Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.22164v1 Announce Type: cross Abstract: Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent sy...
arXiv:2609.22654v1 Announce Type: cross Abstract: Federated learning (FL) has emerged as a leading privacy-preserving framework for collaborative machine learning across decentralized environments. W...
arXiv:2609.22843v1 Announce Type: cross Abstract: Accurate and timely detection of degradation in lithium-ion batteries is crucial to ensure safety, reliability, and longevity in high-demand applicat...
arXiv:2609.23658v1 Announce Type: cross Abstract: Despite impressive visual quality, state-of-the-art video diffusion models often generate content that violates real-world physical laws. While exist...
arXiv:2609.23731v1 Announce Type: cross Abstract: Robotic systems are typically composed of multiple independently developed modules that work together to perceive, predict, and act in the environmen...
arXiv:2609.24260v1 Announce Type: cross Abstract: We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distrib...
arXiv:2609.24556v1 Announce Type: cross Abstract: Principal Component Analysis (PCA) minimises aggregate reconstruction error, which can inadvertently represent majority subgroups with substantially...
arXiv:2601.21702v4 Announce Type: replace Abstract: We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the l...
arXiv:2401.08038v2 Announce Type: replace-cross Abstract: A significant challenge to training accurate deep learning models on privacy policies is the cost and difficulty of obtaining a large and com...
arXiv:2504.09006v5 Announce Type: replace-cross Abstract: We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower where contextual...
arXiv:2504.14280v2 Announce Type: replace-cross Abstract: As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for improving model robustness across...
arXiv:2507.21543v3 Announce Type: replace-cross Abstract: Mutual information regularization has recently been studied in reinforcement learning (RL) as an extension of entropy regularization, in whic...
arXiv:2609.22104v1 Announce Type: new Abstract: As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottle...
arXiv:2609.22110v1 Announce Type: new Abstract: Background: Large language models (LLMs) can improve healthcare information delivery in low-resource settings but may produce inaccurate or culturally...
arXiv:2609.22112v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that...
arXiv:2609.22152v1 Announce Type: new Abstract: Imagination performs as a high-level function of large language models (LLMs) which determines the potential of how an LLM creates unseen or creative c...
arXiv:2609.22204v1 Announce Type: new Abstract: This exploratory pilot study evaluates the scope and perceived accuracy of personal information output from ongoing conversational interactions in gene...
arXiv:2609.22362v1 Announce Type: new Abstract: Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficien...
arXiv:2609.22988v1 Announce Type: new Abstract: Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains c...
arXiv:2609.23463v1 Announce Type: new Abstract: Federated learning lets multiple parties train a shared model without pooling their data, but a client with far less data than the others can end up po...