Spacecraft pose estimation is crucial for autonomous in-space operations, such as rendezvous, docking and on-orbit servicing. Vision-based pose estimation methods, which typically employ RGB imaging sensors, is a compelling solution for spacecraft pose estimation, but are challenged by harsh lighting conditions, which produce imaging artifacts such as glare, over-exposure, blooming and lens flare. Due to their much higher dynamic range, neuromorphic or event sensors are more resilient to extreme lighting conditions. However, event sensors generally have lower spatial resolution and suffer from reduced signal-to-noise ratio during periods of low relative motion. A beam-splitter prism was employed to achieve precise optical and temporal alignment. Then, a RANSAC-based technique was developed to fuse the information from the RGB and event channels to achieve pose estimation that leveraged the strengths of the two modalities. The pipeline was complemented by dropout uncertainty estimation to detect extreme conditions that affect either channel. To benchmark the performance of the proposed event-RGB fusion method, we collected a comprehensive real dataset of RGB and event data for satellite pose estimation in a laboratory setting under a variety of challenging illumination conditions. Encouraging results on the dataset demonstrate the efficacy of our event-RGB fusion approach and further supports the usage of event sensors for spacecraft pose estimation. To support community research on this topic, our dataset has been released publicly. Keywords: event-based pose estimation, rendezvous, domain gap, sensor fusion, close proximity, harsh lighting1. Introduction Spacecraft pose estimation is the problem of determining the 6-degrees-of-freedom (6DoF) pose consisting of the position and orientation of a space-borne object, typically a satellite. It is a critical step in a wide range of space applications, including rendezvous, close proximity operations, debris removal, refueling and on-orbit servicing [1, 2, 3, 4]. Robust pose estimation is paramount to safely and effectively executing these tasks [5, 6]. Several types of sensor technologies can be employed for spacecraft pose estimation, but they are all subject to size-weight-power and cost (SWaP-C) constraints. Optical sensors such as RGB imaging sensors are favored due to their low SWaP-C requirements, high resolution and the availability of established vision-based algorithms. However, operating in the space environment can present nontrivial challenges to vision-based systems.

Autonomous driving systems have made significant advances in Q&A, perception, prediction, and planning based on local visual information, yet they struggle to incorporate broader navigational context that human drivers routinely utilize. We address this critical gap between local sensor data and global navigation information by proposing NavigScene, an auxiliary navigation-guided natural language dataset that simulates a human-like driving environment within autonomous driving systems. Moreover, we develop three complementary paradigms to leverage NavigScene: (1) Navigation-guided Reasoning, which enhances vision-language models by incorporating navigation context into the prompting approach; (2) Navigation-guided Preference Optimization, a reinforcement learning method that extends Direct Preference Optimization to improve vision-language model responses by establishing preferences for navigation-relevant summarized information; and (3) Navigation-guided Vision-Language-Action model, which integrates navigation guidance and vision-language models with conventional driving models through feature fusion. Extensive experiments demonstrate that our approaches significantly improve performance across perception, prediction, planning, and question-answering tasks by enabling reasoning capabilities beyond visual range and improving generalization to diverse driving scenarios. This work represents a significant step toward more comprehensive autonomous driving systems capable of navigating complex, unfamiliar environments with greater reliability and safety.

Forecasting electricity demand is increasingly challenging as energy systems become more decentralized and intertwined with renewable sources. Graph Neural Networks (GNNs) have recently emerged as a powerful paradigm to model spatial dependencies in load data while accommodating complex non-stationarities. This paper introduces a comprehensive framework that integrates graph-based forecasting with attention mechanisms and ensemble aggregation strategies to enhance both predictive accuracy and interpretability. Several GNN architectures -- including Graph Convolutional Networks, GraphSAGE, APPNP, and Graph Attention Networks -- are systematically evaluated on synthetic, regional (France), and fine-grained (UK) datasets. Empirical results demonstrate that graph-aware models consistently outperform conventional baselines such as Feed Forward Neural Networks and foundation models like TiREX. Furthermore, attention layers provide valuable insights into evolving spatial interactions driven by meteorological and seasonal dynamics. Ensemble aggregation, particularly through bottom-up expert combination, further improves robustness under heterogeneous data conditions. Overall, the study highlights the complementarity between structural modeling, interpretability, and robustness, and discusses the trade-offs between accuracy, model complexity, and transparency in graph-based electricity load forecasting.

Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human oversight" risk codifying vague or inconsistent interpretations of key concepts like oversight and control. This ambiguous terminology could undermine efforts to design or evaluate systems that must operate under meaningful human supervision. This matters because the term is used by regulatory texts such as the EU AI Act. This paper undertakes a targeted critical review of literature on supervision outside of AI, along with a brief summary of past work on the topic related to AI. We next differentiate control as ex-ante or real-time and operational rather than policy or governance, and oversight as performed ex-post, or a policy and governance function. Control aims to prevent failures, while oversight focuses on detection, remediation, or incentives for future prevention. Building on this, we make three contributions. 1) We propose a framework to align regulatory expectations with what is technically and organizationally plausible, articulating the conditions under which each mechanism is possible, where they fall short, and what is required to make them meaningful in practice. 2) We outline how supervision methods should be documented and integrated into risk management, and drawing on the Microsoft Responsible AI Maturity Model, we outline a maturity model for AI supervision. 3) We explicitly highlight boundaries of these mechanisms, including where they apply, where they fail, and where it is clear that no existing methods suffice. This foregrounds the question of whether meaningful supervision is possible in a given deployment context, and can support regulators, auditors, and practitioners in identifying both present and future limitations.

Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and leveraging HOIs remains a significant challenge. In this paper, we propose MvHo-IB, a novel multi-view learning framework that seamlessly integrates pairwise interactions and HOIs for diagnostic decision-making while automatically compressing task-irrelevant redundant information. Our approach introduces several key innovations: (1) a principled framework combining O -information from information theory with the recently developed matrix-based Rényi's α - order entropy functional estimator to quantify and extract HOIs, (2) a purpose-built Brain3DCNN encoder designed to effectively utilize these interactions, and (3) a novel multiview learning information bottleneck objective to enhance representation learning. Experiments on three benchmark fMRI datasets demonstrate that MvHo-IB achieves state-of-the-art performance, outperforming existing methods, including modern hypergraph-based techniques, by significant margins. The code of our MvHo-IB is available at https://github.com/zky04/MvHo-IB .

The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection methods often struggle with generalization and capturing subtle temporal inconsistencies. We propose ReStraV(Representation Straightening Video), a novel approach to distinguish natural from AI-generated videos. Inspired by the "perceptual straightening" hypothesis -- which suggests real-world video trajectories become more straight in neural representation domain -- we analyze deviations from this expected geometric property. Using a pre-trained self-supervised vision transformer (DINOv2), we quantify the temporal curvature and stepwise distance in the model's representation domain. We aggregate statistics of these measures for each video and train a classifier. Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos. A lightweight classifier achieves state-of-the-art detection performance (e.g., 97.17% accuracy and 98.63% AUROC on the VidProM benchmark), substantially outperforming existing image- and video-based methods. ReStraV is computationally efficient, it is offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection.

Contrastive Language-Image Pre-training (CLIP) models have demonstrated superior performance across various visual tasks including medical image classification. However, fairness concerns, including demographic biases, have received limited attention for CLIP models. This oversight leads to critical issues, particularly those related to race and gender, resulting in disparities in diagnostic outcomes and reduced reliability for underrepresented groups. To address these challenges, we introduce AdFair-CLIP, a novel framework employing adversarial feature intervention to suppress sensitive attributes, thereby mitigating spurious correlations and improving prediction fairness. We conduct comprehensive experiments on chest X-ray (CXR) datasets, and show that AdFair-CLIP significantly enhances both fairness and diagnostic accuracy, while maintaining robust generalization in zero-shot and few-shot scenarios. These results establish new benchmarks for fairness-aware learning in CLIP-based medical diagnostic models, particularly for CXR analysis.

The Internet of Things (IoT) plays a major role today in smart building infrastructures, from simple smart-home applications, to more sophisticated industrial type installations. The vast amounts of data generated from relevant systems can be processed in different ways revealing important information. This is especially true in the era of edge computing, when advanced data analysis and decision-making is gradually moving to the edge of the network where devices are generally characterised by low computing resources. In this context, one of the emerging main challenges is related to maintaining data analysis accuracy even with less data that can be efficiently handled by low resource devices. The present work focuses on correlation analysis of data retrieved from a pilot IoT network installation monitoring a small smart office by means of environmental and energy consumption sensors. The research motivation was to find statistical correlation between the monitoring variables that will allow the use of machine learning (ML) prediction algorithms for energy consumption reducing input parameters. For this to happen, a series of hypothesis tests for the correlation of three different environmental variables with the energy consumption were carried out. A total of ninety tests were performed, thirty for each pair of variables. In these tests, p-values showed the existence of strong or semi-strong correlation with two environmental variables, and of a weak correlation with a third one. Using the proposed methodology, we manage without examining the entire data set to exclude weak correlated variables while keeping the same score of accuracy.

Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate modifications to prompting and sampling strategies. In this work, we introduce representation consistency (RC), a test-time scaling method for aggregating answers drawn from multiple candidate responses of an LLM regardless of how they were generated, including variations in prompt phrasing and sampling strategy. RC enhances answer aggregation by not only considering the number of occurrences of each answer in the candidate response set, but also the consistency of the model's internal activations while generating the set of responses leading to each answer. These activations can be either dense (raw model activations) or sparse (encoded via pretrained sparse autoencoders). Our rationale is that if the model's representations of multiple responses converging on the same answer are highly variable, this answer is more likely to be the result of incoherent reasoning and should be down-weighted during aggregation. Importantly, our method only uses cached activations and lightweight similarity computations and requires no additional model queries. Through experiments with four open-source LLMs and four reasoning datasets, we validate the effectiveness of RC for improving task performance during inference, with consistent accuracy improvements (up to 4%) over strong test-time scaling baselines. We also show that consistency in the sparse activation signals aligns well with the common notion of coherent reasoning.

Large language models (LLMs) are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-off: They can send private records, many of which are stored in remote databases, to powerful but untrusted LLM providers, increasing their exposure risk. Alternatively, they can run less powerful models locally on trusted devices. We bridge this gap. Our Socratic Chain-of-Thought Reasoning first sends a generic, non-private user query to a powerful, untrusted LLM, which generates a Chain-of-Thought (CoT) prompt and detailed sub-queries without accessing user data. Next, we embed these sub-queries and perform encrypted sub-second semantic search using our Homomorphically Encrypted Vector Database across one million entries of a single user's private data. This represents a realistic scale of personal documents, emails, and records accumulated over years of digital activity. Finally, we feed the CoT prompt and the decrypted records to a local language model and generate the final response. On the LoCoMo long-context QA benchmark, our hybrid framework, combining GPT-4o with a local Llama-3.2-1B model, outperforms using GPT-4o alone by up to 7.1 percentage points. This demonstrates a first step toward systems where tasks are decomposed and split between untrusted strong LLMs and weak local ones, preserving user privacy.