Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601. 18685v4 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace.
arXiv:2601. 19618v2 Announce Type: replace-cross Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is the strongest known remedy.
arXiv:2505. 00473v2 Announce Type: replace Abstract: We explore the promising performance of a transformer model in predicting outputs of parametric dynamical systems with external time-varying input signals.
arXiv:2607. 21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user.
arXiv:2509. 25582v4 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history.
arXiv:2607. 21647v1 Announce Type: new Abstract: Quantum federated learning enables distributed clients to train quantum neural networks without sharing local data, making it promising for privacy-aware intelligent services.
arXiv:2605. 11017v2 Announce Type: replace Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and clinical dosing.
arXiv:2607. 21623v1 Announce Type: new Abstract: We present EaaS, a cloud-native reference architecture that operationalizes AI evaluation methods as six stateless Kubernetes microservices: conformal prediction with finite-sample-corrected Adaptive Prediction Sets, calibration assessment, drift detection via RFF-approximated Maximum Mean Discrepancy, fairness monitoring with bootstrap confidence intervals, a DAG-based pipeline orchestrator, and a result storage API.
arXiv:2607. 22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers.
arXiv:2607. 22153v1 Announce Type: cross Abstract: Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and data acquisition systems, maintenance records, inspection results, and prognostic models.
Large language model research agents can connect literature retrieval, analysis code, and manuscript preparation, but coherent output does not establish scientific validity. We developed Plato-Bio, a biology-routed extension of the open Plato/Denario architecture that couples explicit workflow states with provenance records, citation checks, claim-to-evidence links, scoped file writes, and publication gates.
Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geometry of unlearning are poorly understood.
Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment. We argue that many unlearning methods are vulnerable to a simple clustering attack, which can recover class structure in an unsupervised manner, limiting their suitability for continual deployment where removal requests must be handled reliably on demand.
Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization. However, its applicability remains largely limited to domains such as mathematics and coding, where correctness can be deterministically verified.
Pathological diagnosis is inherently multi-scale, requiring the integration of global tissue architecture at low magnification with cellular morphology at higher magnification. However, existing pathology benchmarks and vision-language models (VLMs) are still largely developed under single-scale settings, limiting their ability to learn clinically meaningful multi-magnification reasoning.
Controllable infrared-visible image fusion aims to integrate complementary thermal and structural information with flexible region-aware modulation, producing fused images that adapt to diverse user requirements and downstream tasks. However, existing methods typically rely on predefined discrete control conditions, leading to a sparse space that fails to support fine-grained modulation demands.
Safe quadrotor navigation in cluttered and dynamic environments depends not only on instantaneous geometric perception, but more critically on anticipating collision risks induced by relative motion. Conventional modular pipelines frequently suffer from perception latency, while end-to-end learning methods relying on implicit scalar rewards often struggle to extract reliable spatio-temporal features without physics-grounded supervision.
Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land somewhere, and what counts is how far, and in which directions, its answers can be steered.
Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear.
This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay.