Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2508. 04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images.
arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.
arXiv:2607. 02586v1 Announce Type: new Abstract: Governance frameworks ask AI providers and auditors for documented evaluation evidence, and perturbation-based construct-validity audits are a common form of that evidence.
arXiv:2606. 05242v2 Announce Type: replace-cross Abstract: Stochastic gradient Langevin algorithms often use tamed denominators to stabilize superlinear drifts.
arXiv:2509. 22082v3 Announce Type: replace Abstract: Federated learning enables distributed information sharing and collaborative model training without exposing raw client data.
arXiv:2607. 03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance.
arXiv:2606. 12471v2 Announce Type: replace-cross Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.
arXiv:2607. 05052v1 Announce Type: cross Abstract: Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as independent labels.
arXiv:2607. 05281v1 Announce Type: cross Abstract: Present-day quantum computing is cloud-based, where a user submits a circuit to a service provider's proprietary backend hardware.
arXiv:2607. 02932v1 Announce Type: cross Abstract: Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI chatbots can use this information for user profiling.
arXiv:2607. 04613v1 Announce Type: new Abstract: Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed.
arXiv:2510. 25599v2 Announce Type: replace Abstract: Regression tasks, notably in safety-critical domains, require reliable uncertainty quantification, yet the literature remains largely classification-focused.
arXiv:2607. 04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow.
arXiv:2607. 04072v1 Announce Type: cross Abstract: Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user.
arXiv:2607. 02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns.
arXiv:2607. 05292v1 Announce Type: cross Abstract: Super-resolving coarse atmospheric fields to local PM$_{2.
arXiv:2607. 03196v1 Announce Type: cross Abstract: WiFi-based human pose estimation (HPE) enables the detection and interpretation of human body positions and movements without the need for wearable devices while preserving individual privacy concerns.
arXiv:2607. 03325v1 Announce Type: cross Abstract: We present an automated pipeline that decomposes Italian tax-court judgments into individual legal issues and extracts, for each issue, a structured XML representation grounded in the IRAC framework and the legal syllogism.
arXiv:2606. 28639v2 Announce Type: replace-cross Abstract: We establish the mathematical limits of AGI safety in two forms: verifying a fixed system, and verifying that a certified safety property persists once the system self-modifies.
arXiv:2604. 15579v2 Announce Type: replace-cross Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents.