跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 14:06 — 2026-11-16 14:06(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2610.19013

Data Density Scaling Laws for Image Self-Distillation

Alvard Barseghyan, Ani Vanyan, Hakob Tamazyan, Hrant Khachatrian

原文摘要

Current scaling law formulations suggest that increasing the number of unique samples in a dataset consistently improves model performance, while repeated exposure to the same samples provides diminishing value. In this work, we challenge this assumption for image self-distillation models. We train iBOT models on random subsets of seven datasets spanning satellite imagery, driving scenes, egocentric video, and natural images, and evaluate their frozen representations on downstream tasks. We propose a density-interaction scaling law that combines unique-image count $U$ and repetition $R$, fitting it on runs with at most 50 million image presentations and testing it at larger budgets $C$. On Maxar dataset, a random subset containing approximately 1.5% of the training pool improves average nearest-neighbor classification accuracy by 3.11 percentage points over training on the full pool at the same budget of 200 million image presentations. Smaller subsets also outperform the full pool on SATLAS and Ego4D, whereas ImageNet favors larger pools at higher budgets. At a fixed subset size, further training can improve performance, lead to a plateau, or reduce performance. Our law captures smaller-subset advantages that the compared baselines cannot represent and improves prediction at higher budgets on Maxar, SATLAS, and Ego4D under nearest-neighbor evaluation. These findings show that both the number of unique images and how often they are repeated matter when allocating a training budget.

cs.LG

新论文 · v1arXiv:2611.14194

You Can Have It All: Small sparse induced-universal graphs for minor-closed classes

Vida Dujmović, Cyril Gavoille, Gwenaël Joret, Piotr Micek, Pat Morin, David R. Wood

原文摘要

We show that, for every fixed proper minor-closed graph class $\mathcal{G}$ and every positive integer $n$, there exists a graph $U_n$ with $n^{1+o(1)}$ vertices and edges such that every $n$-vertex graph in $\mathcal{G}$ is isomorphic to an induced subgraph of $U_n$. This result generalizes and unifies the results of Dujmović et al. (J. ACM 2021) on induced-universal graphs and the results of Esperet, Joret, and Morin (J. London Math. Soc. 2023) on sparse induced-universal graphs from planar graphs to all proper minor-closed graph classes. It simultaneously improves the previous bounds for the number of vertices in induced-universal graphs (previously $O(n^2)$ obtained as a corollary of a result of DeVos et al. (J. Comb. Theory, Ser. {B} 2004) and a result of Gavoille and Labourel (ESA 2007)) and the number of edges in subgraph-universal graphs (previously $O(n^{3/2})$ by Babai et al. (Theory and Practice of Combinatorics 1982)).

math.CO · cs.DM

新论文 · v1arXiv:2611.14191

The Monophonic Directed Convexities

Júlio Araújo, Ana Karolinna Maia, Thiago Marcilon, Nicolas Nisse, Rudini M. Sampaio

原文摘要

Graph Convexity is a topic with many papers in the literature, especially on the $P_3$, geodesic, and monophonic convexities in undirected graphs. Regarding directed graphs, Erd{\H o}s et al. in 1972 and Chartrand and Zhang in 2000 obtained the first results on the $P_3$ and geodesic convexities for directed graphs, respectively. In this paper, we start the investigation of monophonic convexity on directed graphs. We define two convexities, the monophonic and the strong monophonic directed convexities, related to the minimal and the induced directed paths, respectively. We show that deciding whether a set is convex is polynomial-time solvable in the monophonic convexity, but coNP-complete in the strong monophonic convexity. For both convexities, we prove that the hull number is NP-complete even in DAGs. Regarding the monophonic convexity, we prove that the hull number is polynomial time solvable in tournaments, but the interval number is NP-complete in tournaments and also in bipartite oriented graphs.

cs.CC · math.CO

新论文 · v1arXiv:2611.14186

Koopman Model-Based Reinforcement Learning

Wenjian Hao, Paulo C. Heredia, Shaoshuai Mou

原文摘要

We propose a Koopman model-based reinforcement learning (K-MBRL) algorithm for controlling nonlinear robotic systems with unknown dynamics. The K-MBRL learns a control policy by minimizing an approximate policy objective that combines the analytical immediate cost with an estimate of the future cost evaluated at the one-step predicted state. To this end, we develop a stochastic Koopman operator-based learning method to approximate the unknown nonlinear dynamics in a linear representation, while a critic function estimates the remaining future cost. This formulation offers two key advantages. First, the linear Koopman dynamics simplify the model-dependent policy gradient computation to a constant matrix product, enabling computationally efficient policy improvement. Second, one-step model propagation mitigates the accumulation of prediction errors associated with long-horizon rollouts while retaining long-term cost information through the critic. The learned policy enables real-time control through feedforward evaluation without online optimization. We establish policy learning convergence guarantees under standard stochastic approximation assumptions. Simulations on HalfCheetah and quadruped four-legged locomotion tasks demonstrate strong sample efficiency and improved performance compared with classical model-free and model-based reinforcement learning baselines. A pendulum swing-up task is used to assess policy gradient approximation accuracy and conduct ablation studies on the learning mechanism and key hyperparameters. The proposed K-MBRL is further validated on a physical quadruped robot performing a challenging sequence of maneuvers: rising to an upright posture supported by two rounded rear feet, maintaining balance during bipedal walking, and safely returning to the ground, as shown in Fig.1.

cs.RO · eess.SY

版本更新 · v3arXiv:2505.04005

Iterative Orthogonalization Scaling Laws

Devan Selvaraj

原文摘要

The muon optimizer has picked up much attention as of late as a possible replacement to the seemingly omnipresent Adam optimizer. Recently, care has been taken to document the scaling laws of hyper-parameters under muon such as weight decay and learning rate. However, at much larger scales the iterative orthogonalization procedure present in muon may suffer a possible issue as the singular values of random matrices shrink with scale. This paper shows this scaling behavior theoretically and empirically on random matrices but does not suggest what to do about it.

cs.LG

版本更新 · v2arXiv:2611.08982

Stabilizing Vector Approximate Message Passing with Circuit-Designed Lag-Lead Damping

Mohamed Akrout

原文摘要

Vector approximate message passing (VAMP) often fails to converge on ill-conditioned matrices, and its damping factor is tuned either manually or adaptively. Using the fact that VAMP iterations are the discretization of an electric circuit, we show that the denoiser and the likelihood act as nonlinear resistors, the Onsager correction is a mirror resistor and damping is a lag filter. This circuit gives a closed-form loop gain whose spectrum can predict when VAMP fails. Because a lag filter cannot isolate the oscillating modes, we add a lead capacitor whose design often results in a negative capacitance. Across a wide range of condition numbers, our proposed damping strategy achieves a higher convergence rate than adaptive damping and Anderson acceleration at a lower mean iteration cost. On ill-conditioned multipath channels, across ranks and sparsity levels, it also converges more reliably than existing damping baselines.

cs.IT

新论文 · v1arXiv:2611.14183

An Augmented Lagrangian Approach to Lifted Bellman Linear Programming

Jongchan Park, Hyukjun Yang, Narim Jeong, Donghwan Lee

原文摘要

Temporal-difference critics regress onto a bootstrapped target and usually need a target network. Lifted Bellman Linear Programming (LBLP) instead expresses the in-sample optimal values of offline RL as the solution to a linear program over the dataset. Its neural solver ALBUM relaxes the constraints into hinge penalties with fixed coefficients, and its guarantees are conditions on coefficients chosen in advance. We solve the same program with the method of multipliers: the coefficients become multipliers learned by dual ascent, with one penalty parameter $ρ$. In the convex case the fixed points are the KKT pairs of LBLP, and at every stationary point the applied constraint weights balance the objective exactly. The critic can serve a Gaussian actor, a flow actor, and best-of-N sampling, and for the Gaussian actor we propose an advantage-normalized DDPG+BC objective. With a single $Q$ and $V$ and no target network, our AL-LBLP with best-of-N reaches 60.1\% average success on the 50 state-based OGBench tasks. On long-horizon tasks, it reaches 81.5% on humanoidmaze-giant and 79.8% on antmaze-giant. It does not collapse up to batch size 8192.

cs.AI

版本更新 · v3arXiv:2610.18039

Prune-and-Merge: Training-Free Scaling of Vision Transformers

Vatsal, Soumil Malhotra, Priyanshu Chahal, Sanjeev Kumar

原文摘要

Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction methods improve efficiency, but their robustness remains underexplored. We propose Prune-and Merge ViT, a training-free framework for off-the-shelf models. It combines class attention-based pruning with similarity-based merging to reduce redundancy while preserving semantic information. To evaluate robustness we introduce two metrics. Relative Accuracy Drop (RAD) measures relative accuracy degradation under transformations, and Prediction Flip Rate (PFR) quantifies prediction consistency. On pretrained ViT and DeiT, Prune-and-Merge reduces computation competitively while maintaining robustness and better accuracy than existing token reduction methods. Our analysis suggests that hybrid token reduction does not introduce hallucination-like behavior and preserves prediction stability for common image transformations.

cs.CV · cs.AI

新论文 · v1arXiv:2611.14176

SpecValley: Aggregation as Spectral Valley in Dense Heterophilic Graphs

Christoph Jahn, Delvin Bacho, Urs Waldmann, Bastian Goldluecke

原文摘要

Node classification in heterophilic graphs remains an open problem: aggregating over neighbourhoods can damp precisely the part of the signal that carries the labels. The field has answered with ever more expressive propagation operators, leaving the aggregation step that precedes them fixed by degree normalisation. However, degree normalisation acts as a spectral valley in its own right, attenuating a fixed middle band whose position at lambda equal 1 is set by the normalisation rather than by the data, exactly where the eigenvalues of dense graphs accumulate. We therefore begin with the representations rather than the propagation, in two stages: a learnable aggregation followed by an ordinary spectral filter. The first, SpecValley learns the position, sharpness and flank gains of the valley for every graph. We show formally how the aggregation operator and downstream filter interact. We establish that the response 1 minus lambda of degree normalisation vanishes exactly at that accumulation point. A spectral energy budget shows that what aggregation removes from a band, no linear spectral filter can recover. Crowding alone says nothing about the benefit. That is decided by how much label energy the valley removes, which we measure for every graph. SpecValley achieves strong results across heterophilic benchmarks, and a controlled ablation over aggregation operators and downstream filters attributes the gain to aggregation rather than the filter.

cs.CV · cs.LG

新论文 · v1arXiv:2611.14174

Cross-Border Fulfillment Center Selection via Doubly Robust Estimation and Linear Programming

Kriti Mahajan, Patrick Bloebaum

原文摘要

We introduce the cross-border (XB) fulfillment center (FC) Selection Model: a multi-stage optimization framework combining forecasting, doubly robust estimation, and linear programming to select optimal source FCs. For each source-destination shipping arc, the objective is to choose a subset of source-country FCs that minimize delivery time and cost while maximizing profit and shipped units under a fixed domestic network. We evaluate the model on three production-scale international shipping corridors for a large e-commerce company using 12 months of shipment data, employing both aggregate offline replay and shipment-level counterfactual nearest-neighbor matching. Across all shipping corridors, the XB FC Selection Model achieves 8.5-51.1% reductions in delivery time and 4.4-48.3% reductions in logistics cost relative to human expert-defined FC selection policies, with up to 6.5 percentage-point improvements in 5/5 target compliance (5 days, $5 USD). Pareto analysis shows the model consistently dominates single-objective ranking strategies and unconstrained LP on the efficiency-reallocation frontier, with all results statistically significant.

cs.AI

新论文 · v1arXiv:2611.14171

BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions

Shenxi Liu, Yiwei Li, Mingyang Zhao, Yuhang Tian, Kan Li

原文摘要

Repeated sampling with majority selection is an effective means of enforcing self-consistency in large language models. Recently, a variant has also been introduced that terminates early to save costs when the output distribution is favorable. But it still cannot yield a correct confidence estimate from the answer distribution. For this issue, we formalize this as majority identification under an unknown distribution with a budget and a target error rate, and propose BARS, a sequential rule certifying the top-two gap and returning an early stop, a budgeted majority vote, or a refusal when feasibility cannot be established. A refusal is a statement about the rule and its budget, not a claim that a question is unanswerable, and it tells practitioners when to widen the budget or switch models. A certified mode carries proven bounds on the joint answering error and on refusing an instance the budget could handle, while a practical mode, used in our experiments, replaces them with empirical calibration. On synthetic instances drawn from known distributions over thousands of seeds, the difficulty-driven behavior is recovered and the price of the certified mode is measured.On GSM8K the practical mode draws 22.3\% fewer samples than fixed-8 sampling over the same pool, refused questions included, at the cost of declining 18.8\% of the questions. On MATH, it greatly improves the accuracy of its output answers into 82.5\% at the cost of honestly refusing to answer half of the difficult questions that the model itself is unable to solve.

cs.AI

版本更新 · v2arXiv:2607.09553

Writing Bug Reports for Software Repair Agents: What Information Matters Most?

Vincenzo Luigi Bruno, Alessandro Giagnorio, Daniele Bifolco, Leon Wienges, Massimiliano Di Penta, Gabriele Bavota

原文摘要

Software development is increasingly moving toward agentic-first workflows. This includes AI agents responsible for generating initial fixes for submitted issue reports. In this setting, issue reports are no longer merely documentation for human maintainers; they become the primary task specification for the agent. However, little is known about how such reports should be written to maximize the agent's chances of producing a correct fix. We study what makes a bug report agent-ready. Starting from the SWE-Bench Verified benchmark (i.e. a collection of 500 real repository issues with human-written gold patches and test suites for evaluating generated fixes) we manually classify each issue by change type (e.g. bug fix vs refactoring) and annotate each sentence with its information type, such as observed behavior, expected behavior, reproduction steps, localization cues, and suggested fixes. We focus on the 441 issues representing bug reports, and we run on them mini-swe-agent using three LLM backbones (i.e. GPT-5-mini, MiniMax M2.5, and Gemini 3 Flash). We then fit a binomial regression model to estimate the incremental association between each information type and agent success, controlling for confounding factors. Our results suggest that agentic-first reports benefit most from information that narrows the agent's search and repair space. Suggested fixes, expressed either in code or natural language, show the strongest positive associations with pass probability, while localization cues show positive but non-significant associations. An ablation study removing selected information types confirms that agents benefit less from information traditionally useful to humans, such as reproduction steps, and more from sentences that expose a repair direction.

cs.SE

版本更新 · v2arXiv:2502.18733

Cross-Modality Investigation on WESAD Stress Classification

Eric Oliver, Sagnik Dakshit

原文摘要

Deep learning's growing prevalence has driven its widespread use in healthcare, where AI and sensor advancements enhance diagnosis, treatment, and monitoring. In mobile health, AI-powered tools enable early diagnosis and continuous monitoring of conditions like stress. Wearable technologies and multimodal physiological data have made stress detection increasingly viable, but model efficacy depends on data quality, quantity, and modality. This study develops transformer models for stress detection using the WESAD dataset, training on electrocardiograms (ECG), electrodermal activity (EDA), electromyography (EMG), respiration rate (RESP), temperature (TEMP), and 3-axis accelerometer (ACC) signals. The results demonstrate the effectiveness of single-modality transformers in analyzing physiological signals, achieving state-of-the-art performance with accuracy, precision and recall values in the range of $99.73\%$ to $99.95\%$ for stress detection. Furthermore, this study explores cross-modal performance and also explains the same using 2D visualization of the learned embedding space and quantitative analysis based on data variance. Despite the large body of work on stress detection and monitoring, the robustness and generalization of these models across different modalities has not been explored. This research represents one of the initial efforts to interpret embedding spaces for stress detection, providing valuable information on cross-modal performance.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.06749

A Statistical Framework for Algorithmic Collective Action with Multiple Collectives

Claudio Battiloro, Pietro Greiner, Dario Rancati, Bret Nestor, Oumaima Amezgar, Francesca Dominici

原文摘要

As learning systems increasingly shape everyday decisions, Algorithmic Collective Action (ACA), i.e., users coordinating changes to shared data to steer model behavior, offers a complement to regulator-side policy and corporate model design. Real-world collective actions have traditionally been decentralized and fragmented into multiple collectives, despite sharing overarching objectives, with each collective differing in size, strategy, and actionable goals. However, most of the ACA literature focuses on single collective settings. To address this, we propose the first comprehensive statistical framework for ACA with multiple collectives acting on the same system. In particular, we focus on collective action in classification, studying how multiple collectives can influence a classifier's behavior. We provide quantitative statistical bounds on the success of the collectives, considering the role and the interplay of the collectives' sizes and the alignment of their goals. We make such bounds computable by each collective with only partial knowledge of other collectives' sizes and strategies. Finally, we numerically illustrate our framework on simulations inspired by interventions for climate adaptation in smart cities, demonstrating the usefulness of our bounds.

stat.ME · cs.AI

新论文 · v1arXiv:2611.14168

Representational Atoms in Neural Networks

Chenhui Hu, Pengfei Cao, Kang Liu, Jun Zhao

原文摘要

Understanding the internal representations of neural networks and characterizing their relationship with human conceptual structure are two critical questions for elucidating model mechanisms. The former reveals how learned knowledge is organized in internal representations, whereas the latter provides a basis for interpreting these representations through human conceptual structure. Here, we formally define fundamental representational units (FRUs) and establish two evaluation criteria: fidelity and stability. We further prove that threshold-activated sparse autoencoders (TSAEs) can identify FRUs with high fidelity and stability under appropriate conditions, and validate this result through large-scale experiments. Further analyses reveal that FRUs with higher stability exhibit greater monosemanticity and can be composed across layers to recover semantic organization corresponding to human conceptual structure. These results provide a unified framework for defining, evaluating and identifying FRUs in neural networks, and establish a foundation for characterizing the relationship between neural network representations and human conceptual structure.

cs.CL · cs.AI

版本更新 · v2arXiv:2609.24609

GraphToolbox: A Configurable Framework for Controlled Benchmarking of Graph Neural Network Forecasting

Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Argyris Kalogeratos

原文摘要

Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) represent these relations through a graph. Building a complete GNN forecasting experiment is nonetheless laborious, because graph construction, model selection, training, aggregation, and interpretation often require separate tools. We present GraphToolbox, an open-source Python framework that unifies these stages in one configuration-driven pipeline built on PyTorch Geometric. It offers data-driven graph construction, a single interface for most graph convolution operators of PyTorch Geometric and for recurrent graph cells, online expert aggregation, forecasting interpretability, and significance testing on forecasts. We use GraphToolbox to run a controlled benchmark: we compare architectural and modeling choices for French electricity load and net-load forecasting at regional and national levels under a common experimental protocol. On load, most evaluated graph convolutions outperform additive, recurrent, and foundation-model baselines. Pooled XGBoost, trained on the same inputs, has a lower RMSE than the best graph models, although the difference is not significant. Online expert aggregation and daily model updates improve accuracy further. On net-load, graph models outperform additive, recurrent, and XGBoost baselines, with further gains from forecasting the physical components separately. Statistical tests do not identify a single best convolution for load forecasting.

cs.LG · cs.AI

版本更新 · v9arXiv:2503.20550

Structural Origins of Cubic Complexity in Pebble Motion

Tomoki Nakamigawa, Tadashi Sakuma

原文摘要

The pebble motion problem (PMP) asks whether one configuration of labeled pebbles on a graph can be transformed into another by moving pebbles to adjacent unoccupied vertices. Kornhauser, Miller, and Spirakis proved that the worst-case shortest solution length on an $N$-vertex graph is $Θ(N^3)$, but the graph structures responsible for this cubic behavior remained unclear. We first show that cubic complexity cannot occur on trees: every feasible instance on an $N$-vertex tree admits a solution sequence of length $\mathrm{O}(N^2\log N)$, constructible in time linear in its length. This is the first $\mathrm{o}(N^3)$ upper bound for PMP on trees. We then extend the method to general graphs. When $2\le N-n=\mathrm{O}(1)$, every instance on a feasible puzzle admits a solution of length $\mathrm{O}(n\,\mathrm{CL}(G)\,\mathrm{D}(G))$, where $\mathrm{D}(G)$ is the diameter and $\mathrm{CL}(G)$ is the maximum length of a shortest cycle through a vertex; this recovers the classical $\mathrm{O}(N^{3/2})$ bound for square grids. We further show that any graph with worst-case shortest solution length $Θ(N^3)$ has a unique biconnected component $X$ of order $Θ(N)$, while all structures attached through any one cut vertex of $X$ have bounded total size. Moreover, $X$ contains no cycle of unbounded sublinear order, and any two intersecting cycles of order $Θ(N)$ share at least as many vertices as there are blanks. Finally, cubic complexity occurs when a cycle of order $Θ(N)$ contains all but $\mathrm{O}(1)$ vertices, whereas two $Θ(N)$-cycles meeting at one vertex have complexity exactly $Θ(N^2\log N)$. We conjecture that the former construction essentially characterizes the cubic regime.

math.CO · cs.CC · cs.DM

新论文 · v1arXiv:2611.14164

An Empirical Study on CVE-based Vulnerabilities Propagation from one System to another System (IntraProject vs InterProject)

Junaid Akram, Ali Hassan, Danish Vasan

原文摘要

Vulnerabilities in applications, including browsers, media players, online services and document readers, etc. are often exploited and cause a serious damage. The vulnerabilities could exist in your system maybe because of some coding errors, design oversights, outdated software, AI generated codes or maybe transferred from another system during development (e.g., code clones). The propagation of software vulnerabilities is a critical concern in cybersecurity. This study examines the root cause problem of vulnerabilities propagation with experiments. We analyzed the propagation of CVE (Common Vulnerabilities and Exposures) based vulnerabilities within and between different software projects (IntraProject vs. InterProject). We performed several experiments on CVE based vulnerability dataset (retrieved from NVD source) by using our vulnerability detection tool (SQVDT). In the results, we discovered similar patterns of vulnerable code in several very famous recently used software, including latest version of Linux, Android operating systems, and in thousands of open source projects available on GitHub. We found several very high severity level (CVSS) vulnerabilities that propagated from one system to another system, just because of copy/paste (reuse) the code. Furthermore, we performed an empirical evaluation and verification of these vulnerable patterns that propagated to other systems by also considering the frequency of their propagation. Finlay, we recommended the impact of these vulnerabilities propagation on the interconnected systems.

cs.CR · cs.SE

版本更新 · v5arXiv:2602.23872

Altitude-Adaptive UAV-to-Map Image Matching for Aerial Geo-Localization

Xingyu Shao, Mengfan He, Liangzheng Sun, Chunyu Li, Ziyang Meng

原文摘要

Matching downward-looking unmanned aerial vehicle (UAV) images to georeferenced satellite or aerial map tiles supports map-based geo-localization when direct positioning signals are degraded or unavailable. Variations in UAV altitude change the observed ground footprint and create a scale mismatch between query images and fixed-scale map references. We address this problem with an altitude-adaptive aerial geo-localization framework. The framework estimates relative altitude from a single image using a frequency-domain representation and regression-as-classification. The predicted altitude-class center defines a scale prior that guides query normalization toward the canonical map scale before full-gallery visual place recognition. A footprint-adaptive margin classifier (FAMC) adjusts training margins according to footprint overlap. Experiments on two synthetic and two real-flight datasets show that, at the 100 m localization threshold, altitude adaptation improves average R@1 and R@5 by 50.68 and 47.20 percentage points, respectively, for our visual place recognition module compared with the same retrieval pipeline without altitude normalization. These results show that a relative-altitude-derived scale prior improves cross-altitude UAV-to-map image matching in the evaluated regions and camera settings.

cs.CV · cs.RO

版本更新 · v2arXiv:2605.05996

Gaussian mixture models in Hilbert spaces via kernel methods

Daniel López-Montero, Antonio Álvarez-López, Marcos Matabuena

原文摘要

Modern datasets across many disciplines increasingly consist of time-evolving, potentially infinite-dimensional random objects, such as dynamic functional data, which are naturally modeled in Hilbert spaces. In these settings, characterizing probability measures, for example, through densities, can be ill-defined or technically challenging. Motivated by clustering applications, we propose a Gaussian mixture framework for Hilbert-space-valued data based on kernel mean embeddings and develop efficient optimization algorithms for estimation. We establish theoretical guarantees showing that the proposed algorithm is well-defined and that the model yields a dense class of approximations in infinite-dimensional spaces. We evaluate the framework through extensive experiments on diverse data geometries, including $L^2$-functional data and graph signals arising in modern medical applications.

stat.ML · cs.LG

版本更新 · v3arXiv:2509.09353

Low-degree lower bounds via almost orthonormal bases

Alexandra Carpentier, Simone Maria Giancola, Christophe Giraud, Nicolas Verzelen

原文摘要

Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical--computational gaps across a variety of high-dimensional statistical models [Wein25]. For detection problems---where the goal is to test a planted distribution $\mathbb{P}'$ against a null distribution $\mathbb{P}$ with independent components---the standard approach is to bound the advantage using an $\mathbb{L}^2(\mathbb{P})$-orthonormal family of polynomials. However, this method breaks down for estimation tasks or more complex testing problems where $\mathbb{P}$ has some planted structures, so that no simple $\mathbb{L}^2(\mathbb{P})$-orthogonal polynomial family is available. To address this challenge, several technical workarounds have been proposed [SW22,SW25], though their implementation can be delicate. In this work, we propose a more direct proof strategy. Focusing on random graph models, we construct a basis of polynomials that is almost orthonormal under $\mathbb{P}$, in precisely those regimes where statistical--computational gaps arise. This almost orthonormal basis not only yields a direct route to establishing low-degree lower bounds, but also allows us to explicitly identify the polynomials that optimize the low-degree criterion. This, in turn, provides insights into the design of optimal polynomial-time algorithms. We illustrate the effectiveness of our approach by recovering known low-degree lower bounds, and establishing new ones for problems such as hidden subcliques, stochastic block models, and seriation models.

stat.ML · cs.LG

新论文 · v1arXiv:2611.14163

Nonadaptive One-Sided Testing of Binary Rank

Nader H. Bshouty

原文摘要

The binary rank of a binary matrix is the minimum number of disjoint all-one rectangles that partition its one-entries. We study entry-query testing of binary rank at most $d$, with one-sided error and nonadaptive queries. We give a tester using $\tilde O(d^4/ε^2)$ queries, independent of the matrix dimensions and a general lower bound of $\tilde Ω(d^{3/2}/ε)$.

cs.DS · cs.LG

新论文 · v1arXiv:2611.14158

Neural network scaling and generalization for 3D strain fields in heterogeneous materials

Lucas Fourel, Paul Devianne, Marine Debouvry, Tristan Destruhaut, Russell Gunn, Ashwini Gupta, Lori Graham-Brady, Jean-François Molinari

原文摘要

Computational homogenization and coupled multiscale simulations of heterogeneous materials require repeated solution of mechanical fields on Representative Volume Elements, which becomes prohibitively expensive for high-resolution three-dimensional microstructures. Machine-learning surrogates can accelerate these computations, yet most existing approaches predict fields for fixed macroscopic loadings and provide limited guidance on how to scale network architectures for high-resolution 3D tensor-field prediction. This work presents a U-Net surrogate trained to predict the full 36-component strain localization tensor field in voxelized concrete mesostructures at resolutions up to $256^3$. Training localization tensors are generated with an FFT-based linear elastic solver, and an extensive hyperparameter optimization is performed to derive scaling rules and an accuracy-speed trade-off analysis. The results show that only network width and depth need to be scaled with problem complexity, while several conventional U-Net design choices, such as doubling channels after downsampling, are suboptimal for this problem. The final neural network achieves a Mean Absolute Error of 1.118% on both the validation and the held-out test sets, and an inference speedup of approximately 8.7x over the FFT-based solver on an Nvidia H100 GPU. Generalization experiments reveal transfer across aggregate volume fractions and highlight the importance of training on diverse morphologies. To safeguard reliability, a Maximum Mean Discrepancy metric computed on internal feature maps is proposed for detecting out-of-distribution microstructures without costly reference computations.

physics.comp-ph · cs.CE

新论文 · v1arXiv:2611.14154

Uneven Self-Reported AI Use: An Embedded Case Study Across Eleven Teams in a Software Organization

Daniele Veri'

原文摘要

This paper presents a descriptive, embedded single-case study examining self-reported AI use within a software organization. The study draws on 98 structured interview records collected across 11 teams, using ten standardized team-level instruments (n = 65) and one instrument with distinct response anchors (n = 33). Among respondents assessed using standardized instruments, 36 of 65 (55.4%) reported AI-use frequency scores of 4 or 5 on a five-point scale. Team-level proportions varied from 20.0% (1/5) to 71.4% (5/7). A record-level cross-tabulation revealed limited awareness or understanding of organizational AI policies across both frequency groups: 86.1% (31/36) of respondents scoring 4-5 and 96.6% (28/29) of those scoring 0-3 reported either no policy awareness or uncertainty about policy details. In the group assessed using the distinct instrument, 31 of 33 respondents (93.9%) scored 4 or 5. Although the pooled proportion reached 68.4% (67/98), differences in response anchors limit direct comparability, making the standardized-instrument results the primary analytical reference. Interviewer-recorded observations provide qualitative context on reported practices and constraints but do not support estimates of their prevalence or causal explanations for differences in AI-use frequency. The findings characterize AI-use patterns and policy awareness within the interviewed sample, without supporting inferences about organization-wide adoption, policy compliance, or the effectiveness of AI use. The study contributes an empirically grounded organizational case and an explicit account of the methodological boundaries of cross-team comparisons using heterogeneous interview instruments.

cs.HC · cs.CY

版本更新 · v4arXiv:2509.13423

Computational complexity of Berry phase estimation in topological phases of matter

Ryu Hayakawa, Kazuki Sakamoto, Chusei Kiumi

原文摘要

The Berry phase is a fundamental quantity in the classification of topological phases of matter. In this paper, we present a new quantum algorithm and several complexity-theoretical results for the Berry phase estimation (BPE) problems. Our new quantum algorithm achieves BPE in a more general setting than previously known quantum algorithms, with a theoretical guarantee. For the complexity-theoretic results, we consider two main cases. First, we prove $\mathsf{BQP}$-completeness when we are given a guiding state that has a large overlap with the ground state. This result establishes an exponential quantum speedup for estimating the Berry phase. Second, we prove $\mathsf{UQMA} \cap \mathsf{co}$-$\mathsf{UQMA}$-completeness when we have an $\textit{a priori}$ bound for the ground-state energy. Here, $\mathsf{UQMA}$ is the unique witness version of $\mathsf{QMA}$, and $\mathsf{UQMA} \cap \mathsf{co}$-$\mathsf{UQMA}$ precisely captures the complexity of BPE without the known guiding state. Remarkably, this problem is, to our knowledge, the first natural problem complete for $\mathsf{UQMA} \cap \mathsf{co}$-$\mathsf{UQMA}$. These results advance the role of quantum computing in the study of topological phases of matter and provide a pathway for clarifying the connection between topological phases of matter and computational complexity.

quant-ph · cond-mat.str-el · cs.CC

新论文 · v1arXiv:2611.14153

Unipolar Neuron Networks Trained by Recirculation for Reward-Based Continual Learning

Florin Leon

原文摘要

Unipolar neurons are the predominant type of nerve cell in the octopus and in most other invertebrates. A single neurite (a fiber extending from the cell body) branches into a tree that carries both input and output synapses. The branches send graded local outputs to nearby cells, and one site on the main neurite sends a global output to distant targets. This paper proposes a network of such neurons and a learning rule for it. Each neuron is modeled as a tree of passive segments, whose activations are computed exactly as the steady state of a linear system. The network learns from reward alone, with a rule called recirculation. After each forward pass, a second pass sends requested changes of the outputs back through the same connections. Each synapse then adjusts its weight using only quantities available at its own location. Because the system of each neuron is symmetric, this update closely follows the gradient of the error in the predicted reward. Two mechanisms limit forgetting when tasks are learned in sequence: a task code inhibits a different subset of branches in each task, while consolidation lowers the learning rate of synapses that changed strongly in the recent past. The model is evaluated on a sequence of MNIST and Iris tasks. The network maintains high accuracy with low forgetting, whereas gradient-based training of the same network forgets earlier tasks almost completely.

cs.LG

版本更新 · v2arXiv:2606.05156

Temporal Cliques Admit Linear Spanners

Julia Baligacs

原文摘要

A temporal graph is a graph in which every edge carries a non-empty set of time labels, and it is temporally connected if for every two vertices $u$ and $v$, there exists a $u$-$v$-path with non-decreasing time labels. A spanner is a subset of its edges preserving temporal connectivity. Unlike static graphs, temporally connected graphs need not admit sparse spanners; nonetheless, minimizing spanner size is a central and widely studied problem. A particularly intriguing question is whether temporal cliques admit spanners of linear size. Despite considerable effort over the past years, the best known upper bound remained $O(n \log n)$. We finally resolve this question, proving that every temporal clique on $n$ vertices admits a spanner of size $7n$. Moreover, such a spanner can be computed in polynomial time.

cs.DM · math.CO

版本更新 · v2arXiv:2610.35870

Packet Interval Modulation for Uncoordinated NFC Data Networking Around Meander E-Textiles

Shigemi Ishida, Satoshi Ido, Ryo Takahashi

原文摘要

Smart home sensing with low-power wireless nodes is non-intrusive but requires battery maintenance and cannot identify residents. A garment with a meander-coil NFC reader solves both, as it powers battery-free tags on the skin and on nearby objects and attributes every reading to its wearer. Because the number of tags in range changes as the user moves, we propose packet interval modulation (PIM), which encodes sensor values into pulse intervals without reader commands. With five tags, PIM reduces the collision rate of slotted ALOHA from 22.7% to 4.1% while delivering 384 bps, enabling resident-attributed ambient sensing.

cs.NI

新论文 · v1arXiv:2611.14149

From Search to Decision: How Post-Training Shapes Information-Seeking Capabilities in Large Language Models

Haohang Huang, Xuan Lu, Mingjin Kuai, Yuxuan Zhang, Wei Ji, Haiyang Zhang

原文摘要

Information seeking in large language model (LLM) systems increasingly involves decisions about when to acquire information, where to search, and how to evaluate and use evidence. Recent post-training methods have improved several such behaviors, but their objectives and evaluations span different tasks and system settings. This paper organizes research around six interrelated information-seeking capabilities and examines the learning signals, optimization methods, update loci, and credit-assignment mechanisms used to develop them. We synthesize empirical progress in targeted behaviors, end-to-end performance, search control, and generalization. Existing studies report gains in retrieval routing, query refinement, multi-tool exploration, evidence-grounded reasoning, and resource-aware search, although the scope of behavioral evidence varies across capabilities. We identify open challenges in estimating prospective retrieval utility, coordinating information-seeking decisions, and adapting to unfamiliar retrieval environments, and discuss evaluation practices for interpreting future progress.

cs.IR

新论文 · v1arXiv:2611.14147

Secure Information Flow in Quantum Programs

Zhicheng Zhang, Mingsheng Ying, Lirong Xia

原文摘要

Information-flow security aims to prevent the leakage of confidential information through program execution. This problem becomes fundamentally subtler for quantum programs, because their states may involve superposition and entanglement, and their executions may involve intricate interactions between classical and quantum variables. This paper develops semantic foundations and verification methods for secure information flow in quantum programs. We formulate two notions of information-flow security. The first is a noninterference-based definition that naturally generalizes its classical counterpart. The second is a simulation-based definition that explicitly models an attacker, providing a clear operational interpretation of security. We prove that these two notions are equivalent. To verify the information-flow security of quantum programs, we develop a proof framework based on quantum Hoare logic. A key challenge is that the standard self-composition technique, which expresses information-flow security in Hoare logic by composing a program with a renamed copy of itself, fails in the quantum setting due to an obstruction analogous to the no-cloning theorem. To overcome this challenge, we introduce self-conjugation, a novel technique that leverages the deferred measurement principle and properties of unitary operations. We demonstrate our framework on examples drawn from the quantum one-time pad, quantum error correction, and anonymous entanglement generation.

quant-ph · cs.CR · cs.PL