Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Monday 7 September

Multimedia

Can Agents Win the Video Browser Showdown?

Searching large video collections is typically an interactive process in which users play two roles. First, they hold the search intent: the underlying goal that determines what content they seek and why. Second, users must operationalize this intent through an iterative search loop. Users translate their intent into queries, browse the retrieved candidates, and refine their queries based on the results. In this paper, we investigate the capabilities of modern Vision Language Models (VLM) and agentic approaches to reach search goals interactively and fully autonomously. Specifically, we study whether a provided initial specification of a search goal might be sufficient to solve traditionally interactive search tasks with an agentic system. Provided that the involved VLMs are not aware of the whole large video dataset in advance, the key challenge lies in the effective combination of an existing interactive video search system and a smart VLM agent controlling the system. While the search system provides indexing and efficient querying, the VLM-based agents analyze top-ranked items and make decisions about next actions. Our results show that modern agents can autonomously operate interactive video retrieval systems to solve many search tasks from an initial intent description, achieving performance competitive with strong historical expert-operated systems in several settings.
Read the full abstract

All authors Bastian Jäckl, Zuzana Vopálková, Daniel A. Keim, Jakub Lokoč

Probability

Christoffel transform and symplectic skew Howe duality

For a symmetric weight $w(x)$ on a finite discrete lattice and its Christoffel transforms $x^{2}w(x),x^{2}(x^{2}w(x)),\dots$, we prove that, at each Christoffel step, the conjugated projection associated with the transformed Christoffel–Darboux kernel differs from the original orthogonal projection by a rank-one operator on the subspace of functions vanishing at the origin. This provides a general mechanism for transferring local asymptotic results from an orthogonal polynomial ensemble to its Christoffel-transformed counterpart as the lattice size tends to infinity. As a main application, we study local fluctuations of random Young diagrams arising from skew $(\mathrm{Sp}_{2n},\mathrm{Sp}_{2k})$ Howe duality. The corresponding particle ensemble is obtained from the Krawtchouk orthogonal polynomial ensemble on a quadratic lattice by a Christoffel transform. We identify four asymptotic regimes of local fluctuations in the limit $n,k\to\infty$ with $n/k\to c\in(0,\infty)$. Besides the universal bulk fluctuations governed by the discrete sine kernel and universal Airy fluctuations at the right edge of the limit shape, we obtain the discrete Hermite kernel in the critical regime $(k-n)/\sqrt{n+k}\longrightarrow r\in\mathbb{R}$, and the discrete hard-wall sine kernel at the left corner.
Read the full abstract

Computation and Language

LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances

Robustness evaluation of large language models (LLMs) remains a critical challenge, particularly in assessing their sensitivity to perturbations in input data. In this work, we systematically evaluate LLM robustness across multiple dimensions, including word error rate, character repetition and duplication, modifications in choices, and variability in instruction following. To facilitate this evaluation, we construct a synthetic and augmented dataset encompassing a diverse set of LLM benchmarks, specifically targeting multiple-choice question (MCQ) datasets and instruction-following tasks. We conduct extensive experiments on LLMs of varying scales-small, medium, and large-as well as across base and instruction-tuned variants. Our analysis quantifies the variability in model responses under perturbed conditions and highlights discrepancies relative to baseline models. The findings provide insights into the stability of LLMs across different evaluation scenarios contributing to the development of more robust and reliable language models as well as robust evaluation methodologies.
Read the full abstract

Mathematical Physics

Big Crunch on Julia and Anti-Julia Sets in the Integrable Limit

The Julia set is defined by the closure of repelling periodic points in chaotic systems. Why does this structure not appear in integrable systems? In this paper, we address this question by demonstrating the existence of the closure of divergences of the periodic equations, which we designate as the "anti-Julia set." We also call the sets before taking the closures the pre-Julia and pre-anti-Julia sets, respectively. We illustrate the transition mechanism by considering a complex map that interpolates between integrable and non-integrable dynamics, by introducing a real deformation parameter $a$. For $0<a\le 1/2$, we show that the Julia set and the anti-Julia set coincide in the complex plane, although the pre-Julia and pre-anti-Julia sets remain completely disjoint. At the integrable limit $a\to 0$, these two dual structures undergo a critical collision and subsequent annihilation, reminiscent of a cosmological Big Crunch. When $1/2<a<1$, on the other hand, the boundary of the pre-anti-Julia set includes the Julia set. We analytically characterize these phenomena, focusing in particular on the asymptotic behavior of the pre-anti-Julia set as it approaches the integrable limit, and provide numerical visualizations that elucidate the underlying mechanisms of this Big Crunch phenomenon.
Read the full abstract

All authors Masatomi Iizawa, Satoru Saito, Yasuhito Narita, Yasuyuki Maeda, Hiromitsu Harada, Akira Shudo

Computation and Language

SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging

Taxonomy induction aims to organize concept sets into coherent hierarchical structures. Recent LLM-based methods can induce taxonomies directly from flat term lists, avoiding the need for corpora, but degrade sharply as concept sets scale up. We argue that this degradation stems not only from context length limitations, but also from structural failures in hierarchical reasoning. To address this, we adopt a divide-and-merge paradigm that partitions concepts into smaller subsets, induces local taxonomies, and merges them into a global hierarchy. However, we identify two structural failure modes inherent to this paradigm: Structural Fragmentation, where partitioning weakens local hierarchical signals, and Parent Displacement, where locally plausible relations are misplaced in the global hierarchy. To address both, we propose SPARROW, a scalable taxonomy induction framework that combines structure-preserving spectral partitioning to retain hierarchical connectivity within each block, and constraint-guided incremental fusion that treats block-level relations as structural constraints rather than ground truth for global placement. Experiments on large-scale benchmarks show that SPARROW consistently achieves the strongest global structural quality across backbones. The code is available at https://github.com/rebeccazyr/SPARROW.
Read the full abstract

All authors Yirui Zhang, Yixuan Tang, Yandong Sun, Mong-Li Lee, Anthony Kum Hoe Tung

Computation and Language

RouteRelay: Event-Triggered Cross-Layer Route Reuse for Efficient Dynamic Sparse Attention

Dynamic sparse attention reduces long-context prefill cost by routing each query chunk to a small set of key chunks at every Transformer layer. The sparse attention kernel avoids most token interactions, but the router still rebuilds a chunk–chunk score matrix layer after layer, even when the selected routes change little. We introduce RouteRelay, a router-agnostic method that reuses only route metadata across depth while continuing to compute attention with the current layer's queries, keys, and values. Anchor layers perform full routing. Intermediate layers rescore the previous top-$k$ route and a compact sentinel set of near-miss and randomly probed chunks. A query row is rerouted only when a sentinel challenges its weakest selected chunk. We give a top-$k$ stability condition, a probabilistic bound on missed challengers, and a row-selective GPU execution design. In a reproducible empirical evaluation, RouteRelay retains at least 99.99% route recall while rerouting 25.0%, 55.4%, and 78.2% of rows under low, moderate, and high cross-layer drift, respectively. Across routing scales, RouteRelay retains 100.0% recall while evaluating 38.4–51.6% of full-routing score pairs as the key-chunk count grows from 128 to 1024. Its unfused CPU execution remains slower than dense matrix multiplication, exposing row compaction and ledger updates as the main kernel-engineering targets.
Read the full abstract

All authors Bin Li, Sisi Liu, Chenyang Hu, Chaoyang Zhang, Wei Li, Hui Song

Computation and Language

Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure

Demographic synthetic survey panels are often validated by matching aggregate answers to published surveys. We test what that certificate establishes across six multiselect batteries from four survey organisations in three countries. The headline analysis is restricted to three instruments whose synthetic cohort and human target share the stated population frame; three other batteries remain sensitivity analyses. The response contract dominates measured fidelity. In the aligned instruments, committed sets leave 66 of 128 model-battery option slots empty in panels of up to 500 respondents, versus 0 of 128 under per-option probability elicitation. Across eight uncapped model-instrument comparisons, probabilities reduce option-marginal MAE by 4.53 to 7.30 points. The capped instrument reverses on two models until the vectors are projected onto its stated maximum. These are measurement effects: human targets are realised check-all responses, whereas the vectors are latent inclusion propensities. Published marginal agreement also fails to discriminate respondent simulation from direct population estimation. On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons. Constraint-aware probability vectors average 5.34 and beat the query on four of nine, so the baseline challenges the validation criterion rather than proving direct estimation uniformly best. On three unpublished demographic cells, neither approach beats reciting the national distribution. Population-marginal agreement is therefore evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.
Read the full abstract

Discrete Mathematics

A simple algorithm for computing Hamilton paths on independent set polytopes

The independent set polytope, or stable set polytope, of a graph $G$ is the 0/1-polytope defined by the convex hull of the characteristic vectors of all independent sets of $G$. We present a simple algorithm for computing a Hamilton path on the independent set polytope of a given $n$-vertex graph $G$ with amortized delay $\mathcal{O}(n)$. The independent sets are listed such that two consecutive sets differ either in removing a vertex, or adding a vertex and removing its neighbors from the independent set, i.e., the symmetric difference between two consecutive independent sets induces a star in $G$. As applications of this result, we obtain an algorithm to compute a Hamilton path on the matching polytope of an $m$-edge graph $G$ with worst-case delay $\mathcal{O}(m)$, which lists all matchings of $G$ in such a way that the symmetric difference between two consecutive matchings is a path on at most three edges. Furthermore, we obtain an algorithm to compute a Hamilton path on the chain polytope and order polytope of an $n$-element poset $P$ with amortized delay $\mathcal{O}(n)$, which lists all antichains of $P$ or all ideals of $P$, respectively, by star exchanges. Our algorithms are derived from the generic framework proposed by Merino and Mütze (FOCS'23+SICOMP'24) for computing Hamilton paths on arbitrary 0/1-polytopes, which uses a linear optimization procedure as a black box. Our algorithms bypass solving the computationally intractable maximum weight independent set problem by a simple and purely combinatorial greedy rule.
Read the full abstract

All authors Jean Cardinal, Pia Herkenrath, Torsten Mütze, Francesco Verciani

Machine Learning

Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching

Current paradigms for training language models via reinforcement learning rely heavily on sparse outcome rewards. However, as we pursue tasks that require longer and more complicated trajectories, such strategies result in slow learning. Prior work has attempted to address this problem by rewarding partial progress; however, naive formulations are often biased and converge to suboptimal policies. We show that a simple and unbiased dense reward formulation, which we term progressive point matching, scales exponentially more efficiently to long-horizon tasks by rewarding partial progress on a segment level, both theoretically and empirically via synthetic environments. We then show how progressive point matching can be practically instantiated using a single reference trajectory per task. On extremely hard math reasoning problems, sparse outcome rewards cannot make any progress, whereas segment-level rewards enable improvements at larger test-time token budgets when measured by success rate or pass@k.
Read the full abstract

All authors Preston Fu, Kevin Frans, Oleh Rybkin, Sergey Levine, Aviral Kumar

Systems and Control

Timescale-aware surrogate-assisted multi-objective optimization of battery cell design for energy density, fast charging, and degradation

Battery cell design must balance energy density, fast charging, and degradation, yet these metrics evolve over different time scales and are costly to optimize jointly. We develop a timescale-aware surrogate-assisted framework that evaluates beginning-of-life volumetric energy density and 10–80% charging time together with state-of-health (SOH) loss over 200 cycles. Physics-based simulations of 1501 cell designs generate 1427 quality-controlled samples across 12 manufacturing-relevant parameters. Objective-specific surrogates support total-order Sobol analysis, which reveals distinct parameter rankings across the three metrics. A cross-objective rank-union strategy then retains variables influential to at least one objective before evolutionary Pareto optimization. Re-evaluation of the optimized candidates using the original physics-based models confirms designs that outperform the reference cell in all three metrics. Among these jointly improving candidates, the objective-wise best solutions, attained by different designs, can reduce SOH loss by 99.31%, increase volumetric energy density by 12.49%, and shorten charging time by 28.73%. The framework makes Pareto exploration across disparate electrochemical timescales computationally tractable, thereby enabling systematic multi-objective optimization of battery cell design.
Read the full abstract

All authors Qingbo Zhu, Changfu Zou, Yicun Huang, Chunqiu Xia, Torsten Wik

Statistics Theory

Glivenko–Cantelli Theorems for Integrated Volatility Functionals in Pure-Jump Semimartingales with an Application to Cryptocurrency Markets

We develop a two-step procedure for estimating integrated volatility functionals, defined through the occupation measure of the latent spot volatility process, when the asset price is a pure-jump semimartingale. In the first step, block-based estimators formed from absolute powers of high-frequency increments uniformly approximate local averages of powers of volatility. In the second step, these estimates are aggregated into an empirical occupation measure. Since price increments have infinite variance in this setting, arguments based on local Gaussianity are unavailable, and the uniform theory instead rests on maximal inequalities tailored to the stable regime. We establish Glivenko–Cantelli-type uniform consistency over classes of bounded monotone, Lipschitz-in-parameter, and locally Hölder test functions. These results deliver consistent estimation of volatility occupation times and quantiles, together with an argmax-consistency theory for $M$-estimators built on nonparametrically recovered latent processes. We further propose a stability-based rule for selecting the power index of the volatility estimator, which tracks an infeasible ex ante optimal choice closely in Monte Carlo experiments. An application to high-frequency cryptocurrency markets illustrates the framework in a jump-dominated, heavy-tailed environment.
Read the full abstract

All authors Dachuan Chen, Jia Li, Tian Xie, Chengxin Yan

Machine Learning

PCFlow: Physics-Conditioned Flow Matching for GPR B-Scan Image Synthesis

Ground-penetrating radar (GPR) B-scan image synthesis is important for data augmentation, algorithm validation, and simulation acceleration, yet generating radargrams with both visual realism and physical consistency remains challenging. Existing learning-based generative models often emphasize visual appearance but provide limited control over response geometry. In this paper, we propose PCFlow, a physics-conditioned flow matching framework for fast GPR B-scan image synthesis. The core of PCFlow is a Maxwell-informed dense physical condition field constructed from the parameterized physical model used for electromagnetic simulation, including material properties, target geometry, propagation cues, and response-domain priors. This condition field provides an interpretable interface between physical scene parameters and radar response geometry, and guides conditional flow matching in the VAE latent space toward physically feasible generation paths. We evaluate PCFlow on a gprMax-based buried-pipeline dataset with both in-distribution and out-of-distribution test cases. Experimental results show that PCFlow generates images with more accurate response geometry and high visual fidelity, demonstrating its effectiveness for controllable and physically faithful radar image synthesis.
Read the full abstract

All authors Zhijie Shen, Chenchen Fu, Xuanhao Chang, Hongtao Bai, Lili He

Artificial Intelligence

World Models Under Asynchronous Sensor Observations

Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vector at each environment step. Physical sensing instead operates at heterogeneous rates, leaving most observation channels stale at any given instant. Interpolating stale channels introduces measurements that were never observed, while downsampling to the slowest sensor discards valid measurements. A natural alternative is to zero-order-hold the most recent reading and provide the known sampling schedule to the model through two features, staleness and time-to-refresh. We test this prediction using transformer world models across three regimes of increasing causal coupling: open-loop rollouts in continuous-control locomotion, closed-loop model-predictive planning in which each learned model serves as the planner dynamics, and a linear latched-actuator system in which refresh events apply a zero-order-held command to the plant. Our findings show that the effectiveness of time-to-refresh depends on the causal role of the sampling schedule, specifically when refresh events affect the system rather than merely report its state. These results establish when sampling schedules provide useful information for predictive world models operating under asynchronous physical observations.
Read the full abstract

Computer Vision

KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling

3D reconstruction typically strives for geometric fidelity or visual plausibility. Radio frequency digital twins (RFDT) are instead judged by whether communication channels behave in them as they do in the real world. RFDTs promise site-specific channel prediction but current practice forces a choice between coarse automated scenes and hand-built, measurement-calibrated models that take weeks to construct per-site. We present KODAMA, an automated pipeline that reconstructs ray tracing-ready RFDTs at city scale from off-the-shelf geospatial data alone: aerial imagery, LiDAR, and photogrammetry yield terrain and watertight building meshes, while exposure-weighted multi-view fusion of street-level imagery recovers façade relief, electromagnetic materials, and clutter—all without site visits or calibration. Across three sites spanning 3.6 to 28 GHz, KODAMA's uncalibrated predictions achieve single-digit RMSE, reducing point-to-point error by up to 5.35 dB over automated baselines and coming within 0.22 dB of a measurement-calibrated, hand-built RFDT.
Read the full abstract

Quantum Physics

Momentum-Space-Engineered Spatial Photonic Ising Machine for Long-Range Interactions

Long-range Ising models (LRIMs) with dense nonlocal and competing interactions are central to statistical physics, quantum simulation, and complex networks. Although the spatial photonic Ising machine (SPIM) exploits intrinsic optical parallelism for Ising computation, its ability to faithfully encode dense long-range couplings and capture the resulting thermodynamic signatures remains underexplored. Here, we present a momentum-space-engineered SPIM framework that maps prescribed long-range coupling kernels onto momentum-space masks for parallel Hamiltonian evaluation. Based on a high-fidelity optical field propagation model, the annealing dynamics of LRIMs with power-law and Ruderman-Kittel-Kasuya-Yosida (RKKY) interactions are systematically investigated. For the power-law model, we investigate the modulation of the estimated critical temperature by the decay exponent {\sigma} and coupling cutoff radius R. For the RKKY model, we reproduce diverse ordered states induced by complex competing long-range interactions. A proof-of-principle experiment demonstrates the physical feasibility of our approach. This framework broadens the class of many-body systems accessible to the SPIM platform.
Read the full abstract

All authors Haijun Zhou, Hengyang Li, Maolin Wang, Yunru Chen, Yingxiong Qin, Xiahui Tang, Gang Xu

Computation and Language

Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts

Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood as a structured yet dynamic phenomenon. To investigate this, we introduce Conflict-driven Value Probing, a controlled framework that places LLMs in value conflicts and implements four types of interventions that perturb these conflicts to probe LLM value expression. Applying this framework to ten LLMs, we identify three recurring patterns. (1) Expression duality: models shift from broad idealistic orientations in abstract assessment toward more pragmatic priorities in concrete conflicts. (2) Functional steerability: models readily reconfigure their expressed value profiles toward task-defined value objectives. (3) Bounded plasticity: such reconfiguration is not without constraints, i.e. pressure induces a security- and goal-oriented priority shift while negative framing distinguishes protected values from those more amenable to redirection. Together, these findings characterize both the structure and dynamics of LLM value expression: context flexibly reconfigures expressed priorities, yet within behavioral boundaries. This behavioral account provides a foundation for understanding controllability, alignment, and safety in LLMs. Code and data are available at https://github.com/ZeroGen-Lab/CFProbe.
Read the full abstract

All authors Kaicheng Zhang, Jingyi Xiao, Renjun Hu, Xiaoling Liu, Yunshi Lan, Xuan Zhou

Materials Science

Metallic-Phase-Fe$_3$GaTe$_2$ Enabled Interface Engineering for Self-Powered and High-Gain WS$_2$ Photodetectors

Two-dimensional transition-metal dichalcogenides offer strong light-matter interaction but suffer from inefficient carrier separation and contact-related losses in photodetectors. Here, we demonstrate a high-gain WS$_2$/Fe$_3$GaTe$_2$ van der Waals heterostructure photodetector, where metallic Fe$_3$GaTe$_2$ serves as an active interfacial contact. The work-function mismatch, together with interfacial charge redistribution and asymmetric contact geometry, contributes to a built-in field that supports self-powered photodetection at zero bias. Under 450 nm illumination, the device delivers a zero-bias responsivity of 23.5 A/W and an apparent external quantum efficiency of 6.4 x 10$^3$%. At -1 V biasing, the heterostructure exhibits photoresponse at 450, 520 and 633 nm, achieving a responsivity of 9.7 x 10$^3$ A/W and a noise derived specific detectivity of 2.3 x 10$^13$ Jones at 100 Hz under 450 nm illumination. The high photoresponse is attributed to interfacial carrier separation, efficient extraction, and a likely contribution from trap-assisted photogating in multilayer WS$_2$. These results establish Fe$_3$GaTe$_2$-enabled interface engineering as an effective route for self-powered, highly sensitive 2D photodetectors.
Read the full abstract

All authors Wajid Ali, Ming Huang, Juan Li, Jianhua Huang, Liuli Yang, Sajid Ur Rehman, Chinmay K. Mohanty, Zahir Muhammad, Ziwei Li, Maciej R. Molas

Machine Learning

Constitutive State-Space Modeling of Path-Dependent Plasticity: A Resolution-Consistent and Parallelizable Computational Framework

Data-driven constitutive models for path-dependent plasticity are commonly formulated using nonlinear recurrent neural networks, whose sequential state evolution limits parallel training and whose predictions may depend on the discretization of the applied strain path. We introduce a Constitutive State Space (CSS) model that reformulates structured state-space dynamics as an incremental constitutive operator. The strain increment is decomposed into magnitude and direction: the loading direction drives the latent state-space system, while the increment magnitude enters the zero-order-hold discretization of its continuous-time linear recurrence. This mechanics-tailored construction guarantees stationarity under zero increments, strongly reduces sensitivity to strain-path resolution, and retains the parallel-scan structure of S5 for efficient training on long constitutive histories. The CSS and Minimal State Cell (MSC) architectures are compared for four multiaxial path-dependent material models including isotropic J2 plasticity, pressure-sensitive foam plasticity, and combined isotropic-kinematic hardening. CSS matches or exceeds the prediction accuracy of the MSC, including one order of magnitude lower validation losses for the plastically incompressible materials. Importantly, CSS maintains low errors across large changes in strain-path discretization, whereas the MSC error increases substantially when evaluated at coarser resolutions than used for training. CSS trains substantially faster and requires fewer strain-stress pairs to attain comparable or better accuracy. Analysis of the learned state further reveals latent structure consistent with the dimensionality of the underlying physical constitutive models. These results establish mechanics-tailored structured state-space dynamics as a computational framework for efficient and discretization-robust data-driven constitutive modeling.
Read the full abstract

All authors Rui Barreira, Taylan Soydan, Francesco Scipione, Miguel A. Bessa, Dirk Mohr

Social and Information Networks

Ex Ante Estimation of Payable Relief and Compensation Timing for Supplier Selection

Supplier selection affects not only operating performance but also the payable network entered by a new obligation. This paper develops the Compensability Capacity Assessment (CCA), an ex ante buyer-supplier measure of expected gross payable relief and its likely timing. CPM provides the bounded structural kernel; concave CCA variants add bilateral invoice capacity. The measure is tested on 749,952 analytical invoices issued during 2012-2023, using frozen nine-month histories and future weekly, monthly, quarterly, semester, and annual windows. Cycle-restricted and path-enabled clearing are independent outcome-generating environments used to validate the measure, not technologies compared by this study. Across seven fully observed quarters in 2022-2023, log-CCA has a median Spearman correlation of 0.638 with future integrated relief; persistent relations carry 93.5% of relief, and the highest-scoring relation captures 92.5% of buyer-specific best relief. Predictability remains positive from week to year, with quarterly recalibration providing the best operating balance between signal, coverage, and timeliness. A timing analysis shows that, across the two validation environments, 89-91% of attributed relief occurs within seven days of invoice issue and 94-96% within thirty days, on average about sixteen days before contractual maturity. Log-CCA correlates 0.564 with thirty-day relief and 0.566 with relief-days. Its highest quartile has a 96.5% median probability of thirty-day compensation, compared with 57.6% in the lowest quartile. Conditional waiting-time prediction is weaker, so CCA should rank timely compensation opportunity rather than forecast an exact payment date. The findings link supplier placement, financial circularity, and working-capital exposure while motivating deployment, causal testing, and quarterly drift monitoring.
Read the full abstract

Applied Physics

An integrated viscoelastic modeling framework combining analytical and FEM approaches: Application to WSe2 coatings

This work presents an integrated methodology combining analytical and finite element FEM based viscoelastic modeling for characterizing the nanoindentation response of coatings. The proposed framework combines two complementary modeling approaches: an analytical model based on the Burgers formulation to analyze nanoindentation load displacement data and extract rheological parameters, and a numerical FEM model implemented in ABAQUS using a 2D axisymmetric indenter coating substrate configuration with viscoelasticity represented through Prony series. An automated inverse optimization routine employing the Nelder Mead simplex algorithm minimizes the discrepancy between experimental and simulated responses. The methodology is demonstrated and validated on WSe2 coatings, showing an agreement between the analytical predictions, FEM simulations, and experimental measurements. Despite the geometric simplifications, the FEM approach provides accurate predictions while maintaining high computational efficiency of time dependent mechanical behavior. The proposed framework provides a robust tool for characterizing viscoelastic behavior from nanoindentation data while enabling access to internal stress and strain fields, thereby offering deeper insight into plastic deformation, crack initiation, and failure mechanism.
Read the full abstract

All authors Mohamed Bensalem, Fateh Bahadur, Yue Wang, Nabil Daghbouj, Tomas Polcar

Signal Processing

Performance Analysis of LoRa and LR-FHSS in 3GPP LEO Satellite and HAPS Channel Scenarios for Remote Area IoT Coverage

In this paper, we analyze and compare the performance of LoRa and LR-FHSS in a remote area Internet-of-Things (IoT) connectivity scenario using a low-earth orbit (LEO) satellites and high-altitude platform station (HAPS)-mounted gateway. We conducted a link budget analysis to evaluate communication stability to assess the ability of the technologies to support the different distances and behaviors using a 3GPP channel model for non-terrestrial networks. Several parameters are considered, such as altitude, minimum elevation angle as well as the impact of different types of loss, such as shadow and fast fading, ionosphere scintillation loss, for example. Our findings highlight the performance gap between LR-FHSS and LoRa in terms of both connectivity. We also highlight how lower HAPS altitudes can benefit certain LoRa settings compared to LEO satellites. We show that HAPS can enable the use of lower LoRa spreading factors, which improves scalability and energy efficiency, while LR-FHSS and a higher spreading factor LoRa remain the solution for LEO satellites.
Read the full abstract

Software Engineering

Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach

The rapid digital transformation of manufacturing, often referred to as Industry 4.0, relies on seamless interoperability between physical and software assets. A central enabler is the Asset Administration Shell (AAS), a standardized digital representation of such assets. Recent advances in large language models (LLMs) enable the generation of AAS submodels from unstructured sources such as product datasheets but raise challenges for quality assurance. In particular, unexpected errors, the lack of ground truth references, and the absence of standardized quality metrics hinder reliable adoption. In this work, we evaluate quality metrics for AI-generated AAS using a perturbation-based evaluation framework. By systematically degrading AAS generation along multiple dimensions, we assess how well different metrics reflect quality changes. Based on a dataset of 200 products from multiple manufacturers, we generate 6,400 AAS instances using GPT-4o-mini, Qwen3, and DeepSeek-R1. Our results show that metrics based on exact matching of property names and similarity-based soft matching of property values, in particular value-based recall and name-based F1 score, provide the most reliable indicators of quality degradation. Furthermore, we quantify the impact of different perturbation types and analyze differences across model families and product segments. These findings support the selection of suitable metrics, the tuning of LLM-based pipelines, and the integration of AI-generated AAS into industrial applications.
Read the full abstract

Optimization and Control

CLInstGen: An Instance Generation Framework for Two-Tier City Logistics

City logistics addresses the design and management of efficient freight transportation in urban areas. Two-tier networks, where goods are moved by different vehicle fleets from distribution centers to customers using intermediate consolidation facilities, are particularly effective. Although studied from routing, location, and network design perspectives, the research progress is slowed by the lack of standardized, state-of-the-art benchmark data. Many studies rely on outdated and artificial or case-specific instances, limiting reproducibility, comparability, and generality of results. To address this gap, we identify general problem characteristics for two-tier city logistics, provide an instance generation framework CLInstGen that is applicable to a wide range of problem settings, and propose the first benchmark library CLLIB. The library and the CLInstGen code are open-source, allowing researchers to easily use, adapt, and generate instances for their specific applications. CLLIB is based on real-world geographies of urban regions and provides a curated collection of standardized instances for direct benchmarking of models and methods as well as statistical evaluation. A computational study with two different problem settings, namely tactical service network design on two tiers and vehicle routing with simultaneous pickups and deliveries on a single tier, confirms the versatility of both the generator and the library, and provides first numerical and managerial insights on the CLLIB benchmark instances.
Read the full abstract

All authors Julia Lange, Johannes Gückel, Pirmin Fontaine, Timo Gschwind

Robotics

How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to evaluate their reliability as safety-aware decision makers in human-humanoid collaboration. Unlike deterministic safety systems that enforce binary allow/deny decisions, LLM-based orchestrators exhibit a compliance spectrum ranging from overcompliance (refusing safe actions) to full safety violations. This paper introduces the first safety benchmarking environment for LLM orchestrators in human-humanoid collaboration, built on a Model Context Protocol (MCP)-based architecture with safety invariants grounded in ISO 10218-2:2025 protective measures. The benchmark defines five testable safety invariants, a four-level compliance taxonomy (correct compliance, overcompliance, undercompliance, full violation), and a three-layer evaluation pipeline (text prompting, simulated sensor-actuator loops, and physical validation on a Unitree G1 EDU humanoid). We report Layer-1 results: three cloud backends (Claude Haiku 4.5, GPT-4o-mini, Gemini 2.5 Flash) and a local open-weights baseline (qwen3:8b) across 40 100-turn sessions under full-context and sliding-window budget conditions, while the simulation and physical layers remain ongoing. We find that (1) model family determines the safety floor, as Claude and Gemini remain at or near zero violations while GPT-4o-mini commits up to 13 per session, (2) context management dissociates two failure axes, reducing mean behavioral issues by 42-57% for every cloud backend while nearly doubling GPT-4o-mini's violations (3.8 to 7.2 per session), and (3) proportional compliance, clamping movement speed to the rule-specified maximum rather than refusing, emerges consistently only in Gemini; the preliminary simulation layer reproduces the model ranking and the GPT-4o-mini failure-mode inversion.
Read the full abstract

Solar and Stellar Astrophysics

Statistical structure and physical interpretation of the fillout factor distribution in contact binary stars

Contact binary systems exhibit complex evolutionary behavior governed by mass transfer, angular momentum loss (AML), and Roche geometry. The fillout factor ($f$) is widely used as a descriptor of the degree of overcontact, yet its physical and statistical role remains nonuniformly defined across the literature. We used a compiled observational sample of W UMa-type contact binaries to construct a data-driven classification framework based on $f$ and its relation to fundamental system parameters. Unsupervised clustering applied to the one-dimensional $f$ distribution reveals a robust three-class structure corresponding to shallow-, medium-, and deep-contact configurations. The statistically determined boundaries are located at $f \simeq 0.257$ and $f \simeq 0.561$, with a stable silhouette score of $S \simeq 0.613$. The stability of this classification is confirmed through perturbation tests in $f$ and parameter-conditioned samples. A random forest regression model shows that 60.7% of the variance in $f$ can be explained by the considered physical and geometric system parameters, with geometric parameters providing the largest predictive contribution. Among the considered parameters, the mass ratio emerges as the dominant predictor. The identified subclasses therefore appear to reflect a continuous geometric sequence rather than discrete physical states, governed by the progressive evolution of the Roche equipotential configuration under mass transfer and AML. Notably, the second boundary separating medium- and deep-contact systems shows lower stability than the first boundary, suggesting that the transition toward deep contact may be more sensitive to the physical composition of the analyzed sample.
Read the full abstract

All authors A. Poro, K. Li, E. Paki, F. Alicavus, N. Alan

Sound

TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models

Large audio-language models (LALMs) can hallucinate audio objects, answering "yes" to absent sound events, thus undermining reliability in audio question answering. We propose Token-Adaptive Decoding (TAD), a training-free strategy for hallucination mitigation that grounds the initial yes/no decision by contrasting logits under real audio with a matched silent reference. TAD introduces a token-adaptive, confidence-guided gate that is decision-critical at the first decoding step and class-conditional on affirmative tokens, using the audio-silent margin to avoid overcorrection when evidence is weak or already sufficient. Experiments on AudioCaps-Hallucination show that, relative to Audio-Aware Decoding (AAD), a contrastive baseline with fixed contrast strength, TAD improves F1 for Qwen2 by 0.059 to 0.117 across Popular, Adversarial, and Random splits, and for Gemma by 0.025 to 0.064, while on Clotho-AQA it raises F1 from 0.810 to 0.816 on Qwen2 and remains comparable to AAD on Gemma.
Read the full abstract

All authors Heyu Chang, Nianwen Si, Hao Zhang, Wenlin Zhang, Dan Qu

Combinatorics

Ramsey multiplicity and extremal colorings for odd cycles

The Ramsey number $r(H)$ of a graph $H$ is the minimum positive integer $N$ such that every red/blue edge-coloring of the complete graph $K_N$ on $N$ vertices contains a monochromatic copy of $H$. The Ramsey multiplicity $M(H,n)$ is the minimum number of monochromatic copies of $H$ over all red/blue edge-colorings of $K_n$. It is called threshold Ramsey multiplicity if $n=r(H)$, and denoted by $m(H)$. The only previously known general infinite family for which $m(H)$ has been determined is stars, due to Harary and Prins (1974). Let $C_k$ denote a cycle on $k$ vertices. Conlon, Fox, Sudakov, and Wei (2022) conjectured that $m(C_k)=(k-1)!/2$ for every sufficiently large odd integer $k$. In this paper, we determine $M(C_k,r(C_k)+\ell)$ for every fixed nonnegative integer $\ell$ and all sufficiently large odd $k$, and characterize all extremal colorings, thereby confirming the conjecture. This is also a second general infinite family for which $m(H)$ has been determined.
Read the full abstract

All authors Ting Huang, Junying Lu, Jiabao Yang, Yaojun Chen

Quantum Physics

Implementing QESEM's High-Accuracy Error Mitigation on a Quantum Computer: a Water Potential Energy Surface Study

Quantum error mitigation (QEM) is essential for extracting chemically accurate results from near-term quantum hardware. Many widely used QEM methods rely on uncontrolled heuristics whose bias depends on the specific circuit and noise realization. In this work, we employ QESEM—a characterization-based, unbiased quasi-probabilistic mitigation method—on IBM's Aachen quantum processor to compute the ground-state potential energy surface (PES) of the symmetrically-stretched water molecule. We consider a classically-optimized, single-layer perfect-pairing tiled unitary product state ansatz. We map this ansatz to an 8-qubit register corresponding to a (4,4) active space and the STO-3G basis set. Compared to the statevector reference, we find that raw QPU results typically overestimate the ground-state energy by around 500~mHa across the scanned geometries. On the other hand, QESEM-mitigated results fall approximately within 100~mHa, 30~mHa, or “chemical accuracy” ($\sim$1.5~mHa), depending on the target precision. We benchmark QESEM at both loose (0.1~Ha) and tight (0.01~Ha) precision targets, evaluating both individual and merged batches of runs. As the precision target is tightened, the accuracy improves systematically, matching or exceeding results reported in the literature. We further quantify the sampling cost of these results, reporting the number of shots required at each precision level. Our results show how, with the current levels of hardware error, reaching the highest accuracies demands substantial QPU time. The results demonstrate that the characterization-based, unbiased error mitigation provided by QESEM allows to measure quantitatively meaningful potential energy surfaces on current quantum hardware. Concurrently, they highlight the sampling overhead associated with QEM, which remains a central bottleneck en route to larger chemical problems and higher precision.
Read the full abstract

All authors Renato Olarte Hernandez, Emanuele Rossi, Sonia Coriani, Karl Michael Ziems, Erik Kjellgren, Jacob Kongsted, Tali Shnaider, Stephan P. A. Sauer

Statistical Methodology

Efficient model exploration with the integrated nested Laplace approximation

Model and variable selection are important topics in Bayesian inference. In particular, the selection of different fixed, random effects and hyperparameters in hierarchical models can be difficult because of their complex structure. In this paper, we introduce the use of approximate Bayesian inference for model and variable selection for hierarchical Bayesian models. The approach is based on the application of Markov chain Monte Carlo methods on the model space. In particular, the Metropolis-Hastings algorithm is used to sample from the set of model indices. In this way, the marginal likelihood is used to compute the acceptance probability so that it is not required to estimate the parameter models directly. For this, the integrated nested Laplace approximation (INLA) is used because it provides accurate estimates of the marginal likelihood and it can also provide estimates of the posterior marginal of the model parameters. This method can be applied not only to variable selection but to a wide range of problems subject to model uncertainty. To illustrate the potential of this approach, examples on variable selection, changepoint models and log-Gaussian Cox processes are developed.
Read the full abstract

Computation and Language

Separating Stream Stability from Long-Term Recall in Language Models

Methods for streaming language models are often discussed alongside long-context and memory systems, although they solve different problems. An attention sink can stabilize autoregressive generation over an indefinitely long stream while the model remains unable to use content that has left its recent-token cache. We argue that this distinction should be explicit in system claims and evaluation. We introduce three horizons: the stability horizon, over which predictive behavior remains well behaved; the access horizon, over which past content can still causally affect the output; and the utility horizon, over which a task retains acceptable performance. We show constructively that the stability horizon can be infinite while the access and utility horizons are finite. We then propose ThreeH, an evaluation contract that measures all three horizons under a common state and compute budget. Applying the framework to attention-sink streaming clarifies its strength, constant-memory, stable generation, without treating anchor tokens as semantic memory. The framework exposes roles for cache policies, recurrent state, retrieval, and external memory. Experiments on 128K-token streams, delayed binding recall, and delayed decisions show that attention sinks preserve local modeling but not content beyond the active cache; recurrent and retrieval state extend the semantic horizon.
Read the full abstract

All authors Peipei Cao, Xin Zhang, Jie Tang, Xiao Li, Siying Li, Qing Pei