Peer Revenue Publish or profit

Papers

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

All of arXiv

Saturday 3 October

Astrophysics of Galaxies

Finding the evolutionary link between ULIRGs and radio galaxies

Ayisha Fida, Sumana Nandi, Mousumi Das et al. (+4 more)

Ultraluminous infrared galaxies (ULIRGs) are the remnants of the major mergers of gas-rich galaxies. They are dusty systems and are extremely luminous in the infrared. Both starbursts and active galactic nucleus (AGN) activity supply power in these systems, but it is not clear how these two activities are related to the overall evolution of the merger remnant. Studies suggest that there may be an evolutionary link between ULIRGs and radio galaxies. Radio observations of ULIRGs are a useful tool for understanding this evolutionary path as well as studying the energy contributions from starbursts and AGN. We perform a systematic census of these signatures in 38 ULIRGs using upgraded Giant Metrewave Radio Telescope observations and archival radio data. In the sample, 30 sources have enough frequency coverage to obtain their radio spectrum. Of these, 17 sources show a turnover frequency between 63 and 509 MHz and a spectral age variation from 0.009 to 44 Myr. Also, eight sources have extended structures with projected linear sizes varying from 0.7 to 11 kpc. Our results indicate that the primary energy source in these systems is the AGN rather than star formation. The majority of the ULIRGs in our sample, particularly those in the post-merger stage, exhibit gigahertz-peaked spectrum or compact steep spectrum-like characteristics, suggesting that they are evolving into young radio galaxies. We note that six sources with high star formation activity show a low-frequency turnover and a smaller spectral age; we confirm these six sources host buried AGN. This study enables us to trace the evolutionary link between ULIRGs and radio galaxies.
Read the full abstract

All authors Ayisha Fida, Sumana Nandi, Mousumi Das, K. Rubinur, S. Shanbhog, Preeti Kharb, Barenya Dev

Machine Learning

Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures

Yanglin Zhang, Anneke von Seeger, Gilad Lerman et al. (+1 more)

We develop a principled framework for constructing neural networks whose specific parameter realizations admit an explicit algorithmic interpretation. Existing algorithm-inspired architectures can explain the computational structure of a network, yet after standard training the learned parameters need not retain a clear relation to the motivating algorithm. We address this gap as follows. First, we model each data point as a sample of a class-dependent stochastic process and assume that statistics of this process can be estimated from a single sample and these statistics are sufficient to distinguish the classes. We then construct a neural network whose initial parameters exactly implement an algorithm for estimating these statistics, making the network fully interpretable. To account for mismatch between the idealized model and real data, we fine-tune this network while controlling its deviation from the algorithmic initialization. The trained network hence roughly retains the interpretation of the initial network. A PAC-Bayesian analysis yields a uniform generalization bound whose complexity term scales with the fine-tuning radius, providing a statistical motivation for our approach. We instantiate the framework for texture classification using the scattering transform to estimate the discriminative statistics.
Read the full abstract

All authors Yanglin Zhang, Anneke von Seeger, Gilad Lerman, Ron Levie

Computers and Society

Large Language Models and Augmented Democracy

Jairo Gudiño-Rosero

Artificial intelligence enables computational agents to represent political preferences and take part in collective decision-making. In this thesis, I investigate the opportunities and challenges of digital twins (DTs) based on Large Language Models (LLMs) as intermediaries in augmented democracy, focusing on individual preference representation, collective representation of political organizations, and the vulnerability of those representations to attackers. First, using data from an online experiment in Brazil, I examine whether personalized DTs can predict citizens' preferences for unseen policy proposals. Second, I extend the DT framework from individuals to political organizations. Using Swiss parliamentary data, I build topic-specific knowledge graphs from lawmakers' legislative records and connect them to LLM-based lawmaker agents, which are organized into party-level DTs representing collective positions. Agentic deliberation among these agents tests whether aggregated party representations capture a broader range of intra-party perspectives than official party communications. Finally, I study the vulnerability and robustness of LLM-mediated deliberation against prompt-injection attacks that amplify viewpoints, suppress opinions, or redirect consensus. Using data from a 2023 deliberative experiment in the United Kingdom, I analyze how attack effectiveness varies with the distribution of opinions and rhetorical strategies, and evaluate a pipeline combining injection detection, structured opinion representations, and reinforcement learning to improve resistance. These findings characterize the opportunities and challenges of LLM-based digital twins in augmented democracy, stressing accurate preference representation, faithful aggregation, and robustness to strategic interaction.
Read the full abstract

Analysis of PDEs

Complete classification of solutions for spin-1 Bose-Einstein condensates in R

Xiao Luo, Cunxin Wei, Juncheng Wei et al. (+1 more)

Spin-1 Bose-Einstein condensates provide a fundamental platform for exploring quantum magnetism and coherent spin dynamics. Their three Zeeman components are coupled by spin-exchange interactions under conserved particle number and magnetization, giving rise to rich magnetic phases and nonlinear spin structures; a rigorous classification of stationary states therefore clarifies the possible spin configurations and their physical origins. In this paper, as a continuation of our previous work \cite{LLWZ23,LLWZ24,LLWZ26}, we study the classification of solution for the spin-1 Bose-Einstein condensates in $\mathbb{R}$, by applying the non-standard Hirota's bilinear method, the determinant formula and the general left-uniqueness strategy, we present some novel explicit solution and give the complete classification of the solutions. In comparison with the classical Hirota's method, the non-standard Hirota's method needs to introduce auxiliary functions to construct Hirota's bilinear form, which essentially adds additional constraint on the wave functions, so that it possible to deal with more complex equations. As far as we know, this is the first systematic study the complete classification of solutions to the spin-1 Bose-Einstein condensates. Our classification results yields experimentally testable predictions for spin populations, relative phases, and magnetic textures
Read the full abstract

All authors Xiao Luo, Cunxin Wei, Juncheng Wei, Maoding Zhen

Fluid Dynamics

Excitation of non-modal perturbations in hypersonic boundary layers by free stream forcing. Part III: effects of wall temperature and nose bluntness

Lei Zhao, Mingze Sun, Qinyang Song et al. (+1 more)

This paper constitutes Part III of a series investigating the excitation of non-modal perturbations in hypersonic blunt-nose boundary layers. Based on the numerical shock-fitting harmonic linearised Navier-Stokes (SF-HLNS) approach presented in Part I (Zhao & Dong, J. Fluid Mech. 2025, vol. 1013: A44) and the asymptotic analysis developed in Part II (Dong et al., J. Fluid Mech., under review), the present work focuses specifically on the influence of nose bluntness (Reynolds number R) and wall temperature T_w on receptivity efficiency through seven detailed case studies. Analysed via the three-step asymptotic model, the downstream perturbation amplitude is governed by two distinct factors: the stagnation vorticity perturbation, determined through shock-perturbation interaction and the slow-down convection mechanism, and the parabolic evolution of non-modal perturbations driven by the lift-up mechanism. Increasing R strongly amplifies the stagnation vorticity response, with only mild enhancement of the lift-up effect. In contrast, decreasing T_w strengthens the stagnation vorticity perturbation, but slightly weakens the lift-up effect; the net result is an overall intensification of the downstream perturbation amplitude with decreasing T_w. Furthermore, explicit scaling laws for receptivity efficiency with respect to R and T_w are established. This study completes the theoretical foundation for non-modal receptivity in hypersonic blunt boundary layers, and serves as a key step toward a physics-based transition prediction framework.
Read the full abstract

All authors Lei Zhao, Mingze Sun, Qinyang Song, Ming Dong

Computation and Language

Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents

Peigui Qi, Kunsheng Tang, Yide Song et al. (+2 more)

Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools or generating invalid calls. Existing mitigation methods report substantial improvements, yet we identify a previously overlooked failure mode that we term Hallucination Escape. These methods reduce hallucination on the tool configuration they are tuned on but increase it on other configurations, canceling out the gain. We further investigate this phenomenon and find that hallucination rises sharply when a model's intrinsic tool-use tendencies conflict with the current tool configuration, and that existing methods reinforce rather than suppress these tendencies, which in turn contributes to hallucination escape. Building on these findings, we propose EscapeGuard, a training-free inference-time method that combines conflict-aware gating with configuration-derived attention enhancement to mitigate tool hallucination while preventing hallucination escape. Across six benchmarks on various models, EscapeGuard reduces tool-selection hallucination by 9.0 pp and suppresses hallucination escape, lowering the cross-configuration mean by 23.7 pp and achieving an 89.1% net improvement in paired-query evaluation. We hope this work can encourage evaluation beyond a single tool configuration and pave the way for more reliable tool-using LLM agents.
Read the full abstract

All authors Peigui Qi, Kunsheng Tang, Yide Song, Weiming Zhang, Nenghai Yu

Artificial Intelligence

TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models

Martin Maritsch, Timo Stoffregen, Thomas Kaar et al. (+36 more)

Temporal Foundation Models (TFMs) aim to generalize across domains, datasets, and tasks. Yet, their development remains constrained by fragmented, task-specific data formats, annotations, and processing pipelines. We introduce TimeNet, an open-source data standard and scalable infrastructure that decouples temporal data from task definitions and represents signals, metadata, annotations, and supervision in a shared, extensible data model. TimeNet supports multimodal signals with regular, irregular, or ordinal time axes and expresses different task families (including classification, forecasting, temporal localization, question answering, generation, and editing) as reusable views over the same recordings. This shared representation enables heterogeneous time-series datasets to be combined for large-scale model training across domains, modalities, and tasks. We demonstrate TimeNet by transcoding datasets with 1.5M task instances spanning diverse domains, modalities, temporal scales, and forms of supervision, while retaining practical I/O performance relative to native formats. TimeNet enables an existing TFN training pipeline to support joint training on a configurable number of heterogeneous datasets through configuration changes alone. We show this capability by training TFM across multiple datasets and tasks, obtaining a 14% F1 score improvement compared with models trained on individual datasets. These results show that TimeNet provides the data and systems foundation needed to move beyond task- and dataset-specific TFMs toward models that can learn jointly across heterogeneous domains, modalities, temporal scales, and forms of supervision from a common data model.
Read the full abstract

All authors Martin Maritsch, Timo Stoffregen, Thomas Kaar, Behsad Riemer, Maxwell A. Xu, Max Rosenblattl, Juncheng Liu, Nicolas Zumarraga, Yu Yvonne Wu, Denys Herasymuk, Sparsh Rastogi, Hyungjun Yoon, Bosong Huang, Arvind Pillai, Dmytro Lopushanskyy, Tony Chen, Robin Deuber, Yichen Liu, Shvat Messica, Dan Li, Jian Lou, Yuwei Zhang, Jaeho Kim, Renée Rosillo Garcia, Fan Wu, Robert Müller, Elgar Fleisch, Flora D. Salim, Dimitris Spathis, Yuzhe Yang, Aaqib Saeed, Daniel McDuff, Ming Jin, Markus Kreft, Kevin O'Sullivan, Robert Jakob, Azul Garza, Paul Schmiedmayer, Patrick Langer

Robotics

Reachability-Guided Sequential Quadratic Programming-Guarded Model Predictive Path Integral for Safe Nonlinear Predictive Control

Alexandre Didier, Jason J. Choi, Namhoon Cho et al. (+2 more)

Safe robot control often requires combining long-horizon performance optimization with hard state and input constraints, but existing approaches tend to address this tradeoff partially. Sampling-based model predictive control (MPC) methods such as model predictive path integral (MPPI) are effective in handling nonlinear and nonconvex environments, yet their finite-sample rollouts and unconstrained weighted-average update can return an unsafe control. Deterministic nonlinear MPC can explicitly incorporate constraints, but its real-time safety and performance depends strongly on warm starts and local convergence. Hamilton–Jacobi reachability (HJR) provides rigorous safety certificates, but offline value-function computation remains practical only for reduced-order models. We propose ReSQ-MPPI, a reachability-informed generation–refinement architecture that combines these complementary strengths. An HJR value function computed offline for a reduced-order model guides online MPPI sampling toward safe, promising trajectory candidates. The MPPI solution is then refined by a small number of sequential quadratic programming (SQP) iterations in a full-order MPC problem. A key observation is that the standard MPPI inference step is an unconstrained weighted least-squares problem; ReSQ-MPPI replaces it with a constrained MPC refinement that recovers the MPPI update when it is feasible and minimally modifies it otherwise. Simulations in cluttered navigation and autonomous racing environments demonstrate that ReSQ-MPPI improves safety and performance over standalone MPPI, MPC, and reachability-filtered sampling-based control baselines.
Read the full abstract

All authors Alexandre Didier, Jason J. Choi, Namhoon Cho, Claire J. Tomlin, Melanie N. Zeilinger

Machine Learning

CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations

Jeahan Jung, Heechang Kim, Hyomin Shin et al. (+1 more)

Despite the growing popularity of physics-informed neural networks (PINNs), their applicability in the long-time integration of partial differential equations (PDEs) remains constrained. We argue that this problem stems from the lack of consideration of temporal causality in the original PINN formulation, resulting in a bias towards satisfying governing equations at later times before learning the initial condition and hence leading to erroneous solutions. To this end, we propose a novel method that seamlessly integrates temporal causality into the training process. Drawing inspiration from classical numerical methods where the temporal causality is reflected, we divide the time domain into nonoverlapping subintervals, assign a unique neural network to each subinterval, and construct a loss function founded on the integral form of PDEs within these subintervals. The proposed networks undergo sequential training, beginning with the initial time step. Our method demonstrates significant improvement in accuracy for long-time simulations of various PDE problems where the original PINN method fails while it requires less computational cost and memory compared to the PINN method. A parallelization algorithm is provided to further enhance the computational efficiency, showing a significant speedup for solving time-dependent PDEs.
Read the full abstract

All authors Jeahan Jung, Heechang Kim, Hyomin Shin, Minseok Choi

Data Structures and Algorithms

Fair Diversity Maximization via Local Search

Mohammad Ansari, Sina Azizeddin, AmirMohammad Bandari et al. (+2 more)

Diversity maximization is a fundamental optimization problem with applications in machine learning, data summarization, information retrieval, and recommendation systems. In many such applications, the data are partitioned into groups, and the selected subset must satisfy prescribed group quotas. We study Fair Diversity Maximization: given a set of points in a metric space partitioned into $m$ groups, the goal is to select exactly $k_i$ points from each group $i$ while maximizing the minimum pairwise distance among the selected points. The best previously known approximation guarantee is $m+1$, which grows linearly with the number of groups. We show that this dependence on $m$ is not fundamental. We present a new local-search framework that yields a $4$-approximation for any constant number of groups, with no restrictions on the metric space or on the size of the selected set. To the best of our knowledge, this is the first constant-factor approximation whose guarantee is independent of the number of groups in this general setting. Our framework maintains all group quotas exactly while progressively eliminating violations of the diversity objective. We further develop a specialized algorithm for two groups that achieves a $2$-approximation, improving the previous best factor of $3$. This factor is optimal: unless $\mathrm{P}=\mathrm{NP}$, no polynomial-time algorithm can achieve an approximation factor strictly better than $2$, even for the unconstrained case.
Read the full abstract

All authors Mohammad Ansari, Sina Azizeddin, AmirMohammad Bandari, Pouria Mahmoudkhan, Hamid Zarabi-Zadeh

Computation and Language

Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define

Saurabh Kumar Singh, Yogeshwar Singh Dadwhal and Malhar Vedak

Post-training quantization to the GGUF format's mixed-precision K-quants is commonly how open-weight language models reach consumer hardware, yet its effect on fine-grained lexical competence is uncharacterized. We audit 27 quantized artifacts across 13 families and four architecture backbones, 0.35B-14B parameters, evaluated down their published ladder to Q2_K (about 2.6 bits per weight), on 429 frequency-validated rare English words under two probes: surface inclusion of a prompt-supplied word and its one-sentence definition, scored by a tiered multi-synonym matcher, its error measured by a blind LLM-judge census of every definition, with human verification. Three regimes emerge at Q2: total collapse into unusable builds, severe semantic dissociation in sub-2B models, and mostly robust preservation above about 3B. In every sub-2B artifact, definitions fall 20-67% below the artifact's baseline, typically several times the inclusion loss. Two controls separate rarity from task difficulty: within the rare set, loss rises with rarity in six of seven sub-2B artifacts, and on a 100-word common-word set rare words lose more than common words in all eight, significantly in six. Tokenizer vocabulary size does not predict the damage (Spearman rho=0.12); parameter count dominates (rho=0.72), confirmed within five of six same-tokenizer families. Q4_K_M remains lexically clean at >=1B. The damage is frequency-graded, provider-dependent, and not calibrated by WikiText-2 perplexity: across nine artifact-matched ladders, near-identical Q2 penalties (44.7%/47.6%) separate an artifact keeping its definitions (3.6%) from one losing them (43.6%). Aggressively quantized small models can keep generating fluent text while no longer knowing what it means, risking hardware-constrained deployments in domains where semantics carries consequences. Validation must be per artifact.
Read the full abstract

Distributed Computing

Budget-Constrained Fault-Tolerant Mutual Visibility for Autonomous Robots under the Mobility Fault Model

Prakhar Shukla, Animesh Maiti, Shivam Kumar et al. (+1 more)

We investigate the mutual visibility problem for a swarm of $n\ge3$ autonomous mobile robots under the budget-constrained mobility fault model. The robots are opaque, so if three robots are collinear, the middle robot obstructs the visibility between the other two. Each robot is assigned a finite movement budget, reflecting its limited energy, that bounds the total distance it may traverse during the execution. Moreover, an arbitrary number of robots may become permanently immobile due to mobility faults. The objective is to design a distributed algorithm that enables the non-faulty robots to coordinate their movements so that, within a finite time, every non-faulty robot attains unobstructed visibility of all robots in the system, including the faulty ones, while respecting the prescribed movement budget. We consider luminous robots operating under the $\mathsf{SSYNC}$ model with non-rigid movements, without any agreement on their local coordinate systems, and equipped only with a common fixed reference point. We present a deterministic distributed algorithm that solves the problem despite an arbitrary number of mobility faults. The algorithm guarantees mutual visibility for the non-faulty robots, respects the movement budget of every robot, provides collision-free movements for the robots, and uses only 12 light colors.
Read the full abstract

All authors Prakhar Shukla, Animesh Maiti, Shivam Kumar, Subhash Bhagat

Computation and Language

Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media

Safaruzzaman Shovo, Monowar Islam, Asif Hossain et al. (+2 more)

Public vs. private universities is a debatable issue, and it creates polarization on social media in Bangladesh. Debate on quality, jobs, and prestige is passionate among the students, parents, and graduates, the majority of whom speak Bengali, a low-resource language. To measure this polarization, this paper introduces a manually annotated dataset of 4,060 Bengali comments labeled as Pro-Public, Pro-Private, or Neutral. We evaluated the quality of our annotations by Fleiss's Kappa agreement that was 0.89, corresponding to a high agreement among annotators. The classical ML (SVM, Random Forest, XGBoost), BiLSTM network, hybrid BanglaBERT+XGBoost models and the state-of-the-art zero-shot LLMs (Claude Sonnet 4, DeepSeek-V3.1, Llama 4 Maverick, Kimi K2 Thinking, Qwen3-235B Thinking) models are evaluated. The accuracy of BanglaBERT+XGBoost is 91.81% and macro F1 score is 91.70%, which is higher than all the supervised baselines. The zero-shot Llama 4 Maverick Thinking achieves a macro F1 of 0.931 (overall accuracy of 93.31%) without any fine-tuning. All machine learning (ML), deep machine learning (DL) and transformer models were outperformed by the zero-shot Llama 4 Maverick model. Polarization also is evident, in some ways more clearly in the Pro-Private comments, which emphasize modern facilities and timely graduation, versus the Pro-Public comments, which emphasize affordability and government jobs. Our findings open new directions for analyzing social media polarization in low-resource languages.
Read the full abstract

All authors Safaruzzaman Shovo, Monowar Islam, Asif Hossain, Sameya Akhter, Md. Shamsul Islam

Computation and Language

XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions

Zhanxun Liu, Yifan Duan, Hengtao Wu et al. (+7 more)

General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking. Existing turn detectors use heterogeneous, task-specific label spaces and are often trained on limited annotations or evaluated on isolated utterances, making them difficult to use as a unified causal controller with comprehensive context. We propose XTurnix, a compact text-based model that formulates turn control as two binary decisions conditioned on the AI's current listening or speaking state and predicts a single control token from the complete dialogue history. XTurnix is pretrained on 5.5 million causal action examples automatically derived from timestamped two-speaker transcripts, then fine-tuned on synthetic multi-turn examples with a flatter distribution across the four state-action labels. We evaluate XTurnix on four public benchmarks and a balanced self-curated benchmark. Across the public benchmarks, XTurnix achieves the best results on all SemanticVAD and LiveKit splits, ties the native Smart-Turn model on Smart-Turn Bench, and achieves the highest incomplete-turn accuracy on Easy-Turn. On the self-curated benchmark, it reaches 89.06% accuracy, more than 20 percentage points above the strongest third-party baseline at 68.75%, while maintaining F1 scores between 84.21% and 90.63% across all four categories. These results demonstrate unified listening- and speaking-state turn control in a single compact model. Code is available at https://github.com/xcc-zach/xturnix, with an interactive demo at https://huggingface.co/spaces/xcczach/xturnix-demo.
Read the full abstract

All authors Zhanxun Liu, Yifan Duan, Hengtao Wu, Chen Yang, Qinyuan Cheng, Kun Wang, Xingyu Zeng, Xipeng Qiu, Chaochao Lu, Xie Chen

Computation and Language

GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization

Kunsheng Tang, Peigui Qi, Yide Song et al. (+3 more)

Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access to model internals, making them impractical for frozen checkpoints. We investigate whether glitch tokens can be repaired outside the model by optimizing the input tokenization. An empirical study on BPE merge-rule deletion reveals that (1)deleting a glitch token's merge rule can fix a substantial fraction of failures, yet disrupting normal tokens sharing intermediate merge nodes causes the overall glitch rate to rise, and (2)different decomposition granularities yield non-monotonic fix rates while collateral damage on normal tokens grows monotonically. Motivated by these findings, we propose GlitchPatch, a repair framework for frozen language models based on local retokenization, consisting of two stages: the offline stage uses Behavioral Path Optimization (BPO) to find the behaviorally optimal replacement token sequence for each glitch token and compiles validated replacements into a rule table; the online stage substitutes only the IDs of matched glitch tokens in the canonical token sequence, with no modification to model parameters or internal states. Experiments on ten models spanning six tokenizer families show that GlitchPatch achieves an 85.10% mean fix rate, outperforming the strongest baseline by 14.37 percentage points, and reduces the average glitch rate from 14.88% to 2.27%. GlitchPatch achieves a 0.00% RR in full-vocabulary evaluation and leaves rule-unmatched inputs unchanged by design. We further evaluate the practical impact of repair from the perspectives of time cost, language understanding, and capability, supporting its deployment feasibility. We hope this work provides a practical option for improving tokenizer reliability.
Read the full abstract

All authors Kunsheng Tang, Peigui Qi, Yide Song, Peijun Huang, Weiming Zhang, Nenghai Yu

Functional Analysis

Effective Dimensions in Grothendieck–Hölder Inequalities

Joedson Santos and Diana Serrano-Rodríguez

What becomes of Grothendieck's inequality when its Hilbert-space vectors are replaced by vectors in $\ell_p^r$ and $\ell_{p'}^r$? For an $m\times n$ matrix, we show that the universal dimensional loss is governed not by $r$ alone, but by the effective dimension \[ d=\min\{r,m,n\}. \] More precisely, the optimal constant is bounded above and below, up to dimension-free factors, by \[ d^{|1/p-1/2|}. \] The upper bound rests on a pointwise Hilbertian stabilization: for every matrix $A$, \[ G_2^{(r)}(A)=G_2^{(d)}(A). \] Combining this stabilization with Lewis's Euclidean distortion estimate gives the effective-dimensional Grothendieck–Hölder bound. Beyond the universal power law, we retain the finer rectangular geometry. At $p=\infty$ we prove the exact compression formula \[ \Gamma_\infty^\K(r;m,n) = \rho\!\left( \ell_1^m(\K), \ell_1^{\min\{r,n\}}(\K) \right), \] and derive from it endpoint-sensitive lower bounds throughout the full Hölder scale. Over the complex field, interpolation between the Hilbertian problem and the exact rectangular endpoints yields corresponding upper bounds. Thus the effective dimension determines the universal exponent, whereas the tensor-norm endpoint retains additional aspect-ratio information. We determine the boundedness threshold when $p$ approaches $2$: it is governed by \[ |1/p-1/2|\log d. \] For complex two-row matrices, the endpoint tensor ratios are explicit, and the general rectangular estimates give quantitative two-sided bounds for every $1\le p\le\infty$.
Read the full abstract

High Energy Physics (Experiment)

Simultaneous measurement of the Higgs boson decay rates to WW and ZZ in fully hadronic final states at FCC-ee

Jan Eysermans, Mila Pandurovic, Christoph Paus et al. (+2 more)

The precise determination of the Higgs boson couplings to electroweak gauge bosons is a key objective of the FCC-ee physics program. In particular, measurements of the Higgs boson couplings to W and Z bosons play a central role in the model-independent determination of its total decay width. This paper presents a study of Higgs boson decays to H -> WW and H -> ZZ in the Higgsstrahlung production process. The analysis focuses on events in which the associated Z boson and the vector bosons from the Higgs decay all decay hadronically, resulting in six-jet final states. The large H -> WW branching fraction leads to high signal statistics in the fully hadronic channel, while for H -> ZZ the much smaller Higgs branching fraction is partly compensated by the large hadronic branching fractions of the Z bosons. Due to the substantial kinematic overlap between the WW and ZZ decay modes, their signal strengths are extracted simultaneously. Jet-clustering and dedicated jet-pairing techniques are employed to optimize the reconstruction of the hadronically decaying gauge bosons and enhance the separation of the two signal components. Assuming a center-of-mass energy of 240 GeV and an integrated luminosity of 10.8 ab^-1, expected relative uncertainties of 1.48% and 8.20% are obtained on the production cross section times branching fraction, sigma(ZH) x BR, for the H -> WW and H -> ZZ decay modes, respectively.
Read the full abstract

All authors Jan Eysermans, Mila Pandurovic, Christoph Paus, Michele Selvaggi, Aman Desai

Cryptography and Security

JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness

Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian et al. (+13 more)

Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. However, intermediate feature representations are simultaneously exposed to hardware faults and adversarial attacks, which are traditionally evaluated independently. This paper presents a unified framework for the joint assessment of reliability and security in Split Computing. First, reliability is characterized through neuron-level fault injection using the Mean Relative Accuracy Degradation (MRAD) while security through feature-map-aware adversarial attacks simulations using the Attack Success Rate (ASR). Based on these complementary analyses, the Joint Vulnerability Score (JVS) is introduced, along with a confidence-aware extension that jointly captures prediction errors and confidence degradation. The framework is evaluated on ten Split Computing configurations based on ResNet-50 trained on ILSVRC-2012. Experimental results show substantial differences across compression strategies, with MRAD ranging from 44.3% to 61.2% under fault injection, while adversarial attacks achieve up to 98.8% ASR. Furthermore, the proposed joint metrics reveal vulnerability trends that remain hidden when reliability and security are analyzed independently, providing a more comprehensive methodology for designing dependable Split Computing systems.
Read the full abstract

All authors Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian, Rama Mounika Kodamanchili, Juan David Guerrero Balaguera, Juan Esteban Rodriguez Condia, Annachiara Ruospo, Roberta Siciliano, Stefano Di Carlo, Maksim Jenihhin, Marco Levorato, Alessandro Savino, Matteo Sonza Reorda, Christian Herglotz, Michael Hübner, Mahdi Taheri

Classical Analysis and ODEs

Projection theorems for macroscopic intermediate dimensions

Jinjun Li and Lifeng Xi

We introduce lower and upper macroscopic intermediate dimensions of unbounded subsets of Euclidean space by combining covering contributions from all dyadic annuli beyond a given scale. For every unbounded Borel set $E\subset\R^d$ and $m\in \{1,\ldots,d-1\}$, we prove that the macroscopic intermediate dimensions of $P_VE$ equal the corresponding intrinsic capacity profiles for almost every $m$-dimensional linear subspaces $V\subset \R^d$. One full-measure set works for both dimensions and every parameter $\theta\in[0,1]$. The proof combines a covering–capacity comparison with an exponent gap, fractional-moment estimates for projected coverings, and capacity-weighted retention of source shells. The dimensions recover macroscopic Hausdorff dimension at parameter zero, are invariant under quasi-isometries, and are continuous at positive parameters. The upper macroscopic intermediate dimension agrees with the upper discrete intermediate dimension introduced in \cite{LXZ}, whereas the lower one can differ. We compute the projected dimensions of bounded-base discrete digit Moran sets, including the self-similar case obtained when the bases and digit sets are constant, and give applications to Lipschitz graphs and arithmetic sumsets.
Read the full abstract

Mathematical Physics

A Self-Generated Local Structural Prior for Resolving Target Merging in Electrical Impedance Tomography (EIT)

Junkang Liu and Yizhuang Song

Electrical impedance tomography (EIT) is an ill-posed inverse imaging technique with limited and spatially nonuniform resolution. Conductivity targets located in regions with degraded spatial sensitivity may be reconstructed as a single connected region, resulting in the loss of spatial separability between neighboring structures. In this work, we propose a self-generated local structural prior for suppressing target merging in EIT reconstruction. First, an initial conductivity image is obtained from the measured boundary data using an existing EIT reconstruction method. This reconstruction is subsequently used as a reference image to construct a Gaussian similarity matrix according to the intensity similarity between image pixels. The adaptively chosen eigenvector of the covariance matrix is then employed to extract the principal structural information of the reference image. A localized structural mask is constructed and incorporated into a subsequent EIT reconstruction to preserve the spatial separability of neighboring targets. Numerical and water tank experimental results demonstrate that the proposed method effectively separates neighboring conductivity targets that are merged by conventional EIT reconstruction methods.
Read the full abstract

Quantum Physics

Structural Conditions for Distributed Quantum Advantage

Sabina Drăgoi, María Gragera Garcés and Lirandë Pira

Circuit cutting runs a quantum computation on processors smaller than the circuit, at the price of classical knitting whose cost grows exponentially with the number of cut gates. Keeping this cost affordable is necessary but not sufficient for an advantage, since knitting classically easy subcircuits is itself classically easy. We formulate three requirements for distributed quantum advantage under a stated budget: affordable knitting, classical difficulty that survives the cut, and, for variational circuits, resolvable gradients. We prove that under stated assumptions knitting stays affordable when subcircuits grow behind a bounded interface and becomes exponentially expensive when fixed-width subcircuits multiply. We turn the requirements into screening criteria and apply them to eighteen circuit families. We identify finite local-depth circuits with bounded interfaces as a setting in which the requirements can coexist, with hardness established only in the worst case. As a classically verifiable proof of principle, we knit one gate joining two field-perturbed toric-code patches on an IBM Nighthawk processor for up to 142 spins, and confirm that the reconstruction can at least resolve the contact correlation beyond independent execution for up to 98 qubits.
Read the full abstract

Computer Vision

Detecting Defects that Matter: An Application-Driven Benchmark for Anomaly Detection in Manufacturing and Retail Logistics (VAND 4.0 Challenge)

Lars Heckler-Kram, Dorian Henning, Ashwin Vaidya et al. (+6 more)

Existing Anomaly Detection benchmarks are saturated and often unrealistic. As part of the VAND 4.0 Challenge, we introduce a hidden-test, application-driven benchmark across two deployment-critical domains: industrial manufacturing and retail logistics. In the Industrial Track (MVTec AD 2), the results reveal that unsupervised anomaly segmentation remains challenging: the best regular-setting method achieves only ~57% pixel-level $SegF_1$, indicating substantial room for improvement. Zero-shot approaches trail by ~15 $SegF_1$ points, confirming that task-specific training on normal data remains essential for precise defect localization. Robustness to distribution shifts remains a key open challenge and DINOv3-backbones clearly dominate this track. In the Retail Track (Kaputt 2), the results reveal that (1) supervised defect detection is approaching saturation for common defect types; (2) the best off-the-shelf VLM approach trails specialized models by ~28 AP, confirming that currently VLMs cannot replace fine-tuned detectors, (3) reference images did not prove helpful for top-performing approaches. Performance collapses on rare defects (spillage ~53 AP, missing units ~27 AP), where the supervised ceiling is bounded by data availability. To drive future progress in this domain, we provide a new low-prevalence retail AD dataset (Kaputt-Rare). Across both tracks, computational efficiency is assessed as a first-class metric combining performance, throughput, memory, and power consumption. We introduce a novel metric for measuring efficiency and reveal that that top-performing methods rely on heavy architectures while efficiency is largely neglected. Overall, we conclude that the community needs (a) more efficiency-aware method development, and (b) true anomaly detection approaches for rare defects and shifting conditions. https://sites.google.com/view/vand4-cvpr2026/challenge
Read the full abstract

All authors Lars Heckler-Kram, Dorian Henning, Ashwin Vaidya, Jan-Hendrik Neudeck, Ulla Scheler, Anton Milan, Samet Akcay, Paula Ramos, Sebastian Höfer

Robotics

AgenticTactileVLA: Contact-Guided Execution-Time Supervision for Generalizable Dexterous Manipulation without VLA Retraining

Elizaveta Semenyakina, Ivan Snegirev, Mikhail Kiselev et al. (+4 more)

Vision-language-action policies may predict a transferable manipulation strategy yet fail to realize it reliably on the encountered object: objects compatible with the same grasp differ in geometry and compliance, and visual feedback degrades under closure occlusion. AgenticTactileVLA is presented as an execution-time supervisor that shifts part of object-specific adaptation from prediction to physical interaction. A fixed VLA provides the approach and hand targets; the supervisor decides whether to remain transparent, refine finger flexion, retain or release the corrected configuration, return control to the VLA for retry, or select a compliant hand-control regime. It uses finger-position and motor-effort feedback as proprioceptive contact evidence and requires neither tactile sensors nor VLA retraining. On a Unitree G1 with a BrainCo Revo2 hand, a randomized matched-block evaluation on five objects held out from VLA training yields 61.3% completion for the base VLA, 72.0% for unconditional close-to-stall control, and 84.0% for the supervisor under a shared budget; the gain is positive on every object and persists under moderate pose perturbations. Ablations show the gain is not explained by extended closure alone, and that selective triggering reduces correction episodes by 65.7% with no detected change in completion. A retention audit shows acceptance predicts retention in 88.9% of held-out cases, while compliant objects expose conservative false rejection. A thin-walled-cup study demonstrates contextual routing to compliant control, matching an always-compliant reference. These results suggest that contact-guided execution-time adaptation can improve the object-level generalization of a fixed VLA to held-out objects by adapting physical realization without object-specific retraining.
Read the full abstract

All authors Elizaveta Semenyakina, Ivan Snegirev, Mikhail Kiselev, Miguel Altamirano Cabrera, Artem Lykov, Hajira Amjad, Dzmitry Tsetserukou

Machine Learning (Statistics)

Gaussian Flow Dynamics: Simulation-Free Neural SDE Learning Beyond One-Time Marginals

Grigory Bartosh and Christian A. Naesseth

Simulation-free training of latent Stochastic Differential Equations (SDEs) relies on a variational posterior process whose one-time marginals are tractable, typically Gaussian. Such marginals, however, do not determine the underlying dynamics: many processes share the same marginals while differing in their temporal structure, and existing parameterizations fix this structure implicitly, which restricts the posterior family and biases the learned model. We introduce Gaussian flow dynamics, which construct stochastic processes directly from smoothly evolving Gaussian marginals while making the marginal-preserving, or gauge, degrees of freedom explicit and parameterizable. The construction admits state-dependent diffusion coefficients and recovers every linear SDE with additive noise and a non-degenerate Gaussian initial distribution. Building on it, we propose Gauge Matching, a simulation-free method for latent SDE learning that combines Gaussian flow dynamics with the SDE Matching objective. Gauge Matching costs at most quadratically in the latent dimension per step, like SDE Matching, but learns the temporal structure of the posterior beyond its one-time marginals. It comes within a nat of Helmholtz-SDE, which computes the gauge from the prior Jacobian at cubic cost, on the linear benchmark where the exact posterior is known, matches it on nonlinear systems, and applies where Helmholtz-SDE does not, to state-dependent noise.
Read the full abstract

Numerical Analysis

Arbitrarily High-Order Structure-Preserving Parametric Finite Element Methods for Geometric PDEs via Local Pullback Flow Maps

Weizhu Bao, Yifei Li and Dongmin Wang

We develop arbitrarily high-order structure-preserving parametric finite element methods for geometric PDEs including surface diffusion and volume-preserving mean curvature flow based on local pullback flow maps. The central idea is to reformulate the geometric PDEs on an arbitrary intermediate hypersurface and represent the subsequent evolution through a local pullback flow map. Using admissible local pullbacks, we derive two formulations from the corresponding pullback identities for the Laplace-Beltrami operator, referred to as the conformal and equidistribution formulations. We discretize both formulations using arbitrary-degree isoparametric finite elements and Runge-Kutta collocation methods with positive weights. For the conformal formulation, weighted averages of the normal-Jacobian vector ensure exact preservation of the enclosed area or volume, while algebraic stability of the Runge-Kutta method additionally guarantees dissipation of the perimeter or surface area. For the equidistribution formulation, a path-averaged normal-Jacobian vector and a geometric discrete gradient guarantee both exact preservation of the enclosed area or volume and dissipation of the perimeter or surface area, without requiring algebraic stability. Numerical experiments confirm the expected high-order accuracy and structure-preserving properties.
Read the full abstract

Materials Science

Kilovolt-class Vertical (011) e̱ta}-Ga2O3 Schottky Diodes for High Voltage and High Temperature Applications

Emerson J. Hollar, Aaron M. Adams, Nolan S. Hendricks et al. (+2 more)

We report kilovolt-class vertical (011) e̱ta}-Ga2O3 Schottky diodes utilizing high-permittivity dielectric TiO2/Al2O3 field-plate for high voltage and high temperature applications. A systematic study was performed with Pt/(011) e̱ta}-Ga2O3 Schottky barrier diodes (SBDs) with varied diameters from 100 {\mu}m to 300 {\mu}m, for both with and without field-plate, that revealed excellent consistency of reverse blocking performance regardless of diode area. The field-plate SBDs achieved superior breakdown voltages (3.90 - 4.16 kV) compared to the diodes without field-plate (3.06 - 3.16 kV) owing to effective edge termination. Furthermore, we explored high-temperature performance of the field-plate (011) e̱ta}-Ga2O3 diodes that revealed excellent forward conduction properties and high rectification ratio (~10^9) throughout the temperature range (25 - 150 C). At reverse bias, the field-plate diodes also exhibited kV-range breakdown voltage with no evident increase in leakage current up to the explored elevated temperature of 150 C. The low area-dependence of breakdown voltage, excellent forward transport properties, and minimal reverse leakage at both high-voltage and elevated temperature demonstrate the exciting potential of (011) e̱ta}-Ga2O3 SBDs in high-temperature power switches. Thus, our work demonstrates the strategy of advancing the performance of vertical e̱ta}-Ga2O3 SBDs by utilizing the advantageous (011) e̱ta}-Ga2O3 epilayers with low background doping, reduced killer dislocation effects, and effective field management for high-voltage and high-temperature applications.
Read the full abstract

All authors Emerson J. Hollar, Aaron M. Adams, Nolan S. Hendricks, Andrew J. Green, Esmat Farzana

Artificial Intelligence

TrustMed-RL: Long-Horizon Reinforcement Learning for Evidence-Grounded Clinical Diagnosis

Wenxin Zhan, Yizheng Jiao, Haifeng Song et al. (+4 more)

Medical language models can produce correct diagnoses despite incomplete investigations and unsupported reasoning. To support long-horizon, evidence-grounded diagnosis, we introduce TrustMed-RL. Built from PubMed rare-disease cases and over 24,000 manually annotated image panels, it integrates interviews, examinations, testing, specialist consultation, and literature search through state-dependent actions. Our 8B vision–language policy, trained with clinically adapted GiGPO and coverage-adjusted diagnostic rewards, achieves 37.1% diagnostic accuracy on 2,500 evaluation cases, outperforming all evaluated open-weight baselines and improving over supervised fine-tuning by 12.4 percentage points.. When success additionally requires acquiring at least 50% of supporting test evidence, TrustMed-RL achieves 32.5%, exceeding GPT-4o by 6.8 percentage points. Furthermore, it surpasses all evaluated baselines on MTMedDialog and multiple larger 27–32B models on AgentClinic. In physician review of 200 diagnostically accepted test-set trajectories, 83.0% receive evidential-grounding scores of 4–5 out of 5. Physicians' assessments suggest that these diagnostic trajectories are trustworthy and aligned with human diagnostic reasoning.
Read the full abstract

All authors Wenxin Zhan, Yizheng Jiao, Haifeng Song, Shuai Xu, Chencheng Pan, Jiayi Feng, Anjie Xie

High Energy Physics (Phenomenology)

Pion gravitational form factors in an algebraic rainbow-ladder model

Jiayin Kang and Lei Chang

Within rainbow-ladder truncation, we identify three contributions to the pion's gravitational form factors—graviton coupling to the quark, to the gluon dressing the quark, and to the gluon binding the pion—and separate them into quark and gluon parts. Using an algebraic quark model with a dynamical basis, we obtain $A(0)=1$, $D(0)=-1$ in the chiral limit, and momentum fractions $\langle x\rangle_q=0.896$, $\langle x\rangle_g=0.104$. The D-term obeys the same partition at the model scale.
Read the full abstract

Optimization and Control

Largest Rashomon sets of decision trees for robust contextual optimization

Lorenzo Bonasera and David Pisinger

Many decision trees fit the same data almost equally well, yet they can route a query point to different leaves and induce different local empirical distributions. We study decisions that meet prescribed cost, shortage or risk targets despite this predictive multiplicity. We propose the joint Rashomon and robustness optimization framework for optimal decision trees. It jointly selects an operational decision and the largest Rashomon set of trees, so that the targets hold under the local empirical distribution that every tree in this set induces at the query point. We specialize the framework to the regression setting, and we show that a tree affects the decision only through the training observations sharing the query leaf, which we call its query neighborhood. As a result, the robust problem involves only finitely many distinct constraints, which can be examined in order of increasing estimation loss. We develop a constraint generation algorithm that combines query-path pricing with dynamic programming to identify violating neighborhoods without enumerating trees. On synthetic newsvendor instances, the algorithm typically needs few neighborhoods and runs substantially faster than full neighborhood enumeration. On restaurant demand data, the robust orders increase the mean tolerated excess estimation loss by 17.6% and reduce the empirical conditional value-at-risk of the worst 10% of realized costs by 8.3% relative to the sample average approximation orders of the optimal tree, while the mean cost difference is not statistically significant. An interpretability analysis further shows how the retained neighborhoods explain the decision and its robustness limit.
Read the full abstract