthy, and communicate this clearly to their stakeholders, be they different categories of users, engineers, or wider society.
arXiv:2606. 31085v1 Announce Type: new Abstract: Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms.
arXiv:2510. 10895v2 Announce Type: replace Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured.
arXiv:2402. 06734v2 Announce Type: replace-cross Abstract: We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting.
arXiv:2603. 12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt alignment.
arXiv:2602. 02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical.
arXiv:2605. 09235v2 Announce Type: replace-cross Abstract: One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models.
arXiv:2606. 02301v2 Announce Type: replace-cross Abstract: Chronic pain diminishes quality of life by decreasing functional ability, yet objectively measuring this functional impact remains challenging in real-world settings.
arXiv:2606. 23375v2 Announce Type: replace-cross Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated risks have emerged.
arXiv:2507. 07109v2 Announce Type: cross Abstract: The VAMOS++ magnetic spectrometer is a multi-parametric system that integrates ion optical magnetic elements with a multi-detector stack.
arXiv:2602. 22083v2 Announce Type: replace-cross Abstract: Causal identification functionals often require integration over conditional densities of continuous variables, such as those arising in nonparametric identification theory of total and mediated causal effects in DAGs with hidden variables.
arXiv:2606. 30932v1 Announce Type: new Abstract: Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's experience.