In this paper we introduce a visualization methodology to aid a human analyst in classifying adversity modes that impact lidar scan matching. Our methodology is intended for offline rather than real-time analysis. The method generates a vector-field plot that characterizes local discrepancies between a pair of registered point clouds. The vector field plot reveals patterns that would be difficult for the analyst to extract from raw point-cloud data. After introducing our methodology, we apply the process to two proof-of-concept examples: one a simulation study and the other a field experiment. For both data sets, a human analyst was able to reason about a series of adversity mechanisms and iteratively remove those mechanisms from the raw data, to help focus attention on progressively smaller discrepancies.

The European Union's Artificial Intelligence Act (Regulation (EU) 2024/1689) establishes the world's first comprehensive regulatory framework for AI systems through a sophisticated ecosystem of interconnected subjects defined in Article 3. This paper provides a structured examination of the six main categories of actors - providers, deployers, authorized representatives, importers, distributors, and product manufacturers - collectively referred to as "operators" within the regulation. Through examination of these Article 3 definitions and their elaboration across the regulation's 113 articles, 180 recitals, and 13 annexes, we map the complete governance structure and analyze how the AI Act regulates these subjects. Our analysis reveals critical transformation mechanisms whereby subjects can assume different roles under specific conditions, particularly through Article 25 provisions ensuring accountability follows control. We identify how obligations cascade through the supply chain via mandatory information flows and cooperation requirements, creating a distributed yet coordinated governance system. The findings demonstrate how the regulation balances innovation with the protection of fundamental rights through risk-based obligations that scale with the capabilities and deployment contexts of AI systems, providing essential guidance for stakeholders implementing the AI Act's requirements.

Stellarators are inherently steady-state plasma confinement devices, which is among the key reasons behind their renaissance as promising candidates for fusion power plants. Ideal MHD equilibria are a central part in optimising the complex, three-dimensional plasma shapes which are a necessary condition for steady-state operation of such devices. The equilibrium magnetic field is required not only in optimisation but also plays a role in future real-time control algorithms and simulation frameworks (Schissel et al. 2025). Solving the three-dimensional MHD equations requires numerical approaches, because no analytical solutions throughout the full volume of ideal MHD equilibria with nested magnetic topology exists yet (Bruno & Laurence 1996). Recent work advanced analytical models for Fourier components of the equilibrium magnetic field in a subset of reactor-relevant magnetic fields and analytical expansions close to the magnetic axis are used extensively in research (Nikulsin et al. 2024; Sengupta et al. 2024). These analytical solutions and the following numerical solvers assume nested magnetic topology, or inte-grability throughout the volume, and computation of chaotic regions or magnetic islands takes considerably more effort (Hudson et al. 2012). Accuracy of numerical PDE solutions is inherently connected to the representation which defines gradients, and commonly used ideal MHD equilibrium solvers with nested magnetic field topology can be differentiated accordingly: A widely used finite-difference solver employed in the design of currently operating stellarator devices is VMEC (Hirshman & Whitson 1983), another pseudo spectral solver is DESC (Dudt & Kolemen 2020) and a third example is GVEC (Hindenlang et al. 2025), that abstracts the notion of basis functions, which enabled computation of plasmas with figure-8 shape (Plunk et al. 2025). Email address for correspondence: timo.thun@ipp.mpg.de

Physics-informed neural networks (PINNs) are neural networks that embed the laws of dynamical systems modeled by differential equations into their loss function as constraints. In this work, we present a PINN framework applied to oncology. Here, we seek to learn time-varying interactions due to a combination therapy in a tumor microenvironment. In oncology, experimental data are often sparse and composed of a few time points of tumor volume. By embedding inductive biases derived from prior information about a dynamical system, we extend the physics-informed neural networks (PINN) and incorporate observed biological constraints as regularization agents. The modified PINN algorithm is able to steer itself to a reasonable solution and can generalize well with only a few training examples. We demonstrate the merit of our approach by learning the dynamics of treatment applied intermittently in an ordinary differential equation (ODE) model of a combination therapy. The algorithm yields a solution to the ODE and time-varying forms of some of the ODE model parameters. We demonstrate a strong convergence using metrics such as the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

How does a cause lead to an effect, and which intermediate causal steps explain their connection? This work scrutinizes the mechanistic causal reasoning capabilities of large language models (LLMs) to answer these questions through the task of implicit causal chain discovery. In a diagnostic evaluation framework, we instruct nine LLMs to generate all possible intermediate causal steps linking given cause-effect pairs in causal chain structures. These pairs are drawn from recent resources in argumentation studies featuring polarized discussion on climate change. Our analysis reveals that LLMs vary in the number and granularity of causal steps they produce. Although they are generally self-consistent and confident about the intermediate causal connections in the generated chains, their judgments are mainly driven by associative pattern matching rather than genuine causal reasoning. Nonetheless, human evaluations confirmed the logical coherence and integrity of the generated chains. Our baseline causal chain discovery approach, insights from our diagnostic evaluation, and benchmark dataset with causal chains lay a solid foundation for advancing future work in implicit, mechanistic causal reasoning in argumentation settings.

Although both data availability and the demand for accurate forecasts are increasing, collaboration between stakeholders is often constrained by data ownership and competitive interests. In contrast to recent proposals within cooperative game-theoretical frameworks, we place ourselves in a more general framework, based on prediction markets. There, independent agents trade forecasts of uncertain future events in exchange for rewards. We introduce and analyse a prediction market that (i) accounts for the historical performance of the agents, (ii) adapts to time-varying conditions, while (iii) permitting agents to enter and exit the market at will. The proposed design employs robust regression models to learn the optimal forecasts' combination whilst handling missing submissions. Moreover, we introduce a pay-off allocation mechanism that considers both in-sample and out-of-sample performance while satisfying several desirable economic properties. Case-studies using simulated and real-world data allow demonstrating the effectiveness and adaptability of the proposed market design.

Multi-Agent Deep Reinforcement Learning (MADRL) has shown potential for cooperative and competitive tasks such as autonomous driving and strategic gaming. However, models trained by MADRL are vulnerable to adversarial perturbations on states and actions. Therefore, it is essential to investigate the robustness of MADRL models from an attack perspective. Existing studies focus on either state-only attacks or action-only attacks, but do not consider how to effectively joint them. Simply combining state and action perturbations such as randomly perturbing states and actions does not exploit their potential synergistic effects. In this paper, we propose the State-Action Joint Attack (SAJA) framework that has a good synergistic effects. SAJA consists of two important phases: (1) In the state attack phase, a multi-step gradient ascent method utilizes both the actor network and the critic network to compute an adversarial state, and (2) in the action attack phase, based on the perturbed state, a second gradient ascent uses the critic network to craft the final adversarial action. Additionally, a heuristic regularizer measuring the distance between the perturbed actions and the original clean ones is added into the loss function to enhance the effectiveness of the critic's guidance. We evaluate SAJA in the Multi-Agent Particle Environment (MPE), demonstrating that (1) it outperforms and is more stealthy than state-only or action-only attacks, and (2) existing state or action defense methods cannot defend its attacks.

Healthcare fraud detection remains a critical challenge due to limited availability of labeled data, constantly evolving fraud tactics, and the high dimensionality of medical records. Traditional supervised methods are challenged by extreme label scarcity, while purely unsupervised approaches often fail to capture clinically meaningful anomalies. In this work, we introduce CleverCatch, a knowledge-guided weak supervision model designed to detect fraudulent prescription behaviors with improved accuracy and interpretability. Our approach integrates structured domain expertise into a neural architecture that aligns rules and data samples within a shared embedding space. By training encoders jointly on synthetic data representing both compliance and violation, CleverCatch learns soft rule embeddings that generalize to complex, real-world datasets. This hybrid design enables data-driven learning to be enhanced by domain-informed constraints, bridging the gap between expert heuristics and machine learning. Experiments on the large-scale real-world dataset demonstrate that CleverCatch outperforms four state-of-the-art anomaly detection baselines, yielding average improvements of 1.3\% in AUC and 3.4\% in recall. Our ablation study further highlights the complementary role of expert rules, confirming the adaptability of the framework. The results suggest that embedding expert rules into the learning process not only improves detection accuracy but also increases transparency, offering an interpretable approach for high-stakes domains such as healthcare fraud detection.

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight, model-agnostic preprocessing framework that couples fine-grained safety classification with category-specific guidance and explicit actions (Block, Reframe, Forward). Unlike binary moderators, SHIELD composes tailored safety prompts that enforce nuanced refusals or safe redirection without retraining. Across five benchmarks and five representative LVLMs, SHIELD consistently lowers jailbreak and non-following rates while preserving utility. Our method is plug-and-play, incurs negligible overhead, and is easily extendable to new attack types -- serving as a practical safety patch for both weakly and strongly aligned LVLMs.

We introduce MENAValues, a novel benchmark designed to evaluate the cultural alignment and multilingual biases of large language models (LLMs) with respect to the beliefs and values of the Middle East and North Africa (MENA) region, an underrepresented area in current AI evaluation efforts. Drawing from large-scale, authoritative human surveys, we curate a structured dataset that captures the sociocultural landscape of MENA with population-level response distributions from 16 countries. To probe LLM behavior, we evaluate diverse models across multiple conditions formed by crossing three perspective framings (neutral, personalized, and third-person/cultural observer) with two language modes (English and localized native languages: Arabic, Persian, Turkish). Our analysis reveals three critical phenomena: "Cross-Lingual Value Shifts" where identical questions yield drastically different responses based on language, "Reasoning-Induced Degradation" where prompting models to explain their reasoning worsens cultural alignment, and "Logit Leakage" where models refuse sensitive questions while internal probabilities reveal strong hidden preferences. We further demonstrate that models collapse into simplistic linguistic categories when operating in native languages, treating diverse nations as monolithic entities. MENAValues offers a scalable framework for diagnosing cultural misalignment, providing both empirical insights and methodological tools for developing more culturally inclusive AI.