Papers

Planning a large data center is difficult because a facility big enough to matter changes the electricity prices it will pay. Those prices are set by market clearing, a constrained optimization problem solved anew in every operating condition. However, simulating the market tells a planner how a candidate plan performs but not how to improve it. Here we treat market clearing as a differentiable optimization layer: each forward pass solves the market, and reverse-mode automatic differentiation propagates the planning cost back through the cleared prices to the plan. After validating these gradients against finite differences, we apply them to a concrete problem: allocating 50 MW of data-center load across six candidate buses in two synthetic networks, under a fixed cost per active site, evaluated over 36 operating states. Judged against exhaustive enumeration of all site combinations, gradient optimization recovers the continuous allocations almost exactly, with worst-case objective gaps of 2.3% and 8.5% of the cost difference between the best and worst single site. Its one systematic error is instructive: near the costs at which a site should close, the smooth relaxation of the discrete site count shrinks the site rather than closing it, so discrete transitions arrive late. Differentiable market clearing thus turns market-aware planning into a problem gradients can search.

Face recognition in unconstrained environments remains highly challenging due to diverse and extreme variations encountered in real-world scenarios. To mitigate these effects, existing margin-based approaches model sample quality through feature magnitude. However, magnitude-based modeling alone is susceptible to identity-agnostic noise, which can degrade the reliability and discriminative power of learned representations. In this paper, we propose Dual Quality Margin Learning for Face Recognition (DQM-Face), a novel framework that enables refined attraction and repulsion dynamics during representation learning. Our approach unifies conventional magnitude-based quality estimation with a newly introduced semantic quality learning mechanism, realized via squeeze-and-excitation semantic attention. By jointly leveraging magnitude and semantic cues, we construct enhanced quality-aware margins that adaptively strengthen intra-class compactness through improved attraction during learning. To further enhance inter-class discrimination, we introduce a repulsion margin formulation that explicitly enlarges inter-class separation. The unified integration of semantic quality modeling with dual attraction-repulsion margin optimization results in a more structured and discriminative feature geometry. Extensive experiments on multiple challenging benchmarks demonstrate that DQM-Face consistently outperforms state-of-the-art face recognition methods. Moreover, we show that the quality learned for margin optimization is highly effective for face image quality assessment within the proposed framework, demonstrating that the learned quality signal is intrinsically aligned with the recognition objective. The code is publicly available: https://github.com/RAIB-group/DQM-Face

The rapid advancement of generative models has significantly worsened the problem of manipulated image detection, as these methods are capable of producing highly realistic forgeries, reinforcing the importance of multimedia forensics. Conventional approaches typically frame image manipulation detection as a binary classification task (real vs. generated), which limits the capability to distinguish and localize different forms of manipulation. To address these constraints, this work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered). In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions. The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task. Find the code at https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images.

Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT), yet its performance is highly sensitive to initialization due to the information bottleneck imposed by low-rank decomposition. Existing approaches attempt to construct high-quality LoRA initializations by exploiting principal components of pretrained weights, activations, or gradients. However, these methods do not directly account for the training dynamics of the full-rank model. In this paper, we propose Training-aware Low-Rank Adaptation Initialization (TaRA), a method that initializes LoRA such that the gradients induced by the low-rank factors closely approximate the gradient of the corresponding full-rank weight matrix. Derived from a mathematical formulation, TaRA improves gradient fidelity at the start of training while introducing negligible computational overhead. Across diverse and challenging fine-tuning tasks, TaRA consistently outperforms prior state-of-the-art methods, establishing a simple, robust, and scalable solution for effective LoRA initialization.

Knowledge graphs have become an important source of structured knowledge for Web applications, including search, question answering, and recommender systems. In these applications, link prediction can serve either as a prediction task itself or as a means to enrich incomplete knowledge graphs for downstream tasks. Interestingly, different link prediction models, or even different training runs of the same model, can produce substantially different predictions for the same query. This suggests a variability in the capture of the underlying knowledge by models, thus raising a fundamental question: to what extent do different models capture complementary knowledge, and how much of this knowledge could be recovered by combining them? We propose to measure model complementarity through the performance of an oracle that, for each query, selects the best prediction among a considered set of models, hence providing an upper bound on the performance achievable through model combination. Across several architectures and benchmarks, we find a substantial gap between individual models and their oracle, revealing that different models capture complementary knowledge. Yet, this complementarity rapidly saturates as more models are added, leaving a persistent subset of queries unsolved even by a large number of models. These findings reveal both the potential of model complementarity and a fundamental limit to what current link prediction models can collectively recover; thereby highlighting the need for further research to build robust Web applications.

The purpose of this contribution is to analyze a hierarchical cell structure with a hot spot embedded in a WCDMA macrocellular system. Particular attention is paid to the impact of introducing smart antennas in this context. A system-level simulation approach is employed, in which we consider two main solutions to address hot-spot traffic: the placement of a microcell antenna or the adoption of smart antenna technology at the macrocell. Relative gains in signal-to-interference ratio (SIR) are then evaluated. Distinct scenarios are defined based on the proportion of users of different service classes. An evaluation of which solution is best suited to each scenario is then conducted.

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder. To better characterise the latent space during action diffusion, we introduce a cross-attention-based embedding-weighting method that amplifies relevant features while suppressing less informative ones. Quantitative evaluation shows that weighted clustering consistently outperforms the baseline. To improve interpretability, we extract human-interpretable concepts for each cluster, linking latent representations to semantic descriptions. Our analysis shows that latent clusters progressively disentangle spatiotemporal and kinematic features, with representations becoming more refined in the middle layers and stabilising toward the output. As such, LAVLA advances the interpretability of language-driven robotic systems.

Conventional designs for model predictive control typically rely on terminal costs and constraints derived from a steady state to guarantee closed-loop stability and performance. However, this dependence on a steady-state assumption limits the applicability of this control method to systems in which such a fixed operating point is either not available or not desirable. This work introduces a novel framework, termed policy-guided MPC, to address this limitation. Our approach constructs terminal costs and constraints using a known sub-optimal control policy. Specifically, the terminal region is defined around a center determined by a rollout of the policy, and a penalty on deviation from this center is used to define the terminal cost. This method obviates the need for a steady state or reference trajectory. Closed-loop performance guarantees are established relative to the guiding policy, for both finite and infinite horizon problems. The effectiveness of the proposed framework is demonstrated through numerical simulations on an energy management example.

Network Slicing (NS) is a fundamental pillar of 5G and beyond networks, enabling the provisioning of isolated, logical networks tailored to specific Quality of Service (QoS) requirements. While 3GPP standards comprehensively define slicing architectures over cellular access networks, the seamless integration of Non-3GPP technologies such as Wi-Fi into a unified slice instance remains an active area of investigation, particularly regarding empirical validation. This paper presents an end-to-end prototyping study that integrates 5G Standalone (SA) and Wi-Fi networks by adapting the Trusted Non-3GPP Gateway Function (TNGF) to extend NS to WLAN networks, enabling the unified management of Wi-Fi transmission resources. We implement a functional testbed leveraging an open-source 5G Core and an explicit Non-3GPP access to validate multi-Radio Access Technology (multi-RAT) slice operation. Our empirical results showcase the dynamic viability of multi-RAT slicing under varying bandwidth allocations and traffic steering policies, providing a concrete proof of concept for unified 3GPP and Non-3GPP service delivery.

Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models (LLMs) to automatically inject vulnerabilities into Solidity smart contracts, and demonstrate it in a case study targeting 49 vulnerability types from OpenSCV. Injected contracts are validated through a multi-step pipeline checking compilation, execution, business logic, and the presence of the intended vulnerability. Applied to real-world contracts from SmartBugs, LLMs generate nearly 1,000 candidate variants; after deduplication and validation, 32 confirmed vulnerable contracts spanning 25 vulnerability types survive (a 16.58% survival rate). Surviving contracts concentrate in structurally simpler targets and vulnerability types with localized syntactic patterns. We report practical challenges including LLMs' non-determinism and the difficulty of preserving contract semantics. We then use the validated contracts to assess three static analyzers, revealing complementary and incomplete coverage profiles. Results show that LLM-based vulnerability injection is feasible, while exposing key limitations in scalability and diversity.

Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system generates a new utterance that reflects a given direction relative to a reference utterance while preserving speaker identity and linguistic content. A key challenge is the lack of training data capturing such relative modifications. To address this, we propose a scalable pseudo-triplet construction pipeline that generates~(reference utterance, direction text, modified utterance) triplets. It generates controlled style variations using an impression-controllable TTS model and uses an LLM to produce natural language directions from estimated impression differences. Experimental results demonstrate that pseudo-triplets alone enable stable speaker-preserving modification, and that combining pseudo and recorded data further improves direction alignment while maintaining speaker similarity. Audio examples are available on our demo page https://ntt-hilab-gensp.github.io/IS2026pseudo/

Simulation-based science often requires a distribution over simulator parameters whose push-forward reproduces a set of real observations: this is the source distribution estimation (SDE) problem. Existing methods fit the source against a likelihood surrogate trained once from a fixed proposal prior. Their objective is therefore stated only in terms of the surrogate instead of the true simulator, which may fail for inaccurate areas in parameter space where the surrogate was never trained. We instead solve SDE by expectation maximization: an E-step trains an amortized posterior on fresh simulations from the current source estimate, and an M-step refits the source to the average of that posterior over the observed data. We give two parameterizations, (1) separate source and posterior flows and (2) a single shared conditional flow. We evaluate our method on three benchmark tasks under both broad and misspecified initial priors. Both improve on existing fixed surrogate approaches and on iterated variants of each, most clearly on Lotka–Volterra, where no baseline falls below 0.96 data-space C2ST while our methods reach 0.64-0.68 in three of four initial-prior settings.

Generative AI is changing how cultural artifacts are created and circulated, and with it our understanding of creativity itself. Researchers disagree about whether these tools enrich or impoverish culture, and we argue that much of that disagreement comes from conflating two distinct components of creativity: novelty, a property of single artifacts, and diversity, a property of populations. We argue further that creativity in the context of generative AI is best understood as a property of hybrid collectives, or populations of interacting people and algorithms, rather than of individuals. AI-assisted ideation reliably raises the novelty of individual output while narrowing diversity in the aggregate, but this is not an inevitable consequence of putting machines in the loop. Because humans and models search in complementary ways, mixed groups can outperform and out-diversify groups of either kind alone, and machine-discovered solutions can enter human culture and persist there. What decides the outcome is composition: which agents are present, in what proportion, and how they are connected. The question is no longer whether AI helps or harms creativity, but which mixtures let individual gains accumulate without eroding collective diversity.

Emotion-driven image editing aims to evoke a specified target emotion by modifying emotion-relevant visual cues in a source image, while preserving the overall composition and semantic-structural coherence of the original scene. Existing scene-level editors typically specify the target with a single emotion category and often learn visual transformations from operation-level text instructions. A category collapses a mixed affective endpoint into one dominant label, while language cannot precisely quantify how coexisting emotions should increase, decrease, or remain stable. We introduce AffectDelta, a source-aware editor that treats editing as a transition between eight-dimensional emotion distributions. A frozen Emotion Distribution Predictor estimates the source state, and the signed source-to-target difference encodes the direction and magnitude of the requested transition. Within AffectDelta, an internal transition encoder and a source-aware diffusion backbone jointly translate this signal into context-dependent semantic and appearance changes. To train this formulation, we construct AffectPair-249K, comprising 248,841 source-target pairs with predicted eight-dimensional distributions and spanning both cross-category and within-category transitions. Experiments against six baselines, combining quantitative evaluation with qualitative comparisons, demonstrate improved affective alignment and content preservation, while ablations validate our design choices. Code and dataset will be made publicly available upon acceptance.

Intelligent Tutoring Systems (ITSs) traditionally focus their adaptive support on cognitive aspects of learning. Although effective, little is known about how such systems can be enhanced by addressing students' emotional states. In particular, the role of mindful interventions for supporting student learning and experiences in adaptive math learning remains underexplored. We developed "Math with Matt", an ITS that leverages Large Language Models (LLMs) to provide both cognitive and emotional support in algebra learning. The system offers 1) an LLM-based mindful chat that delivers context-sensitive emotional support through a pedagogical agent Matt, and 2) mindful feedback and hint messages (not just evaluative) to enhance learning experiences and reduce math anxiety. We conducted a classroom study with 7th graders, comparing a Mindful version against a version with cognitive support only. Overall, the ITS reduced executive state-math anxiety and improved students' math learning, though no significant differences emerged between the conditions. However, students with the mindfulness interventions showed higher learning efficiency and well-balanced problem-solving behavior, since they achieve a similar level of math learning with less learning time and fewer requested hints compared to the Cognitive version. Additionally, they reported that the pedagogical agent felt more supportive and caring than students in the cognitive condition. Our study demonstrates the feasibility and scalability of integrating mindfulness into ITSs through LLM-based interactions and positions LLMs as an adaptive, socio-emotional layer within cognitive math tutoring.

Loneliness is a critical public health issue among older adults, linked to higher risks of depression, cognitive decline, and mortality. Scalable, objective methods for its detection remain limited, particularly in natural conversational contexts. We analyzed speech and language markers of loneliness in 310 older adults using semi-structured telephone interviews to help understand how they process feeling lonely and how their language differs at different levels of feeling loneliness. Our multimodal framework combined linguistic features (psycholinguistic dictionaries, n-grams, and topic models) with acoustic features (pitch, tone, loudness) to examine associations with self-reported loneliness scores. Both predefined and data-driven methods captured patterns in verbal content and vocal delivery. Higher loneliness was associated with negations(r = 0.11), negative tone(r = 0.12), and conflict-related language. Lower loneliness was linked to social references(r = -0.18), motivational drives(r = -0.11), and emotional richness in speech(r = -0.12). We also found that the multimodal model (r = 0.298) outperforms the text-only and audio-only models. Findings suggest that loneliness manifests through both linguistic and acoustic cues, supporting the potential of speech-based analysis in psychological assessments and as an early indicator of emotional loneliness when used alongside existing assessments, rather than as standalone diagnostic tools.

The Mini-Girona Intervention Autonomous Underwater Vehicle (I-AUV) represents an advancement in accessible underwater robotics, designed to bridge the gap between costly, specialized research AUVs and basic Remotely Operated Vehicles (ROVs). Developed with a focus on affordability and usability, the Mini-Girona, priced at approximately $50,000, integrates advanced components such as a 5-DOF manipulator arm, stereo vision, and AI-driven processing for autonomous navigation and intervention tasks. This paper presents the design and development of the Mini-Girona, detailing its performance during the RAMI 2025 student competition. Despite challenges such as thermal management issues and restricted team access, the Mini-Girona achieved second place overall, excelling in vision-based perception and intervention tasks. This work highlights the platform's potential as a tool for underwater robotics research and education, fostering innovation in real-world underwater applications.

This work presents an approach to the Generalizability Across Tumors (BraTS-GoAT) task of the BraTS 2026 Challenge, which focuses on robust segmentation of brain tumor sub-regions across a heterogeneous patient population. The proposed method employs the nnU-Net framework with a large residual encoder architecture, integrating a semi-supervised learning technique with pseudo-labels generated from the unlabeled training data and a tumor-aware deformable augmentation that locally deforms the lesion while preserving the surrounding anatomy. We evaluate the individual contributions of each component, as well as their combination, using varying proportions of the most confident pseudo-labeled cases. The submitted configuration for the generalization task achieves Dice and NSD scores of 0.881 and 0.473 for Whole Tumor, 0.817 and 0.490 for Tumor Core, and 0.775 and 0.533 for Enhancing Tumor on the BraTS-GoAT validation set, improving over the labeled-only baselines across all tumor regions and confirming that self-training and the proposed augmentation are complementary. Our source code is publicly available at https://github.com/Henrique-zan/brats-goat-2026/.

We study the relationship between quasi-uniform spaces, topological spaces, and quantale-valued metric spaces. Our main result is a metrization theorem establishing an equivalence between the category of quasi-uniform spaces and a category of quantale-valued metric spaces. We also obtain a quantale-based metrization theorem for arbitrary topological spaces that refines existing constructions. These results identify quasi-uniformities as the appropriate qualitative counterpart of quantale-valued metrics. Building on this correspondence, we show that the Hausdorff-Smyth monad on quantale-valued metric spaces, which is used in quantitative robustness analysis, arises as a lifting of a corresponding monad on quasi-uniform spaces along the equivalence. This provides a unified categorical framework connecting topology, quasi-uniformity, and quantitative robustness analysis.

Much of agriculture depends on open-source software spanning farm management platforms, cloud services, edge gateways, embedded systems, and field-deployed sensors, forming a domain-specific software supply chain that has drawn little empirical security attention. It is unknown whether this ecosystem's supply chain security posture differs from that of comparable non-agricultural software, and if it does, whether the difference reflects the agricultural domain or the size and maturity of the projects within it. As a step towards securing agricultural open-source software, we present AgOSS, a dataset of 66 repositories across six architectural categories. We assess supply chain security within the dataset via OpenSSF Scorecard, governance metrics, SBOM-based dependency analysis, and KEV matching, and compare against matched non-agricultural controls. We report two findings. First, governance is largely independent of inherited dependency risk. Scorecard tracks community activity, but we detect no association with vulnerability count, density, or known-exploited count, and in regression the exposure signal loads on architectural category rather than domain. Second, agricultural projects score far lower on raw Scorecard, but size and maturity confound the gap: the residual loses significance under matching and regression. Securing this ecosystem means investing in contributor capacity and dependency hygiene, not agriculture-specific controls.

This paper investigates the stealthy attack detection for sensor-fusion cyber-physical systems with unknown-but-bounded noises through the control channel. The detection framework is particularly applicable to sensor-fusion scenarios in which multiple suspicious sensors contributing to the fused estimate may be compromised simultaneously. First, we construct an admissible output set using secure sensors and an attack output set for each attack hypothesis. Then, we introduce a receding-horizon optimization framework to design exposure inputs, namely bounded auxiliary control perturbations injected through the control channel, so as to enlarge the separation between the admissible output set and the attack output sets according to the separation tendency. A sufficient detection condition is further derived, showing that set separation guarantees detectability of the compromised sensors. Moreover, an offline exposure budget guidance is developed to support budget selection before online exposure starts. Simulations on a UAV navigation system under stealthy GNSS and LiDAR attacks validate the proposed method.

Although almost all graphs are asymmetric – having no nontrivial global automorphisms – they may still possess local symmetries in the form of isomorphisms between induced subgraphs, i.e., partial automorphisms. We study such local symmetries via asymmetric depth, defined in terms of the maximum rank of a nontrivial partial automorphism. We prove a tight upper bound on asymmetric depth in the class of planar graphs and identify the extremal graphs: duals of IPR fullerenes attain the maximum already on $47$ vertices. Our main structural result concerns the IPR fullerenes that are neither maximally asymmetric nor symmetric. In such a cage no purely local action realises a low asymmetric depth, and we show that the map which does realise it cannot be confined to a small part of the cage either: neither to a single face, nor behind an interface of at most $5-k$ edges, $k \le 3$ being the deficiency. A cage of asymmetric depth $2$ or $3$ is therefore not asymmetric in one place; it carries a broken symmetry invisible to its automorphism group. Such cages are rare – under $2\%$ of the asymmetric IPR fullerenes at $n = 118$. In all $727$ of them the largest partial automorphism is a near-mirror reflection, which we state as an explicit conjecture. We also extend the asymmetric depth bound to graphs of higher genus.

This paper studies the computational implementation of proper orthogonal decomposition reduced-order models (POD-ROMs) for evolutionary parametric time-dependent partial differential equations (PDEs). For a one-parameter model, many papers in the literature build the correlation matrix by projecting onto $L^2(\Omega)$ even though optimal pointwise error estimates are proved when projecting onto $H^1_0(\Omega)$. We compare both scenarios and observe the similar performance in practice. Additionally, to get the POD approximation it is necessary to compute the nonlinear term in the reduced equations. This requires a high computational cost that increases when the problem gets more complex. Numerical results in this paper show different approaches to address this issue. Discrete Empirical Interpolation Method (DEIM) is the most efficient approach. It reduces computational time by approximately half compared to computing the whole FEM formulation by a tensor construction while maintaining the same accuracy. For a multiparameter model, we analyze the new and standard method proposed in \cite{newmethod} using a two-dimensional Brusselator model to complement the results and support the error analysis with a more complex system.

Decoding visual perception from electroencephalography (EEG) is important for non-invasive brain-computer interfaces (BCIs). However, most existing visual decoding pipelines directly align EEG features with semantic features from pretrained vision models. Those EEG signals carry information at more than one level and this practice disregards the varying neural visibility of different visual components in EEG signals, leading to cross modal mismatches and incomplete information use. In this work, we address this limitation through layer-wise contrastive learning. For each subject, the intermediate CLIP layer that maximizes retrieval performance is selected as the Neural Visibility Optimal Layer (NVOL). Built on NVOL, a hierarchical framework couples retrieval and generation through a shared intermediate representation. The retrieval branch fuses multi-NVOL features, aligns them to image embeddings via contrastive learning, and applies cross-domain similarity local scaling (CSLS) at test time to mitigate hubness. The generation branch reconstructs subject-specific NVOL features from EEG using a conditional diffusion prior, maps them to CLIP space through a lightweight adapter, and drives a pretrained Stable Diffusion XL model. Experimental validation on THINGS-EEG showed that, NVOL-based retrieval achieves 78.1% mean Top-1 accuracy in 200-way retrieval, rising to 86.4% with CSLS. Two-stage NVOL-to-semantic reconstruction also outperforms single-stage final-layer diffusion on semantic and structural metrics. By aligning EEG with layer-wise neural visibility rather than fixed high-level semantics, the proposed framework improves both retrieval accuracy and image reconstruction in EEG-based visual decoding.

Large language models (LLMs) are increasingly deployed as economic agents, yet there is little evidence whether LLM agents are suited for participating in market mechanisms designed for humans, and whether these mechanisms deliver desired outcomes when faced with LLM agents. We address this question by replicating seminal economic experiments, replacing human subjects with LLM agents. We place agents in a double auction environment, which is a widely-used market mechanism. We check whether such a market is able to deliver an efficient allocation of resources, thereby testing a novel dimension of alignment of LLM agents – their compatibility with a fundamental market mechanism. We find that markets populated by LLM agents exhibit slower or no convergence towards market equilibrium, thus providing less efficient allocations than markets populated by humans. We then analyze agents' individual trading decisions and find substantial heterogeneity both across model families and market roles. We also run a lexical analysis of Chain-of-Thought (CoT) traces generated by the agents. We find that the decision to execute a trade rather than continue incrementally adjusting prices is associated with a shift from strategic considerations toward urgency. We publicly release our testing framework, which can be used for future evaluations.

The Boltzmann equation plays an important role in modeling mesoscopic behavior in a wide range of scientific and engineering applications. However, its numerical solution is computationally expensive due to the high dimensionality of the model and the nonlinear nonlocal collision operator, especially for steady-state problems that require iterative solvers. This cost becomes prohibitive for inverse problems, where the induced optimization problem requires repeated forward solves. In this work, we propose a reduced-order model (ROM) for the parametric Boltzmann equation to address this computational challenge. The ROM constructs a low-dimensional approximation space for the parameter-induced solution manifold through a residual-based greedy strategy, and the reduced solution is then obtained via residual minimization over the reduced space, subject to mass conservation. The overall efficiency of the ROM is achieved by exploiting the quadratic structure of the collision operator and a precomputed separable approximation of the collision kernel. The resulting ROM is further applied to a thermally-driven inverse problem for reconstructing collision parameters from the observed macroscopic temperature data. This is accomplished either by directly replacing the PDE constraint with the ROM, leading to a bilevel optimization formulation, or by reformulating the task as a single-level optimization problem through the Karush–Kuhn–Tucker (KKT) conditions. Numerical experiments in both collision-dominated and transport-dominated cases are performed to demonstrate the efficiency and accuracy of the proposed ROM and its effectiveness in inverse problems. In particular, the resulting inverse problem is computationally much more tractable, achieving speedups of several orders of magnitude over that based on the full-order model while maintaining comparable accuracy.

This paper investigates how a production transitional autonomous vehicle (tAV) develops and executes mandatory lane-change decisions. Using 150 controlled mandatory lane changes from the NC-tALC experiments, the study examines whether the eventual target gap is observable before lateral movement begins and how the tAV progresses longitudinally from that pre-lane-change state to lane-change start. Signal time (SigT) is defined as an operational pre-lane-change-start reference point. A Firth logistic regression predicts whether the tAV eventually merges in front of or behind its nearest target-lane vehicle using relative position and relative speed at SigT. Longitudinal progression from SigT to lane-change start is then examined separately for in-position and repositioning cases. The traffic state at SigT contains substantial information about eventual target-gap choice and provides meaningful lead time before lateral movement begins. The proposed formulation predicts whether the tAV remains with its current gap or repositions to a neighboring gap by moving forward or dropping back, including cases with longitudinal overlap and ambiguous current-gap geometry. The model achieves an average five-fold cross-validated accuracy of 0.89. Results also provide preliminary evidence that in-position and repositioning cases follow different longitudinal pathways from SigT to lane-change start. These findings support a two-stage conjecture of the observable lane-change process: longitudinal preparation from SigT to lane-change start, followed by lateral maneuver execution. The formulation applies to in-position, repositioning, and longitudinally overlapping cases, and can support lane-change models that distinguish target-gap choice from lateral-onset timing while representing longitudinal preparation before lateral movement begins.

Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, realworld applications like text-image co-creation, character tracking, and spatial reconstruction require constant interaction between text and images. Consequently, models must possess a deep understanding of these interleaved contexts. To bridge this gap, we introduce a novel benchmark, TIC-Bench (deeply interleaved Text-Image Contexts), designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts. This benchmark encompasses three core domains: Logical, Temporal, and Spatial Association, which are further categorized into eight specific types, comprising a total of 2,280 questions. We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts, together with persistent difficulties in integrating evidence distributed across interleaved visual and textual inputs. Ultimately, this benchmark provides a valuable analytical tool for assessing and advancing the ability of multimodal models to effectively integrate text and image information in deeply interleaved contexts. TIC-Bench is publicly available at https://huggingface.co/datasets/pino10010/TIC-Bench

Volumetric video based on point cloud representations enables immersive virtual and augmented reality applications but introduces significant challenges for efficient and secure content delivery. Prior work proposed a selective coordinate encryption framework for point clouds that encrypts only a subset of coordinates, reducing computational costs while visually degrading unauthorized content. However, it remains unclear whether the remaining unencrypted information is sufficient to enable content reconstruction. In this paper, we evaluate the robustness of selective coordinate encryption against machine learning-based reconstruction attacks. We consider an attacker with access to selectively encrypted point clouds attempting to recover encrypted coordinates without decryption by exploiting spatial and geometric correlations in the unencrypted data. We evaluate PointNet and Random Forest models under two encryption granularities: X, where all $X$ coordinates are encrypted, and 2X, where every second $X$ coordinate is encrypted. Our results show that reconstructing fully encrypted $X$ coordinates remains challenging, whereas the 2X scheme leaks sufficient information through neighboring coordinates to enable accurate reconstruction. These findings demonstrate that the security of selective coordinate encryption depends strongly on encryption granularity.

Machine-learnt corrections can complement numerical weather prediction provided that they operate stably within an evolving numerical model. In this study, we couple the Met Office (UKMO) Unified Model (UM) with distributed reinforcement-learning agents through rank-local tensors. A column-aware deep deterministic policy gradient (DDPG) actor uses local vertical structure together with full-column context to apply bounded corrections to potential temperature and horizontal wind. During training, we perform ten nudged 6-hr 12-min forecasts, with nudging towards the UKMO operational analysis providing an immediate counterfactual target from which the policy learns. The resulting actor is then frozen and applied to a non-nudged forecast without access to analysis inputs or further weight updates. Relative to a matched non-nudged native forecast at +6 h, the corrected forecast reduces global latitude-weighted MAE by 2.85% for $Z_{500}$, 2.16% for MSLP, 5.16% for $T_{500}$ and 2.27% for $T_{1.5\textrm{m}}$, with an observed 3.57% wall-time overhead compared to native execution. Even though training and inference share the same initialisation, this single-case experiment demonstrates significant promise and feasibility, laying the groundwork for RL-based bias correction and parametrisations within operational systems.