arXiv:2607.13312v1 Announce Type: new
Abstract: This study presents and validates a minimum-lap-time planning (MLTP) framework for motorsport applications that embeds robustness against both state disturbances and parameter uncertainty. The methodology builds upon a prior disturbance-aware framework that, at each track point, propagates stochastic vehicle dynamics over a short horizon and tightens tyre-friction constraints based on the worst-case scenario at horizon end. We extend the formulation to account for uncertainty in key vehicle parameters: moment of inertia, centre-of-mass position, and aerodynamic drag coefficient. To keep the extended formulation computationally tractable, a spatially selective, parsimonious activation strategy confines the robust constraints to the circuit segments where they are most critical. We demonstrate the improved driveability of the robust references by employing a model predictive controller (MPC) as a virtual test driver. For each reference, the same MPC drives a simulated FSAE (Formula SAE) car over 1000 runs on a representative Barcelona-Catalunya sector, with randomly realised impulsive disturbances and parameter scatter. We compare a nominal reference, planned without robustness, against its robust counterparts. The latter yield consistently fewer failed runs and, at a moderate sector-time cost, show tighter dispersion of key signals (vehicle inputs, axle saturations) around the reference values, evidence of better trackability.
Science Journals
arXiv:2607.13200v1 Announce Type: new
Abstract: This paper addresses multi-objective service placement in computing continuum environments through a collaborative hybrid island-model MOEA. The key innovation is not the design of a new general hybrid algorithm, but the systematic application and analysis of heterogeneous hybridization for this specific optimization domain through two independent experimental campaigns: a first one with four state-of-the-art MOEAs (NSGA-II, NSGA-III, U-NSGA-III, and SMS-EMOA), and a second one with a complementary hybrid configuration based on NSGA-II, MOEA/TS, and MOCPO, both co-evolving and periodically exchanging solutions. These designs enable complementary search behaviors across islands and are naturally aligned with the distributed edge-fog-cloud architecture of the computing continuum, facilitating scalable parallel execution. To evaluate the approach, we define two research hypotheses: (i) whether hybrid cooperation yields significant performance gains over standalone algorithms, and (ii) whether all constituent algorithms contribute equally to the final outcomes. We combine standard Pareto-front quality indicators (GD, IGD, HV, S, and STE) with a traceability-oriented analysis based on genetic load, which quantifies the contribution of each island to the evolved solutions. Across 30 independent runs, the hybrid method outperforms most of the standalone baselines, and statistical tests confirm significant improvements. Results also show non-uniform contributions among islands, providing interpretable evidence of effective hybrid cooperation.
arXiv:2607.13472v1 Announce Type: new
Abstract: Deploying humanoid robots in unstructured terrain remains an open problem. While classic reinforcement learning struggles with the sheer complexity of real-world interactions, more promising methods leveraging human priors remain limited to models lacking contextual awareness. The restricted motion synthesis is a direct consequence of existing dataset pipelines failing to capture human-scene sequences in challenging environments. To bridge this gap between humanoid learning and scene reconstruction, we introduce the Egocentric Human-Terrain Reconstruction (EgoHTR) dataset. We develop and open-source a reconstruction pipeline capturing 55 scene-aligned 4D human motion sequences in diverse, complex environments using a multi-sensor setup of egocentric wearables and a portable 3D scanner. The resulting dataset comprises over 150k frames, which we evaluate against motion-capture ground truth, demonstrating state-of-the-art accuracy and establishing a rigorous benchmark for human motion analysis and synthesis. Further, we leverage this data to train perceptive locomotion policies, demonstrating hardware deployment on a Unitree G1 for reconstructed reference motions. Our pipeline enables community-driven dataset extensions and factors the problem to help researchers build foundational, context-aware robots that reliably traverse uneven terrain.
arXiv:2607.13060v1 Announce Type: new
Abstract: The uncanny valley is a long-standing empirical rule in humanoid robot design: making robots more human-like can reduce, rather than increase, affinity. Yet existing guidelines, such as adopting robot-like appearances, avoiding excessive realism, and reducing cross-modal mismatches, remain difficult to use for algorithmic design because they are not expressed as manipulable variables. Here, we propose a hierarchical Bayesian generative model that operationalizes these guidelines as mathematical design variables. The model represents affinity toward humanoid robots as posterior-weighted negative category-conditional surprise and explains category ambiguity and perceptual mismatch as increases in surprise. It maps uncanny-valley mechanisms onto four variables: deviation from the predicted robot-category mean, inconsistency in human likeness across modalities, prediction uncertainty, and observational uncertainty. Simulations showed that category ambiguity and appearance--motion mismatch can produce affinity reductions, and that uncertainty reshapes the valley. In a human-subject experiment with robot--human morphing images, we manipulated prediction uncertainty using blurred prior robot stimuli and observational uncertainty using blurred evaluation stimuli. Increased observational uncertainty attenuated the decrease in familiarity ratings at intermediate human likeness, whereas low prediction uncertainty increased ratings for robot-like appearances. This framework turns empirical uncanny-valley heuristics into a computational basis for algorithmically evaluating and optimizing humanoid robot appearance and behavior.
arXiv:2503.09057v3 Announce Type: replace-cross
Abstract: Evolution is the adaptation of populations to their environment expressed through the concept of fitness. Darwin did not define fitness but described evolution as the higher prevalence of lineages with advantages in survival and reproduction in changing environments, an implicitly statistical and relational notion. As evolutionary dynamics became more quantitative, however, fitness acquired a narrower meaning of relative reproductive success. Crucially, this narrower definition suffers from three fundamental difficulties, known as the circularity, mismatch, and prediction problems. We show that interpreting evolutionary dynamics in terms of inference resolves these three problems while also creating new productive analytical tools. This shift redefines fitness via a Bayesian likelihood, a predictive probability of the environment specific to each type. We show that averaging the growth rate over environmental histories connects selection to information as types with better environmental models are amplified. It follows that long-run evolutionary dynamics maximizes the mutual information between population structure and environmental statistics, establishing information maximization as the governing principle of natural selection. We illustrate this approach in several population dynamics problems including task switching, evolutionary games, and selection in group-structured populations. In each case, we derive phase diagrams as functions of environmental statistics and Hamilton-type rules for the emergence of cooperation, while also demonstrating the generality of the approach.
arXiv:2511.01680v4 Announce Type: replace-cross
Abstract: Social scientists are increasingly turning to unstructured datasets to unlock new empirical insights, e.g., estimating descriptive statistics of or causal effects on quantitative measures derived from text, audio, or video data. In many settings, unsupervised analysis is of primary interest, in that the researcher does not want to (or cannot) manually pre-specify all important aspects of the unstructured data to measure; they are interested in "discovery." This paper proposes a general and flexible framework for pursuing such discovery from unstructured data in a statistically principled way. The framework leverages recent methods from the literature on AI interpretability to map unstructured data points to high-dimensional, sparse, and interpretable "concept embeddings"; computes statistics from these concept embeddings for testing interpretable, concept-by-concept hypotheses; performs selective inference on these hypotheses using algorithms validated by new results in high-dimensional central limit theory, producing a selected set ("discoveries"); and both generates and evaluates human-interpretable natural language descriptions of these discoveries. The proposed framework has few researcher degrees of freedom, is robust to data snooping and other post-selection inference concerns, and facilitates fast and inexpensive sensitivity analysis and replication. Applications to recent descriptive and causal analyses of unstructured data in empirical economics are explored.
arXiv:2511.13592v2 Announce Type: replace-cross
Abstract: The existing method of GS-PowerOpt solves the non-convex optimization problem of the form $\max_{\boldsymbol{x} \in \mathbb{R}^d} f(\boldsymbol{x})$ through maximizing a Gaussian-smoothed surrogate $F_{N,\sigma}(\boldsymbol{\mu}) = \mathbb{E}_{\boldsymbol{x}\sim\mathcal{N}(\boldsymbol{\mu},\sigma^2 I_d)}[e^{N f(\boldsymbol{x})}]$. We analyze the role of the smoothing radius $\sigma>0$ and identify a limitation of the fixed-$\sigma$ design used in GS-PowerOpt. Specifically, $\sigma$ induces an inherent exploration--refinement tradeoff: a larger $\sigma$ improves global exploration and finite-time surrogate optimization, but may distort the location of the surrogate maximizer; in contrast, a smaller $\sigma$ better preserves local structure but can weaken gradient signals away from high-value regions.
To address this limitation, we propose GS-PowerHP, a power-smoothed homotopy method with an incrementally decaying $\sigma$ schedule. The proposed mechanism uses larger smoothing radii in early iterations to maintain informative gradient signals when the iterate is far from high-value regions, and gradually decreases $\sigma$ to improve local refinement near the maximizer. We provide theoretical results showing that this decaying schedule improves the exploration--refinement tradeoff of fixed-$\sigma$ power smoothing. Empirically, GS-PowerHP consistently outperforms the fixed-$\sigma$ baseline and exhibits robust performance across different optimization tasks, including adversarial attacks on ImageNet ($d=150{,}528$), where it substantially improves over other smoothing-based zeroth-order methods.
arXiv:2601.02291v3 Announce Type: replace-cross
Abstract: We investigate the angle of repose ${\theta}_r$ of dense suspensions of colloidal silica particles ($d = 2$ $\mu m$ to $7$ $\mu m$) in water-filled microfluidic rotating drum experiments, to probe the crossover between the thermal (colloidal) and athermal (granular) regimes. For the smallest particles, thermal agitation promotes slow creep flows, and piles always flatten completely regardless of their initial inclination angle, resulting in ${\theta}_r = 0$. Above a critical particle size, piles of colloids stop flowing at a finite angle of repose, which increases with particle size but remains below the minimal value expected for athermal frictionless granular materials: $0 < {\theta}_r < {\theta}_{ath} \approx 5.8{\deg}$. We quantify the arrest dynamics as a function of the gravitational P\'eclet number $Pe_g$, which characterizes the competition between particle weight and thermal agitation. Our measurements are consistent with a recent rheological model [Billon et al., Phys. Rev. Fluids 8, 034302, 2023], in which the arrested state stems from a crossover between glass and jamming transitions as the granular pressure in the pile increases relative to the thermal pressure.
arXiv:2601.07926v2 Announce Type: replace-cross
Abstract: We propose a general method for studying systems that display excitations with arbitrarily low energy in their low-temperature phase. We argue that in a rectangular right prism geometry, with longitudinal size much larger than the transverse size, correlations decay exponentially (at all temperatures) along the longitudinal dimension, but the scaling of the correlation length with the transverse size carries crucial information from which the lower critical dimension can be inferred. The method is applied in the particularly demanding context of Ising spin glasses at zero magnetic field. The lower critical dimension and the multifractal spectrum for the correlation function are computed from large-scale numerical simulations. Several technical novelties (such as the unexpectedly crucial performance of Houdayer's cluster method or the convenience of using open - rather than periodic - boundary conditions) allow us to study three-dimensional prisms with transverse dimensions up to $L=24$ and effectively infinite longitudinal dimensions down to low temperatures. The value that we find for the lower critical dimension turns out to be in agreement with expectations from both the Replica Symmetry Breaking theory and the Droplet model for spin glasses. We argue that our novel setting holds promise in clarifying which of the two competing theories more accurately describes three-dimensional spin glasses.
arXiv:2603.28408v2 Announce Type: replace-cross
Abstract: Energetic particle populations are ubiquitous throughout the Universe. In our solar system, the most prominent sources of energetic particles are solar flares or collisionless shocks often driven by huge eruptions of magnetised plasma called coronal mass ejections (CMEs). Remotely, low energy electrons from the Sun can be observed as solar radio bursts that are produced by accelerated electron beams undergoing beam-plasma interactions. There are still many open questions on the generation of solar energetic particles (SEP): how and where are SEPs accelerated during solar flares and CMEs and how they escape the solar atmosphere? Another important question is: what is the link between the solar radio bursts and the observed SEPs at spacecraft? SKA can provide high-resolution radio images combined with spectroscopic observations to determine the acceleration time, trajectory and escape of low energy electrons from the solar corona. The synergy between SKA and current space missions will help investigate solar activity and energetic particles across a wide range of wavelengths and particle energies. Particle data from spacecraft can be used to make a connection between radio bursts and SEPs by comparing SEP inferred injection times and energies to those of electrons generating radio bursts at the Sun. Radio observations in turn can be used to distinguish between flare and shock acceleration since different radio bursts pinpoint towards different energetic processes. Since the acceleration region and origin of SEPs of various properties is still largely debated, radio observations have the potential to be an invaluable tool in unraveling these processes.
arXiv:2607.13945v1 Announce Type: new
Abstract: Imaging spectrometers increasingly distribute source-resolved methane plume products in which the plume mask, integrated mass enhancement (IME), plume length, emission rate, and uncertainty are physically and algorithmically linked. Using 63 EMIT-derived Carbon Mapper plume records from 27 scenes, we show that these published scalar quantities do not uniquely constrain the plume boundary: substantially different yet plausible masks reproduce the same IME, plume length, and emission rate. Genetic-algorithm (GA) ensembles conditioned on the published IME and plume length make this equifinality explicit: the high-confidence core selected by nearly all target-consistent masks covers a median of 13% of the plausible footprint envelope, and ambiguity is largest for weak, low-overlap plumes. The diagnostics come from PlumeQuant, which recomputes IME, plume length, emission rate, and five-term uncertainty from distributed product components under stated conventions and evaluates four mask representations: the distributed reference mask, a transparent Carbon Mapper-informed analogue (CM-like), the GA ensemble, and optional expert edits. The CM-like mask is generated per plume without access to the reference mask or published quantities, with settings fixed once on a scene-disjoint 44-plume development split. It reproduced published IME with +0.72% median difference and emission rate with +0.16% (6.98% mean absolute), reached 0.843 median intersection-over-union against the reference masks, and matched the published uncertainty scale (median ratio 1.01). Holdout mean absolute errors were 7.6% (IME), 9.5% (length), and 6.1% (rate). These are product-level consistency diagnostics, not independent validation. They flag weak, offset, or ambiguous plumes for expert review.
arXiv:2607.13956v1 Announce Type: new
Abstract: Dynamical systems undergoing transition to oscillatory state exhibit change in the nature of the transition from supercritical to subcritical Hopf bifurcation or vice versa upon variation of a secondary parameter. This phenomenon is referred to as change of criticality. Many real-world systems undergo transition to oscillatory state that do not fit in the framework of Hopf bifurcation, and hence the change of criticality. We perform experiments on a ducted turbulent aeroacoustic flow constrained by two orifices separated at a distance apart. We vary the Reynolds number (Re), a bifurcation parameter causing a transition between various limit cycles. We change the distance between the orifices as the secondary parameter. We discover that turbulent aeroacoustic flows exhibit a metamorphosis of the transition from continuous to abrupt through a canard explosion, a bifurcation unique for its continuous yet rapid nature. We observe two distinct abrupt bifurcations, differing in their dynamical states associated with the transition. Understanding this metamorphosis from continuous to abrupt aids in developing low-cost control and preventive strategies for systems undergoing a route to oscillatory instabilities.
arXiv:2606.23109v2 Announce Type: replace
Abstract: Ion stopping in dense plasma is crucial for stellar evolution and fusion ignition. However, its behavior in the strong ion-plasma coupling regime beyond the linear limit has long remained elusive, due to formidable experimental challenges. Here we report the first experimental investigation of ion stopping at an unprecedented coupling parameter exceeding unity, achieved by sending laser-accelerated short-pulse and intense quasi-monoenergetic carbon ions ($\sim$583 keV/u, C$^{5+}$) into a uniform, long-lived, well-characterized dense plasma target ($T_e$ $\approx$ 17 eV, $n_e$ $\approx$ 4$\times$10$^{20}$ cm$^{-3}$). By simultaneously measuring ion energy loss and charge-state evolution, we eliminated key experimental ambiguities arising from charge-state determination. Our results clearly show a reduction in stopping power compared with predictions from standard linear dielectric response or binary collision models, and they agree well with the hybrid calculation of molecular dynamics with quantum corrections. The importance of nonlinear screening effects arising from many-body interactions and quantum effects due to the wave nature of electrons was demonstrated at strong coupling. This work establishes a definitive high-fidelity experimental benchmark for collisional dynamics in the strong-coupling regime. It offers critical insight for accurate modeling of energy transport in inertial confinement fusion and astrophysical plasmas.
arXiv:2605.05378v4 Announce Type: replace-cross
Abstract: Well-known chaotic maps, such as the logistic and tent maps, have been used to generate cryptographically secure pseudorandomness, yet we know of no efforts which attempt to utilize the Gauss continued-fraction map, a known chaotic map, as a starting point for producing quality pseudorandom output. In this paper, we consider the family of $r$-continued-fraction maps, which generalize the Gauss map, and use them to generate pseudorandom output which outperforms many standard generators, such as the Mersenne Twister, in statistical quality, as ascertained by the use of the Dieharder, PractRand, and TestU01 suites. In this way, we demonstrate the potential viability of these maps as a starting point for novel generators, and provide practical motivation for further study of the properties of both the exact and finite-precision $r$-continued-fraction maps.
arXiv:2605.14777v2 Announce Type: replace-cross
Abstract: Spectrally multiplexed telecom quantum networks require quantum memories combining efficient storage with programmable frequency addressing. An integrated implementation should therefore unite a native telecom transition, efficient storage, and fast on-chip spectral control. Here we demonstrate a cavity-enhanced memory in an isotopically purified $^{167}\mathrm{Er}^{3+}$-doped thin-film lithium niobate microring. Long-lived hyperfine shelving states enable persistent, high-contrast atomic frequency comb preparation with a single-component lifetime of $277.6(52.6)$~s, while cavity impedance matching yields $23.3(5)\%$ on-chip efficiency for 100-ns storage. The intrinsic electro-optic response enables frequency-selective storage and routing at rates up to 20~MHz. We further store and retrieve time-energy-entangled telecom photons, violating an entanglement-witness bound by more than 11 standard deviations. Our results establish erbium-doped thin-film lithium niobate as a programmable light--matter interface for spectrally multiplexed quantum networks.
arXiv:2607.13959v1 Announce Type: new
Abstract: The random-offerer mechanism for bilateral trade selects the seller or the buyer uniformly and lets the selected agent make a profit-maximizing take-it-or-leave-it offer. Let $\rho_{\rm RO}$ be the infimum, over independent value distributions, of the mechanism's gains from trade divided by first-best gains from trade. We prove $\frac1\pi\le \rho_{\rm RO}<0.460242308085529$.
For the lower bound, we improve the previous guarantee from approximately $0.317844$ to $1/\pi\approx 0.318310$. The proof uses a parameterized Lagrangian bound for pointwise-monotone allocations. At multiplier one, this bound has coefficient $2/\pi$, and the Lagrangian separates into two terms controlled by the optimal seller-offering and buyer-offering profits. For the upper bound, we construct an explicit family consisting of a truncated equal-revenue buyer and a seller distribution with a tilted power-law lower tail and a constant-virtual-cost segment. The family satisfies $\operatorname{FB}/\operatorname{RO}>2.17276852308451$, improving the previous explicit ratio $2.0749$; rigorous interval arithmetic certifies the numerical inequality.
arXiv:2607.13841v1 Announce Type: new
Abstract: Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard diffusion and flow-matching models typically begin from Gaussian noise or Gaussian source distributions, which yield tractable training targets but provide a poor inductive match for heavy-tailed data. We propose Heavy-Tailed Flow Matching via Random Clocks (HTFM), a framework that portrays heavy-tailed sources as mixtures of clock-conditioned Gaussian sources. Conditioning on a given clock path, the source distribution and flow are Gaussian; marginalizing over the clock gives a Gaussian scale mixture covering Gaussian, $\alpha$-stable, and Student-t families. To make the clock-conditioned vector field practical, we encode the path-valued clock using truncated logsignature features, allowing the velocity field to adapt to the realized conditional space with negligible overhead. Empirically, on 2D imbalanced $\alpha$-stable mixtures, CIFAR10-LT, and HRRR weather fields, HTFM improves mode coverage, sample quality, and tail-statistic recovery over Gaussian flow matching and competitive heavy-tailed baselines, while retaining the low-NFE sampling advantage of flow matching. Moreover, the random-clock formulation further provides a practical tail-control interface: by varying only the clock law or tail parameter, the same architecture can calibrate the ``heaviness'' of generated tails across different distribution families.
arXiv:2607.13184v1 Announce Type: new
Abstract: Existing architectural simulators expose aggregate metrics or raw traces, but fail to reveal complex interactions among microarchitectural events and their relationship to program execution. Consequently, architects observe performance symptoms but cannot systematically attribute them to root causes across abstraction layers. This paper introduces Microflow, an observability framework elevating causality to a first-class analytical object. Microflow transforms execution traces into the Microflow Intermediate Representation (MFIR), explicitly capturing dependencies across software semantics, instructions, microarchitectural events, and hardware resources. By unifying these elements, MFIR enables direct traversal from observed stalls to their underlying causes, paving the way for automated root-cause analysis. Microflow precisely attributes stalls, reveals unobservable phenomena, and enables exact critical-path decomposition through counterfactual analysis. These capabilities allow systematic reasoning about complex hardware-software interactions opaque to existing tools. Making causality queryable, Microflow provides a strong foundation for performance analysis and hardware-software co-design. We demonstrate it on two SPEC CPU 2017 benchmarks, uncovering bottlenecks invisible from aggregate symptoms: hidden misprediction costs in leela and cross-loop-iteration contention in mcf.
arXiv:2607.13300v1 Announce Type: new
Abstract: Diffusion generative models have demonstrated immense potential for synthetic medical image generation. However, these models often struggle to capture complex morphological characteristics of heterogeneous tumors with irregular boundaries, limiting their utility for downstream clinical tasks such as segmentation. This limitation stems from the standard denoising objective: minimizing a per-pixel error, which smooths high-variance irregular structures characteristic of tumors. To address this, we propose finetuning these generative models with Fr\'echet Distance loss (FD-loss). FD-loss aligns the first and second order feature statistics of real and generated images in a pretrained encoder space, encouraging the generator to capture complex structural variations characteristic of heterogeneous tumors. We integrate FD-loss across diverse architectural settings, using both natural- and medical-image encoders on multiple liver and brain cancer datasets spanning CT and MRI modalities. Downstream segmentation networks trained on our FD-regularized synthetic data consistently achieve superior performance, improving tumor DSC by $>$$5\%$ over unregularized synthetic augmentation alone. Qualitative analysis suggests these gains are associated with more faithful tumor synthesis and fewer segmentation hallucinations. Our results show FD-loss as an effective regularizer for medical image generative models to improve clinical workflows.
arXiv:2607.13936v1 Announce Type: new
Abstract: Arrhythmogenic left ventricular cardiomyopathy is a genetic myocardial disease difficult to diagnose due to the lack of gold standard criteria. Simultaneous PET/MR imaging, combined with multiparametric quantitative analysis, could facilitate the identification of different profiles related to the phenotype and progression of cardiomyopathy. This preliminary study focuses on a methodological strategy for dealing with PET/MRI data, including inter-patient data linkage and regional analysis. Two-step clustering was applied to T1 and T2 maps, LGE, and 18F-FDG-PET images of 99 patients genetically diagnosed with arrhythmogenic left ventricular cardiomyopathy. Each patient's images were independently z-scored and summed into a single volume, which was clustered into supervoxels. Thirty-two inter-patient groups of supervoxels were obtained by spectral clustering. An "abnormality" score was assigned to each cluster and modality, and used to visualise abnormal regions likely associated with disease. They enabled the generation of automated textual and bullseye health reports for each patient, which were compared with cardiac imager assessments using balanced accuracy in repeated nested cross-validation. This approach was further validated on a larger cohort of 167 numerical phantoms. The reports generated by clustering accurately identified most of the cardiac physicians' observations (BA = 0.76 $\pm$ 0.04 in repeated nested cross-validation on patients, and BA $\ge$ 0.8 on phantoms). Furthermore, the identified abnormal clusters closely matched their visual observations, facilitating the identification of varying degrees of fibrosis or inflammation on the images. This approach enables a more systematic handling of multimodal PET/MRI data to characterise myocardial heterogeneity in arrhythmogenic left ventricular cardiomyopathy patients.
arXiv:2607.13304v1 Announce Type: new
Abstract: Teams measuring whether large language models (LLMs) recommend a brand face a reproducibility problem: ask the same question twice and the answer moves. Practice resamples each prompt a few times (commonly five) and averages, treating within-prompt resampling as the source of the noise. But a measured brand score moves for at least four separable reasons: within-prompt resampling, prompt paraphrase, model identity, and query language. We specify a crossed random-effects (generalizability-theory) decomposition that partitions the total variance of a response-level brand outcome into these four sources, and embed the components in a decision-study allocation that returns how many repeats, paraphrases, models, and languages to buy for a target reliability. We apply it to a fully crossed corpus of 12,933 LLM responses on 20 Central and Eastern European brands, 8 languages, and 3 models (GPT-5.2 and Gemini 3 Flash in parametric mode, Perplexity in grounded retrieval), with a stability subset of 1,435 cells resampled about five times. The outcome is per-response multilingual sentiment polarity. Query language is the largest systematic facet (26.5% of the variance of one response) against 1.5% for brand identity (ICC 0.0146), so a single AI answer carries almost no brand-discriminating signal. Once a cell term isolates pure resampling, resampling is 34.8% of variance and the brand-in-context interaction 29.6%; brand-by-language is 8.6% (a bilingual penalty) while brand-by-model and brand-by-prompt are near zero. Per unit of query budget, adding languages and models reduces relative-error variance far more than adding repeats: a repeat past the fifth reduces it by only 0.0003. Brand-ranking reliability stays low, near 0.01 for a single answer and about 0.36 at the full crossed design, so reliability is bought by spreading across languages and models, not by repeating one prompt.
arXiv:2607.13866v1 Announce Type: new
Abstract: Surrogate models are used to substitute classical numerical solvers in engineering applications where the computational cost of the latter becomes infeasible. For instance, in aerodynamics such models offer cost-effective alternatives to computational fluid dynamics in problems such as shape optimization and load analysis, which oftentimes require high-fidelity simulations for a multitude of different parameter combinations. A specific class of deep learning-based surrogate models termed operator learning models directly approximates the solution operators to the partial differential equations underlying the physical phenomenon, thereby learning to replicate solutions to entire families of problems. However, while nowadays numerous architectures of this type get published, corresponding benchmark studies remain scarce. In this article, we advance the study of AI-based surrogate methods by thoroughly benchmarking four state-of-the-art operator learning models on their aptitude for applications in aerospace engineering. In two experiments, we assess the models' capabilities of predicting the surface pressure distribution on two-dimensional airfoil shapes of varying complexity and on an industrial-scale three-dimensional aircraft configuration. Thereby, we evaluate the models' abilities to fulfill frequent requirements in aerodynamics such as capturing discontinuities (shocks) in the solutions, scalability towards excessive amounts of mesh points and handling of data scarcity. Accompanied by a careful analysis, our findings drive forward the field of AI-based surrogate modeling by providing detailed insights into the strengths and weaknesses of the individual architectures, thus allowing to identify priorities for future developments. In particular the Bi-Stride Multi-Scale Graph Neural Network and Transolver(++) are highlighted as promising surrogate models for aerodynamical applications.
arXiv:2607.13880v1 Announce Type: new
Abstract: In underwater covert cooperative missions, autonomous underwater vehicles (AUVs) often cannot rely on active sonar to continuously obtain complete information, since active sensing and frequent communications increase the risk of exposure. As a result, AUVs primarily rely on passive observation, an approach that yields incomplete local perception and limited task efficiency. Although underwater acoustic communications can mitigate this limitation through information sharing, they are simultaneously constrained by long delays, severe interference, low reliability, and the risk of covert exposure. Existing communications-oriented multi-agent reinforcement learning (MARL) studies often model communication as an ideal information flow, whereas traditional communication optimization primarily focuses on link-level performance. However, both are insufficient to characterize the actual contribution of perceptual information to cooperative tasks under realistic conditions of covert physical communications. This paper proposes a Sensed Information Value Realization Multi-Agent Reinforcement Learning (SVR-MARL) framework that leverages practical information to characterize the utility of information for cooperative tasks and learns distributed cooperative policies under realistic communication and covert constraints. Through a case study of covert multi-AUV cooperative localization and tracking, the potential of the proposed framework to improve collaborative task efficiency while reducing unnecessary communication and exposure risks is demonstrated.
arXiv:2607.13882v1 Announce Type: new
Abstract: Learning from demonstration (LfD) enables robots to learn manipulation skills directly from expert demonstrations but remains challenging for contact-rich tasks involving geometric constraints and force interaction. Existing approaches typically require multiple complete demonstrations and do not support reverse skill execution. In this paper, we present a unified one-shot framework for constrained manipulation that learns both forward and reverse execution from a single, possibly unfinished demonstration. Our method decomposes demonstrations into non-contact and contact phases, with non-contact motion encoded with dynamic movement primitives (DMP), and contact motion represented as a sequence of screw motion primitives segmented by our proposed geometry-driven twist-direction segmentation algorithm. During execution, screw primitives are executed sequentially under admittance-guided pose correction and speed regulation, enabling task completion beyond the demonstrated trajectory length as well as reverse skill execution without additional learning data. Experiments on peg insertion, battery insertion, lock opening, and screw driving tasks demonstrate improved success rates and robustness over segmentation and one-shot trajectory learning baselines. Details are available on the project website: https://tuwien-asl.github.io/LfD-Screw/.
arXiv:2607.13884v1 Announce Type: new
Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from failures. Existing self-correction mechanisms rely on prompt-based reflection, which is inherently brittle, incurs heavy time and API costs due to iterative trial-and-error loops, and produces task-specific memory that may be hard to generalize to new scenarios. To address this, we propose Experience Memory Graph (EMG), a framework that reformulates agent failure recovery as a graph matching problem. At training time, we convert both failed exploration trajectories and successful expert trajectories into directed action decision graphs. By matching these graphs, we extract common subgraphs (successful workflows) and graph edit paths that explicitly indicate how to correct failures (e.g., which actions to add, delete, or relabel under a given observation), and store them in a memory graph with intra-task nodes and cross-task edges. At test time, EMG retrieves relevant insights and guides the agent in a single, loop-free execution. Experiments on ALFWorld and ScienceWorld show that EMG consistently outperforms state-of-the-art reflection baselines in success rate and average reward, while requiring no test-time trial-and-error.