arXiv:2607.15583v1 Announce Type: new
Abstract: Persistent aerial surveillance using multi-unmanned aerial systems (UASs) requires decentralized coordination, continuous team reconfiguration, and provable mission correctness despite limited onboard energy and communication constraints. This paper develops a distributed framework for continuous aerial surveillance under bounded Linear Temporal Logic (LTL) mission specifications. The proposed approach partitions the UAS team into stationary anchors and mobile workers operating under cyclic replacement modes, and constructs a deep neural network (DNN)-inspired communication topology that enables fully decentralized coordination through local interactions. A hierarchical bounded LTL specification formally captures mode-to-mode reference consistency, cyclic team rotation, finite-time reachability, trajectory tracking, and prescribed surveillance coverage. By proving the finite-time convergence of the worker-agent coordination dynamics, the paper guarantees the finite-time satisfaction of the mission specification. To maximize sensing effectiveness, an information-theoretic optimization framework synthesizes the reference configuration of newly deployed worker agents by minimizing the Kullback--Leibler divergence between the surveillance-node distribution and the induced coverage density. The resulting reference configuration uniquely determines a deterministic, mode-dependent communication topology, eliminating online communication-graph optimization while preserving the formal mission guarantees. Finally, a decentralized quadrotor controller realizes the distributed references using only local communication. Numerical simulations demonstrate cyclic team reconfiguration, decentralized communication-topology synthesis, finite-time formation convergence, and certified persistent surveillance coverage.
Science Journals
arXiv:2607.15957v1 Announce Type: new
Abstract: Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations.Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior.However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.
arXiv:2607.15961v1 Announce Type: new
Abstract: Control barrier functions (CBFs) provide formal safety guarantees for constrained nonlinear systems, but their effectiveness relies on accurate system dynamics. In high-dimensional manipulators subject to unknown disturbances and model uncertainties, fixed safety constraints constructed from nominal dynamics may become inconsistent with the actual system behavior, leading to safety degradation or excessive conservatism. This paper proposes a dynamic constraint reconstruction based control barrier function (DCR-CBF) framework for safety-critical control of disturbed robotic manipulators. An extended state observer is employed to estimate lumped disturbances online, and the estimated disturbance is incorporated into high-order control barrier functions to reconstruct safety constraints according to the estimated true dynamics. To address estimation inaccuracies, a safety margin is introduced, and a sufficient condition is derived to guarantee forward invariance under bounded estimation errors. Simulation studies on a 4-DOF excavation manipulator demonstrate that the proposed DCR-CBF method achieves zero safety violation under strong unknown disturbances while significantly improving trajectory-tracking performance compared with standard and robust CBF methods.
arXiv:2607.15963v1 Announce Type: new
Abstract: With the rise of online insurance sales, consumers face a significant \enquote{advice gap}, requiring them to navigate complex legal contracts without expert guidance. This paper presents a human-centric, extrinsic evaluation of a state-of-the-art Retrieval-Augmented Generation system, designed to make Quebec automobile insurance contracts more understandable. Through a user study with 154 participants from Laval University, we assess the agent's real-world utility by measuring system satisfaction, cognitive effort, perceived autonomy, and risk. Our results show the system is perceived as a \enquote{cognitive equalizer}, receiving high ratings for satisfaction, trust, and clarity. Crucially, users value the sense of autonomy the system provides even more than the knowledge itself, with this effect being most pronounced among participants with lower financial literacy, demonstrating how such an agent can directly empower individuals. However, our study also highlights some limitations: participants expressed a strong preference for human agents in high-stakes or emotionally charged scenarios. This work highlights the importance of human-in-the-loop frameworks in ensuring the responsible implementation of AI in high-stakes consumer finance.
arXiv:2510.11539v5 Announce Type: replace
Abstract: Accurate state estimation is critical for legged and aerial robots operating in dynamic, uncertain environments. A key challenge lies in specifying process and measurement noise covariances, which are typically unknown or manually tuned. In this work, we introduce a bi-level optimization framework that jointly calibrates covariance matrices and kinematic parameters in an estimator-in-the-loop manner. The upper level treats noise covariances and model parameters as optimization variables, while the lower level executes a full-information estimator. Differentiating through the estimator allows direct optimization of trajectory-level objectives, resulting in accurate and consistent state estimates. We validate our approach on quadrupedal and humanoid robots, demonstrating significantly improved estimation accuracy and uncertainty calibration compared to hand-tuned baselines. Our method unifies state estimation, sensor, and kinematics calibration into a principled, data-driven framework applicable across diverse robotic platforms.
arXiv:2510.11600v3 Announce Type: replace
Abstract: We present a data-driven active flow control framework designed for deployment with few non-intrusive sensors. The method builds upon Artificial Intelligence driven reduced-order predictive models based on Long-Short-Term Memory (LSTM) networks and efficient gradient-based Model Predictive Control (MPC). The model uses only surface-mounted pressure probes to infer the wake state, and is trained entirely offline on a dataset built with open-loop actuations, thus avoiding the complexities of online learning. Sparsification of the sensors needed for control from an initially large set is achieved using SHapley Additive exPlanations (SHAP). A parsimonious set of sensors is then deployed in closed-loop control with MPC. The framework is tested in numerical simulations of a two-dimensional truck model at Reynolds number 500, with pulsed-jet actuators placed in the rear of the truck to control the wake. The resulting LSTM-MPC achieved a drag reduction of 12.8\%.
arXiv:2510.12229v3 Announce Type: replace
Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear. In this work, we investigated whether the well-known Knobe effect, a moral bias in intentionality judgements, emerges in finetuned LLMs and whether it can be traced back to specific components of the model. We conducted a Layer-Patching analysis across 3 open-weights LLMs and demonstrated that the bias is not only learned during finetuning but also localized in a specific set of layers. Surprisingly, we found that patching activations from the corresponding pretrained model into just a few critical layers is sufficient to eliminate the effect. Our findings offer new evidence that social biases in LLMs can be interpreted, localized, and mitigated through targeted interventions, without the need for model retraining.
arXiv:2510.19248v2 Announce Type: replace
Abstract: Clustering-based features are widely used in machine learning, but most methods must choose a resolution -- a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stable partitions, known as configurations. Based on this, we introduce Configuration-Mixed Prediction (CMP), a setting where models learn to adaptively weight these configurations per sample for downstream prediction. We propose MixConfig, a plug-and-play feature augmentation module that extracts configurations from any frozen embedding and learns energy-aware mixing weights via a novel selector that jointly reasons about sample context, cluster assignments, and stability statistics. Experiments across tabular, molecular, vision, and text domains demonstrate consistent improvements over single-resolution and static baselines across diverse predictor architectures, with gains particularly pronounced in low-data regimes.
arXiv:2510.21971v3 Announce Type: replace
Abstract: Inertial spheres settling through sharp density interfaces can arrest, reverse direction, and resume descent, a phenomenon known as bouncing. Using synchronized particle image velocimetry and tracking in water-salt and water-glycerol stratifications, we demonstrate that bouncing is the dynamic response of a coupled sphere-fluid composite. As the sphere crosses the interface, it entrains a boundary layer of lighter fluid, creating a transient buoyant wake.
We formalize this mechanism into a phenomenological dynamic model that couples the momentum of the sphere with the entrainment and detachment of the wake. Evaluating the stationary points of this system yields a criterion that classifies trajectory archetypes (smooth crossing, deep minima, and bouncing) across different fluid regimes. We identify a dual role of viscosity, which is often overlooked by density-only models: it acts kinematically to thicken the boundary layer and increase the entrained wake volume, and dynamically to alter the drag-to-weight balance.
Furthermore, we describe the spatial dynamics of the crossing: inertia-dominated spheres penetrate further into the lower fluid before arresting due to a longer wake-detachment length, whereas buoyancy-dominated spheres arrest closer to the interface. Finally, we show that the retention time is governed by the buoyancy-driven detachment of the entrained film. By normalizing the measured retention times with a characteristic detachment timescale, we collapse the data from different viscosity regimes onto a single curve. These physical insights allow the prediction of trajectory archetype, deceleration depth, and retention time from bulk properties.
arXiv:2607.15610v1 Announce Type: new
Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation. In long-horizon agentic tasks, such a uniform rollout strategy can waste budget on uninformative dead-end attempts, while promising intermediate states do not receive sufficient exploration. The multi-turn structure of agentic trajectories, with interleaved actions and observations, naturally supports organizing a trajectory group as a tree, where each turn serves as a decision point for exploration. This perspective reframes effective exploration as the problem of deciding where to branch. We propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL. PATR uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops degenerate paths to reduce wasted sampling. The resulting rollout groups remain compatible with standard policy optimization while providing more efficient exploration under the same training budget. We evaluate PATR on FrozenLake and the challenging SWE-Bench, which is largely unexplored by prior tree-rollout agent RL methods. Experiments show that PATR improves performance by up to +5.0 points on SWE-Bench and +9.3 points on FrozenLake, highlighting process-guided tree rollouts as an effective strategy for scalable multi-turn RL.
arXiv:2607.15972v1 Announce Type: new
Abstract: Accurate hand gesture recognition using surface electromyography (sEMG) typically relies on multichannel sensor arrays and computationally intensive models. This limits practical deployment in low-power and embedded systems. This study investigates the feasibility of classifying ten hand gestures using a single sEMG channel combined with lightweight machine learning architectures. Raw sEMG signals were transformed into a comprehensive feature-based representation, including time-domain, frequency-domain, higher-order-crossing, and relative-intensity features. Feature redundancy was reduced using Pearson correlation filtering and the removal of highly correlated features, while dimensionality-reduction techniques (LDA and PCA) were applied selectively. Three classifiers, a feed-forward neural network (NN), k-nearest neighbors (KNN), and a support vector machine (SVM), were systematically evaluated across four experiments. Results demonstrate that combining time and frequency features with Pearson filtering and a compact NN can achieve up to 90 percent accuracy, even with limited temporal and spatial information. These findings highlight the potential of single-channel sEMG systems for cost-effective, low-power gesture-recognition applications.
arXiv:2510.24819v2 Announce Type: replace
Abstract: Large Language Models (LLMs) are increasingly embedded in software systems ( GenAIware), enabling new forms of automation and interaction However, their probabilistic nature and reliance on prompt programming challenge reliability, robustness, and maintainability In current practice, prompt-related concerns (e.g., context management, interaction logic, output validation) are embedded in general-purpose code, leading to implicit, hard-to-analyze systems We argue that prompt programming should be treated as a first-class Software Engineering (SE ) concern and propose LLM Scripting Language (LSL ), a Domain Specific Language ( DSL) for structuring LLM interactions as analyzable programs LSL introduces abstractions for interaction blocks, context scopes, output constraints, and control flow, separating deterministic logic from probabilistic model behavior while ensuring syntactic compliance From an SE perspective, LSL supports disciplined development by making interaction logic explicit, analyzable, and amenable to verification and validation It also acts as cognitive scaffolding, externalizing prompt design into programmable artifacts that reduce implicit reasoning and support systematic debugging, evolution, and reuse We illustrate these properties in a structured generation scenario, showing improved failure localization and interaction transparency While LSL does not guarantee semantic correctness or factual accuracy, it provides a principled foundation for more analyzable and maintainable prompt-based systems.
Global Kilometer-Scale Simulations with ARP-GEM2: Effect of Parameterized Convection and Calibration
arXiv:2511.00829v2 Announce Type: replace
Abstract: The objective of this paper is twofold. First, it documents the second version of the global atmospheric model ARP-GEM and its calibration at kilometer-scale resolution. The model is currently able to run simulations at a resolution of up to 1.3 km. Second, this paper focus on multi-year global atmospheric simulations at a 2.6 km resolution with and without parameterized convection and associated calibration. Simulations without deep convection tend to be similar to those with infinite, or at least large, entrainment values. Consistently, entrainment and detrainment are used as primary drivers for the gradual reduction of convection as resolution increases. The results indicate that, with this hydrostatic model, parameterized convection still plays a significant role in the correct representation of the mean state at the kilometer scale. Additionally, they suggest some added value of high resolution in representing climate variability. However, a compromise between the adequate representation of the mean state and variability is necessary, as both are differently favored by the degree of parameterized convection. Finally, it is likely that even higher resolutions are necessary to achieve an unequivocal added value.
arXiv:2511.12974v3 Announce Type: replace
Abstract: We introduce Controlled Stochastic Activity Networks (Controlled SANs), a formal extension of classical Stochastic Activity Networks that integrates explicit control actions into a unified semantic framework for modeling distributed real-time systems. Controlled SANs systematically capture dynamic behavior involving nondeterminism, probabilistic branching, and stochastic timing, while enabling policy-driven decision-making within a rigorous mathematical framework.
We develop a hierarchical, automata-theoretic semantics for Controlled SANs that encompasses nondeterministic, probabilistic, and stochastic models in a uniform manner. A structured taxonomy of control policies, ranging from memoryless and finite-memory strategies to computationally augmented policies, is formalized, and their expressive power is characterized through associated language classes. To support model abstraction and compositional reasoning, we introduce behavioral equivalences, including bisimulation and stochastic isomorphism.
Controlled SANs generalize classical frameworks such as continuous-time Markov decision processes (CTMDPs), providing a rigorous foundation for the specification, verification, and synthesis of dependable systems operating under uncertainty. This framework enables both quantitative and qualitative analysis, advancing the design of safety-critical systems where control, timing, and stochasticity are tightly coupled.
arXiv:2511.14159v4 Announce Type: replace
Abstract: Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, existing robustness benchmarks typically focus on hallucination or misleading textual inputs, while largely overlooking the equally critical challenge posed by misleading visual inputs in assessing visual understanding. To fill this important gap, we introduce MVI-Bench, the first comprehensive benchmark specially designed for evaluating how Misleading Visual Inputs undermine the robustness of LVLMs. Grounded in fundamental visual primitives, the design of MVI-Bench centers on three hierarchical levels of misleading visual inputs: Visual Concept, Visual Attribute, and Visual Relationship. Using this taxonomy, we curate six representative categories and compile 1,248 expertly annotated VQA instances. To facilitate fine-grained robustness evaluation, we further introduce MVI-Sensitivity, a novel metric that characterizes LVLM robustness at a granular level. Empirical results across 18 state-of-the-art LVLMs uncover pronounced vulnerabilities to misleading visual inputs, and our in-depth analyses on MVI-Bench provide actionable insights that can guide the development of more reliable and robust LVLMs. The benchmark and codebase can be accessed at https://github.com/chenyil6/MVI-Bench.
arXiv:2511.18468v2 Announce Type: replace
Abstract: Continual Test-Time Adaptation (CTTA) is crucial for deploying models in real-world applications with unseen, evolving target domains. Existing CTTA methods, however, often rely on source data or prototypes, limiting their applicability in privacy-sensitive and resource-constrained settings. Although several methods attempt to mitigate catastrophic forgetting, they often fail to preserve long-term domain-specific knowledge across many domain shifts. Moreover, their relatively slow adaptation rates during domain transitions can cause error accumulation, allowing mistakes to propagate before effective adaptation occurs. To address these challenges, we propose SloMo-Fast, a source-free, dual-teacher CTTA framework designed for enhanced quick adaptability and generalization. It includes two complementary teachers: the Slow-Teacher, which exhibits slow forgetting and retains long-term knowledge of previously encountered domains to ensure robust generalization, and the Fast-Teacher rapidly adapts to new domains while accumulating and integrating knowledge across them. This framework preserves knowledge of past domains and adapts efficiently to new ones. Our extensive experiments show that SloMo-Fast consistently outperforms state-of-the-art methods across Cyclic Test-Time Adaptation (Cyclic-TTA), a CTTA benchmark that simulates recurring domain shifts, along with ten other CTTA settings, highlighting its ability to both adapt and generalize across evolving, revisited domains.
arXiv:2511.20332v3 Announce Type: replace
Abstract: This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinearity to describe a local problem. Multilayer networks gradually transform the raw representation to the desired representation through multiple such combinations. Analysed some reference principles for designing neural networks. Designed a relatively small PID convolutional neural network, with a total of 17 layers and 413 thousand parameters. Implemented a simple but practical feature reuse method by concatenation and pooling. The network was trained and tested using the simulated randomly moving ball datasets, and the experimental results showed that the prediction accuracy was close to the upper limit that the input image resolution can represent. Analysed the experimental results and errors, as well as the existing shortcomings and possible directions for improvement. Finally, discussed the advantages of high-dimensional convolution in improving computational efficiency and feature space utilization. As well as the potential advantages of using PID information to implement memory and attention mechanisms.
arXiv:2511.20687v4 Announce Type: replace
Abstract: This paper presents a novel hybrid approach for coupling subdomain-local non-intrusive Operator Inference (OpInf) reduced order models (ROMs) with each other and with subdomain-local high-fidelity full order models (FOMs) with using the overlapping Schwarz alternating method (O-SAM). The proposed methodology addresses significant challenges in multiscale modeling and simulation, particularly the long runtime and complex mesh generation requirements associated with traditional high-fidelity simulations. By leveraging the flexibility of O-SAM, we enable the seamless integration of disparate models, meshes, and time integration schemes, enhancing computational efficiency while maintaining high accuracy. Our approach is demonstrated through a series of numerical experiments on complex three-dimensional (3D) solid dynamics problems, showcasing speedups of up to 106x compared to conventional FOM-FOM couplings. This work paves the way for more efficient simulation workflows in engineering applications, with potential extensions to a wide range of partial differential equations.
arXiv:2511.23213v3 Announce Type: replace
Abstract: Targeted execution of Android applications (apps) remains a longstanding challenge for software testing and analysis. Although recent advances in GUI testing have substantially improved app exploration, existing approaches remain largely coverage-driven and struggle to steer execution reliably toward specific methods of interest. This limitation hinders important downstream tasks, such as vulnerability detection, program comprehension, and dynamic analysis.
We present GAPS (Graph-based Automated Path Synthesizer), the first approach to bridge static program analysis and dynamic GUI exploration, enabling targeted execution in Android apps. Given a target method, GAPS performs a lightweight static backward traversal of the call graph, enriched with data-flow reasoning, to identify feasible execution paths that lead to the target. It then translates these paths into actionable execution strategies that guide dynamic interactions with the app.
We evaluate GAPS on the AndroTest benchmark and show that it reconstructs paths toward 88.24% of the target methods, requiring only 12.67 seconds per app on average. During dynamic execution, GAPS reaches 56.93% of the target methods, outperforming state-of-the-art alternatives. In comparison, the model-based GUI testing tool APE reaches only 11.12%, the hybrid exploration framework GoalExplorer reaches 4.75%, and the recent LLM-driven approach Guardian reaches 34%. To assess scalability in real-world settings, we further evaluate GAPS across the 50 most-downloaded apps on the Google Play Store. GAPS reconstructs execution paths toward 62.03% of the target methods, averaging 278.9 seconds per app, and dynamically reaches 54.80% of them. These results show that combining static path synthesis with guided dynamic exploration provides an effective and scalable solution for targeted method execution in Android apps.
arXiv:2512.02384v3 Announce Type: replace
Abstract: Markov chain Monte Carlo algorithms have long been observed to obtain near-optimal performance in various Bayesian inference settings. However, developing a supporting theory that makes these studies rigorous has proved challenging.
In this paper, we study the classical spiked Wigner inference problem, where one aims to recover a planted Boolean spike from a noisy matrix measurement. We relate the recovery performance of Glauber dynamics on the annealed posterior to the performance of Approximate Message Passing (AMP), which is known to achieve Bayes-optimal performance. Our main results rely on the analysis of an auxiliary Markov chain called restricted Gaussian dynamics (RGD). Concretely, we establish the following results:
1. RGD can be reduced to an effective one-dimensional recursion which mirrors the evolution of the AMP iterates.
2. From a warm start, RGD rapidly converges to a fixed point in correlation space, which recovers Bayes-optimal performance when run on the posterior.
3. Conditioned on widely believed mixing results for the SK model, we recover the phase transition for non-trivial inference.
arXiv:2512.02851v4 Announce Type: replace
Abstract: Visual traversability estimation is central to autonomous navigation, yet most approaches either rely on prompt-driven Vision-Language Model (VLM) or decouple traversability from trajectory planning, requiring separate planners with heavy mapping, manual tuning, and extended deployment time. We propose EmbodiedDiffusion, a diffusion-based framework that simultaneously predicts traversability maps and generates feasible trajectories from RGB images using planner-free synthetic supervision and embodiment conditioning for cross-platform transfer. The framework distills category-level traversability semantics from a VLM teacher into a lightweight student model during training, enabling prompt-free, real-time inference at deployment. A modular FiLM-based conditioning mechanism isolates embodiment-specific reasoning into a compact trainable subset of the network, allowing rapid adaptation to new robot platforms without retraining the visual backbone or the trajectory diffusion model. Across indoor environments with quadruped and aerial robots, EmbodiedDiffusion achieves 80-100% navigation success in the full-data regime with real-time inference (90 ms) and adapts to new platforms using only 10 min of visual data collection, demonstrating scalable, unified traversability reasoning and trajectory generation for heterogeneous robots.
arXiv:2607.16078v1 Announce Type: new
Abstract: The Stackelberg Vertex Cover problem is a bilevel optimization problem with two players on a graph $G = (F \cup P, E)$ where each vertex from $F$ has a weight and the first player selects a price for each vertex in $P$. Afterwards, the second player finds a minimum vertex cover $X$ and the first player receives the set price for each vertex from $X \cap P$. The goal is to maximize the revenue of the first player.
This problem was recently shown to be NP-complete for bipartite graphs while being solvable in linear time on paths. We present three new algorithms for solving Stackelberg Vertex Cover on certain kinds of trees: (1) a pseudo-polynomial algorithm working on general trees when all weights are integer, i.e., it is FPT with the maximum weight as a parameter; (2) a strongly polynomial algorithm for trees having the property that the least common ancestor of any two vertices from $P$ is again in $P$ (this case includes paths); and (3) an FPT-algorithm for trees, where the parameter is the maximum number $P$-vertices $v_i$ that an $F$-vertex $u$ can reach while using no other $P$-vertices.
These algorithms are based on a lemma that allows us to split instances at a vertex $u$ into multiple sub-instances, which follows from LP duality and integrality of the vertex cover LP on bipartite graphs. The lemma requires that the minimum vertex covers of the sub-instances agree on $u$ (either all include $u$ or all don't). For this we introduce the concept of commitments. Finally, we show that the Stackelberg Vertex Cover problem with commitments is weakly NP-complete.
arXiv:2607.16083v1 Announce Type: new
Abstract: The growing adoption of Large Language Models in scientific research has created a need to understand what competencies researchers and graduate students require to use these tools critically and responsibly. This rapid review analyzed 194 articles retrieved from Elicit and Google Scholar (2022 to 2025), from which 40 were selected for competency extraction and thematic analysis following independent dual screening (Gwet AC1: 0.76 to 0.83). Eight competencies were identified. The most prevalent was domain expertise and oversight of AI outputs (n = 123), encompassing subject matter mastery, systematic skepticism, source verification, and researcher accountability. Other key competencies include metacognition and decision making about AI use (n = 55), ethics and academic integrity (n = 53), prompt engineering for research (n = 38), and reproducibility of AI use (n = 29). AI literacy and technical knowledge (n = 16) was explicitly identified as a risk factor when absent, with domain expertise treated as a prerequisite for meaningful critical evaluation. The findings suggest that preparing researchers to use LLMs goes beyond technical instruction, requiring an integrated set of epistemic, ethical, and methodological competencies centered on human accountability for the knowledge produced. These results have direct implications for the design of graduate programs and AI literacy initiatives.
arXiv:2607.16084v1 Announce Type: new
Abstract: This paper illustrates the Pick-to-Learn methodology applied to the calibration of a Model Predictive Control policy. While developed around a specific example, the presentation is meant to highlight a methodology of broad applicability. The example concerns an aircraft traveling from an origin point to a destination point in the presence of uncertain crosswinds and a low-connectivity zone that should be avoided. The MPC policy is parameterized by two hyperparameters, which are selected from data by the P2L procedure. Starting from a dataset of 400 wind realizations, also called scenarios, P2L identifies a final compression set containing only two informative scenarios. The resulting MPC policy avoids the low-connectivity zone on all available scenarios and, according to the P2L theory, satisfies a probabilistic risk bound of $4.8\%$ at confidence level $1-10^{-5}$, where the risk is the probability of entering the low-connectivity zone in a future flight under a new wind realization not included in the sample.
arXiv:2512.03054v3 Announce Type: replace
Abstract: Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions to collaboratively train deep learning (DL) models, even with limited data. However, the significant resource requirements of FL often exclude centres with limited computational infrastructure, further widening existing healthcare disparities. To address this issue, we propose a Green AI-oriented adaptive layer-freezing strategy designed to reduce energy consumption and computational load while maintaining model performance. We tested our approach using different federated architectures for Magnetic Resonance Imaging (MRI)-to-Computed Tomography (CT) conversion. The proposed adaptive strategy optimises the federated training by selectively freezing the encoder weights based on the monitored relative difference of the encoder weights from round to round. A patience-based mechanism ensures that freezing only occurs when updates remain consistently minimal. The energy consumption and CO2eq emissions of the federation were tracked using the CodeCarbon library. Compared to equivalent non-frozen counterparts, our approach reduced training time, total energy consumption and CO2eq emissions by up to 23%. At the same time, the MRI-to-CT conversion performance was maintained, with only small variations in the Mean Absolute Error (MAE). Notably, for three out of the five evaluated architectures, no statistically significant differences were observed, while two architectures exhibited statistically significant improvements. Our work aligns with a research paradigm that promotes DL-based frameworks meeting clinical requirements while ensuring climatic, social, and economic sustainability. It lays the groundwork for novel FL evaluation frameworks, advancing privacy, equity and, more broadly, justice in AI-driven healthcare.