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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 12:09 — 2026-11-22 12:09(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.26011

A Matter of Representation: Evolving Partial Spreads for Bent Functions

Claude Carlet, Marko Đurasevic, Domagoj Jakobovic, Luca Manzoni, Luca Mariot, Stjepan Picek

原文摘要

Partial spread ($\mathcal{PS}$) bent functions are Boolean functions of maximum nonlinearity built from families of subspaces that pairwise intersect only in the null vector. We design an Evolution Strategy (ES) to construct such partial spread families, comparing two encodings: one based on generator matrices of the subspaces, and one based on spread sets. With the latter, combined with a ruin-and-rebuild operator, the ES finds $\mathcal{PS}$ functions up to $n=10$ variables. An ablation study shows that mutation is necessary, while the population size is not, and that a restarted look-ahead greedy heuristic outperforms the ES on the hardest instance. We investigate this finding with a landscape analysis of the stagnation points, and we also introduce a quality-diversity variant of the ES which finds $\mathcal{PS}$ functions of low algebraic degree for 8 variables. Interestingly, the bent functions evolved by the ES have higher 2-ranks and mostly higher degrees than those obtained by a baseline Genetic Programming optimizer.

cs.NE

版本更新 · v2arXiv:2609.15435

Profiling Handwriting-Process Deviations in Developmental Dysgraphia: An Open, Normatively-Referenced Instrument

Jihyun Mun, Mounîm A. El-Yacoubi

原文摘要

Online handwriting captured on digitizing tablets yields hundreds of kinematic, temporal, spatial, and dynamic features. These features are rarely organized into interpretable, reusable constructs, and, although standardized tests norm the handwritten product, no openly available instrument places a child's handwriting process relative to a verified-typical reference. We introduce and validate an open measurement instrument for profiling handwriting-process deviations in children with developmental dysgraphia from sentence-level online handwriting. The instrument comprises (i)~a literature-only vocabulary, fixed before any cohort analysis, organizing 136 online-handwriting features into 12 handwriting-process domains, and (ii)~an age- and sex-adjusted normative reference framework, fit on verified-typical children only, that turns those features into a 12-axis deviation profile with per-child bootstrap uncertainty. We establish its measurement properties on the DiaGraMo cohort (N=257 Czech children aged 8--12; 110 verified-typical, 147 with dysgraphia): the vocabulary is structurally coherent, and the reference is calibrated, parsimonious, and leakage-free. On the same cohort, five of twelve domains separate the groups at BH~$q<.05$ (Cliff's~$δ$ +0.19 to +0.51), on spatial, temporal, and pen-orientation processes, and 96.5\% of participant~$\times$~domain scores have a bootstrap CI narrower than one z-unit. No classifier is trained: the instrument reports uncertainty-aware deviation scores rather than a diagnostic label, and its outlier rate is not a diagnostic rate. The vocabulary, the analysis code, and an open reference implementation that scores new participants are all openly released, giving handwriting and dysgraphia researchers a reusable, validated instrument for situating individual children against a normative reference.

cs.HC

版本更新 · v3arXiv:2506.18852

Mechanistic Interpretability Needs Philosophy

Iwan Williams, Ninell Oldenburg, Ruchira Dhar, Joshua Hatherley, Constanza Fierro, Nina Rajcic, Sandrine R. Schiller, Filippos Stamatiou 等 9 位作者

原文摘要

Mechanistic interpretability (MI) aims to explain how trained neural networks work by uncovering their underlying mechanisms. As the field grows in influence, it is increasingly important to examine not just models themselves, but the assumptions, concepts and explanatory strategies implicit in MI research. We argue that mechanistic interpretability needs philosophy as an ongoing partner in clarifying its concepts, refining its methods, and navigating the epistemic and ethical complexities of interpreting AI systems. There is significant unrealised potential for progress in MI to be gained through deeper engagement with philosophers and philosophical frameworks. Taking three open problems from the MI literature as examples, this paper illustrates the value philosophy can add to MI research, and outlines a path toward deeper interdisciplinary dialogue.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26003

AI agents can redesign engineering parts with more than a thousand CAD parameters and nonlinear simulations

Alexandra Starostina, Alexander Hermann, Mahish Guru, Kartik Bali, Roland Aydin, Christian C. Cyron

原文摘要

Simulation-driven design of real engineering components has to meet three conditions at once. It runs on few solves, since a nonlinear finite-element simulation of a 3D part takes hours; its design space has many values, the hundreds to thousands of values of the part's CAD model; and a better design often needs a redesign, coordinated changes of the part's proportions rather than local polishing of its surface. Automated optimisers meet at most two of these conditions. Classical optimisers, Bayesian or derivative-free, need a person to cut the design down to a few parameters, and on all the values they need far more solves; industrial shape optimisers move every surface node of the mesh in one solve per cycle, but only in small steps that polish rather than redesign. We ask whether a general-purpose large language model (LLM) can meet all three by joining what it knows with what the simulation shows. GPT-6 Astra edits a magnesium stent through a CAD geometry parametrisation of about 1,650 values, with a budget of 15 simulations; every proposal is built in CAD, meshed and simulated with large-deformation plasticity and contact, and the LLM reads the full results of every solve. Within that budget it lowered the objective, a high percentile of the strains in the stent's bends, by 32%; on the same budget, the industrial shape optimiser Tosca improved the original design by a tenth and then stopped improving. An earlier GPT-6 Astra design, 25% lower in the same objective, was checked in an independent, higher-fidelity model of the full deployment with crimping and damage: it was 14% less strained than the original after the full chain, and its most damaged spot began to fail later and carried 63% less damage at full expansion. LLMs can thus join their learned knowledge with simulation data to adjust more than a thousand design values and reach valid designs with real improvements.

cs.AI

新论文 · v1arXiv:2611.26000

Xing-Audio-NVVASR: Scaling and Refining Supervision for Joint Recognition of Speech and Non-Verbal Vocalizations

Pengyu Xu, Gang Liu, Genliang Zhao, Hongjie Chen, Jian Kang, Jie Lian, Jie Li, Yongxiang Li

原文摘要

Joint recognition of speech and non-verbal vocalizations (NVVs) is hindered by scarce event-rich training data and inaccurate or missing event labels. We present Xing-Audio-NVVASR, an end-to-end recognizer trained through progressive data mining and iterative supervision refinement. Guided by unified acoustic criteria, two heterogeneous models cross-audit annotations, flagging disagreements for teacher reannotation. To uncover shared omissions that model agreement may conceal, complementary breath detectors screen the entire corpus for human review. Human-confirmed labels accumulate across rounds and are preserved during subsequent refinement. Over five rounds, we refine annotations for 170,000 utterances from public corpora and incorporate 630,000 mined utterances. The resulting corpus of approximately 800,000 utterances is used to train a single 1.7B-parameter model that transcribes speech with inline tags for six NVV classes. Across four human-annotated benchmarks, Xing-Audio-NVVASR ranks first among nine models in both composite score and six-class Macro-F1. It achieves a mean composite score of 64.46, surpassing the strongest comparison model, StepAudio 3 Chat Preview, by 6.03 points, and exceeds the annotation teacher's breathing F1 by 14.40 to 31.57 percentage points. We plan to release the model weights, inference code, four evaluation benchmarks, annotation guidelines, and evaluation code.

cs.CL

版本更新 · v2arXiv:2609.02402

A Physics-Consistent Benchmark for Contact-Rich Human-Robot Interaction in Assistive Care

Chengxiao He, Shenghai Yuan, Liuqun Fan, Shenzhe Zhu

原文摘要

Conventional task-level evaluation asks whether a robot policy completes a specified action, but can miss failures that emerge only during physical human contact. This limitation is critical in contact-rich assistive tasks, where meaningful evaluation requires a physically responsive human, interaction-quality assessment beyond task success, and a leak-free observer-scorer protocol. We introduce a physics-consistent benchmark for contact-rich human-robot interaction, instantiated in robot-assisted bathing. The benchmark combines a deformable, passively responding human, physics-aware scores alongside task-level success, and a frozen vision-only / scorer-only evaluation protocol. To establish physical validity, region-wise simulated responses are calibrated against force-indentation measurements from Franka impedance pushes on a medical-care manikin. Under a frozen T1-T7 protocol with 140 runs per method, an LLM-augmented state machine (State Machine) achieves 72.9% task success but drops to 56.4% after correct-region and force-safety screening; VoxPoser produces lighter and more stable contact but completes only 27.9% of trials; and zero-shot pi0.5 achieves 0.7% task success with no correct-region or safety-gated successes. These results show that task completion alone does not imply physically valid contact and motivate physics-aware screening before deployment of contact-rich assistive robot policies.

cs.RO

版本更新 · v2arXiv:2610.17205

Releasing the Inner Jev: A Simple Recipe for Open Decision Models

Jonathan Geuter, Andrew Cheng, David Alvarez-Melis

原文摘要

LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typed input state, a question, and a set of options, they return a calibrated probability for each option in a single forward pass, without text generation. We show that open instruction-tuned LLMs can achieve performance comparable to Jev without any additional training, by reading out answers from letters (A, B, C, etc.) in the model's output logits at the last token position. Next, we propose a simple supervised LoRA fine-tuning recipe that can improve their performance further. We evaluate four instruction-tuned LLMs: Gemma 4 31B, Gemma 4 12B, Qwen3.6-27B, and Qwen3.5-4B. Furthermore, we introduce OpenDecisions, a novel 2,352-question validation dataset designed to reflect the task composition of JevBench (JevBench maintainers, 2026) and which computes a Capability score based on accuracy and calibration. Without fine-tuning, Gemma 4 31B scores 79.6 on OpenDecisions, compared to Jev's 80.1. After fine-tuning, it scores 89.0, outperforming Jev by 8.9 Capability points and on par with the strongest open decision model we evaluated. The same recipe improves the three other models by 7.8 to 15.7 points. On a suite of public decision datasets, our models achieve accuracy and calibration comparable to Jev. Our results show that open LLMs already possess System One capabilities, and with simple fine-tuning they outperform Jev on a wide range of decision tasks. We release our models, training and serving code, OpenDecisions, and DecisionBank, our training dataset consisting of 261,561 decisions.

cs.AI

新论文 · v1arXiv:2611.25995

Two-Timescale Channel Estimation and Port Selection for Fluid Antenna Systems With Limited Port Observations

Xusheng Zhu, Kai-Kit Wong, Jiajian Wang, Songling Zhang, Shihao Fan

原文摘要

Port selection in fluid antenna systems (FAS) requires instantaneous channel state information, but a single radio-frequency chain can probe only a few ports in each coherence block. Existing FAS channel estimators, even with learned or generative priors, work within a single block and are limited by its few probes, which cannot resolve several propagation paths. To overcome this limitation, we propose a two-timescale channel estimation and port selection scheme that exploits the slow variation of the path angles. Specifically, a sequential Monte Carlo filter accumulates the angle posterior over blocks, while the fast-fading path gains are integrated out in closed form. Furthermore, a Fisher information analysis reveals that a single probe per block carries no angle information, whereas two or more spread-out probes accumulate it linearly over blocks. Simulation results demonstrate that the proposed scheme approaches the selection with known angles after about twenty blocks and, with four probes per block, matches memoryless schemes with eight.

cs.IT

版本更新 · v2arXiv:2608.24891

Measurement-Budget Allocation in Quantum Learning with Finite-Shot Generalization Guarantees

Ferhat Ozgur Catak

原文摘要

On near-term quantum hardware, estimating a Born probability requires repeated circuit executions. A quantum learning experiment with a fixed measurement budget $B$ must therefore decide how many distinct training states $n$ to use and how many shots $S$ to spend on each. We study this trade-off for binary quantum classifiers whose measurement operator $M$ is learned from the training data and evaluated with fresh measurement outcomes. We prove a distribution-free generalization bound for bounded, $L$-Lipschitz losses with a sample term of order $\sqrt{d/n}$ and a shot term of order $\sqrt{(\log n)/S}$; under $B=nS$ the two terms move in opposite directions. Minimizing a closed-form surrogate of the bound gives the allocation rule $n^* = 2\sqrt{2dB/\log(4B/δ)}$, $S^* = B/n^*$, whose bound value is within 0.1% of the exact numerical minimum on all budgets we evaluate, and a worst-case rate of $B^{-1/4}$. PennyLane simulations with 2- and 4-qubit variational circuits on nine synthetic benchmarks show that the empirical gap stays below the bound in all configurations, although the bound is vacuous at the simulated budgets and becomes non-vacuous only for larger budgets (e.g., $B \gtrsim 5000$ for $d=4$). For a loss that is concave in the score, the empirical gap is U-shaped under a fixed budget and the measured shot contribution matches its analytical value; for the absolute loss, shot noise is unbiased and no shot-limited regime appears. The rule can be used to plan finite-shot evaluations before an experiment is run.

cs.AI

新论文 · v1arXiv:2611.25991

From AI Surrogate to Engineering Tool: Toward Production Use of Fiber-Orientation Prediction in Crash CAE

Osamu Ito, Yoshikazu Nakagawa, Tomoaki Tatsukawa

原文摘要

Crash simulations of glass-fiber-reinforced plastic parts are highly sensitive to the fiber-orientation field supplied to the material model. In conventional workflows, that field comes from resin-flow analysis, which requires molding-specialist support and takes about 25 hours of work per part. We previously proposed a surrogate model that addresses this bottleneck by predicting the orientation field in about 3 minutes. This paper reports the implementation, validation, and operational design that turned the model into an engineering tool for Honda design workflows. We present staged validation from 2D plates to production parts, evaluation against a predefined engineering angular-error criterion, and the expert review that approved design use in March 2025; the system has since been transferred to the crash-safety group and is in initial, limited use in directed fracture-prediction scenarios. The developed system combines injection-gate setting support for cases in which gates are unknown (90% gate-count accuracy, mean position error 11% of flow length), voxelization, surrogate inference, automatic mapping to the crash CAE model, and report generation in a single GUI. The complete orientation-preparation workflow takes about 0.1 hours, a 99.6% reduction from the conventional 25-hour flow-analysis route, and can be run directly by crash CAE engineers without molding-specialist support. As evidence of practical impact, component-level crash analysis using the predicted orientation field reduced the absolute peak-force error from 19.0% with an isotropic baseline to 11.4%, while confining predicted fracture to the test-observed region. The deployment lesson is that a surrogate model alone is not enough for practical adoption: gate-setting support, automatic data conversion, and shareable reporting are what make the model usable as a design tool.

cs.AI

新论文 · v1arXiv:2611.25990

Asymptotic Bounds for Codes in Toroidal Distance

Pengjie Zhong, Jinquan Luo

原文摘要

The toroidal distance naturally describes the geometry of codes over \(\mathbb Z_q\), where distances are measured modulo \(q\). In this paper, we study asymptotic bounds for codes in \(\mathbb Z_q^n\) under the toroidal metric. We first derive an explicit asymptotic lower bound from the classical Gilbert--Varshamov bounds for the Hamming and Lee metrics, which serves as a baseline for comparison. We then develop a saddle-point approach for the toroidal metric, which yields an asymptotic Gilbert--Varshamov lower bound and an asymptotic Hamming-type upper bound. For \(3\mid q\), we embed ternary Hamming codes into \(\mathbb Z_q^n\) and obtain another asymptotic lower bound for the toroidal metric. In addition, we derive an asymptotic lower bound for Maximum Toroidal Distance (MTD) codes. We compare these lower bounds with the baseline and prove that they are nontrivial in the corresponding parameter ranges. Finally, we compare the asymptotic bounds numerically.

cs.IT

新论文 · v1arXiv:2611.25989

Policy Improvement-Guided Replay for Continual Reinforcement Learning

Qin-Wen Luo, Haoxuan Gao, Sheng Ren, Xiang Chen, Sheng-Jun Huang

原文摘要

Continual reinforcement learning (CRL) requires models to acquire new capabilities while retaining performance on previous tasks. A stability-oriented perspective common in conventional continual learning emphasizes knowledge preservation and interference mitigation. Complementing this perspective, we revisit CRL for vision-language models through policy improvement, a fundamental principle of RL, to preserve acquired performance gains. Using the performance difference lemma, we characterize historical performance changes through the current policy's expected advantages on historical task distributions, motivating replay of historical prompts with the current policy. To allocate limited replay memory, we propose Contrastive Likelihood Replay (CoLiR), which contrasts likelihood gains on correct responses from the final task policy with likelihood reductions on incorrect responses from the initial policy. Our analysis links correct-response likelihood gains to reference-policy advantages under an idealized KL-regularized optimal update and provides an endogenous-reward interpretation for general policy updates. CoLiR estimates scores from finite training rollouts and cached log-likelihoods, selects prompts at task boundaries, and replays them uniformly during subsequent training, with KL regularization restricted to replayed prompts. Memory construction only requires a small amount of additional cross-policy scoring but no additional response generation. Across three Qwen3-VL model sizes on MRCL, CoLiR achieves the highest mean final accuracy and mean task accuracy among the compared methods while maintaining competitive new-task performance.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.25988

Sequential Contract Design for Budgeted Crowdsourcing

Michal Feldman, Vasilis Gkatzelis, Shaul Rosner, Inbal Talgam-Cohen

原文摘要

A principal wishes to crowdsource a collection of tasks under a fixed compensation budget. The quality of a task's outcome is stochastic and depends on the worker's effort level. Since this effort is unobservable, the principal offers contracts to workers specifying their compensation for each possible outcome. The principal offers these contracts sequentially, using previously observed outcomes and payments to decide whom to approach next and what contract to offer. The objective is to maximize the expected value of the work produced while ensuring that total payments never exceed the budget, regardless of the realized outcomes. Contract design must therefore account both for a worker's incentives and for the budget available to incentivize others. For valuations that are additive across tasks, we characterize how the approximability of the optimal adaptive policy depends on the numbers of workers, effort levels, and outcomes. Polynomial-time constant-factor approximation is possible whenever the number of workers, effort levels per worker, or outcomes per task is constant, but impossible in general when all three are unrestricted, unless $P=NP$. We obtain tight guarantees for every fixed number of workers, establish computational hardness even in restricted settings, and obtain exact algorithms and approximation schemes in more structured settings. We also investigate simple contract structures, demonstrating both the benefits of adapting contracts to previous outcomes and the limitations of local contract rules, while identifying conditions under which a local policy achieves a constant-factor guarantee. Finally, we extend our analysis beyond additive valuations, obtaining constant-factor approximations for monotone submodular valuations with binary outcomes, including guarantees against a stronger full-knowledge benchmark under additional assumptions.

cs.GT

新论文 · v1arXiv:2611.25986

Seeing Beyond the Obvious: Complementary Semantic Guidance for Salient Single-Positive Multi-Label Learning

Tong Jin, Meng-Long Wang, Xingyu Zhao, Sheng-Jun Huang

原文摘要

Salient Single-Positive Multi-Label Learning (SalSPML) assigns each image its most salient positive label, leaving other classes unlabeled. Existing methods construct class-level Salient Prototypes from observed positives to guide the recognition of unobserved classes. However, since salient annotations favor visually prominent instances, these prototypes may not fully capture the visual diversity of hidden positives, resulting in insufficient positive supervision. To address this limitation, we propose CoST, a Coverage-guided Complementary Soft-Target Refinement framework that supplements Salient Prototypes with complementary class-semantic information. Specifically, CoST identifies semantically relevant candidates from unknown classes by leveraging task-learned category information and image-text semantic correspondence. The selected candidates are then aggregated into class-wise Coverage Prototypes to complement the semantic representations provided by Salient Prototypes. Furthermore, we introduce a ranking-based selective refinement strategy that identifies classes receiving stronger semantic support from Coverage Prototypes and selectively enhances their soft targets while preserving the base soft targets for the rest. Experiments on multiple benchmarks demonstrate the effectiveness of CoST, with strong performance gains over existing baselines.

cs.LG

新论文 · v1arXiv:2611.25985

Law at the Speed of AI: Critical Legal Infrastructure for the Machine Age: Autonomy Under Law Architecture (AULA)

Natasha E Blycha, James Myint, Chen Feng, Dr Amani Soysa, Koshin Jama, Schellie-Jayne Price, Matthew Blycha

原文摘要

The global deployment of autonomous AI agents within and across organisations exceeds the governance infrastructure available to constrain it. Agent communication and authentication protocols, principally the Model Context Protocol and the Agent2Agent Protocol, are maturing quickly, but maturity at the protocol layer does not produce legal legibility at the governance layer. Runtime enforcement written by the deploying organisation fixes the resources an AI agent can reach, not the authority under which it acts. Legal legibility is the capacity of a legal system to recognise, interpret and regulate activity by mapping it onto legal personhood, property, rights and liabilities. Existing (analogue) legal infrastructure cannot supply it for autonomous deployment. The resulting deficit is bidirectional. It concerns the attribution of liability when an AI agent causes harm, and the allocation of rights, including data and economic rights, generated by agentic activity and by the AI agent itself as a source of value and form of property. This paper characterises that deficit as the legal attribution gap, a material and unaddressed risk to economies, organisations and citizens that is magnified in cross-organisational multi-agent deployment. The paper describes the Autonomy Under Law Architecture (AULA), in which AI systems and data assets are registered as legal objects anchored to one or more identified legal persons, governed by cryptographically tethered smart legal instruments and evaluated at runtime. Each smart legal instrument can carry a legal context clause, through which the legislation, regulation and judicial decisions in force at the time of the act are given practical and legal effect in that evaluation. Infrastructure of this kind is a precondition for the continued function of any legal, property and economic system with both human and autonomous machine stakeholders.

cs.CE · cs.AI · cs.ET · cs.MA

新论文 · v1arXiv:2611.25984

A Brief Overview of Non-Terrestrial Networks (Updated 2026)

Jose Alberto Hernandez, Pedro Reviriego

原文摘要

This article extends the 2023 preprint \emph{A brief introduction to satellite communications for Non-Terrestrial Networks (NTN)} (\href{https://arxiv.org/abs/2305.04590v1}{arXiv:2305.04590v1}) with a revision of its foundations, tables and state of the art as of 18 November 2026. It revisits propagation, link budgets, spectrum reuse and phased arrays, including corrected equations and numerical examples. Updated tables distinguish operational, launched and planned constellations and compare published fixed-terminal rates with direct-to-device services. The discussion incorporates developments in 3GPP Releases 17--20, commercial LTE-based direct-to-cell services and research towards 6G non-terrestrial networks. Operator announcements are distinguished from independent measurements and future plans. Open challenges include spectrum coordination, Doppler and timing compensation, mobility, capacity, security and the sustainability of low Earth orbit.

cs.NI

版本更新 · v2arXiv:2605.09435

Star Complexity of Parikh Images of Languages over Infinite Alphabets

Yoav Danieli

原文摘要

Parikh's theorem identifies the commutative images of regular and context-free languages over finite alphabets. We study the commutative images of quasi-regular and quasi-context-free languages over infinite alphabets, these are the languages that are accepted by the corresponding automata models augmented with registers. Over finite alphabets commutative images of regular languages are known to be precisely the semilinear sets, over infinite alphabets the corresponding algebraic sets are called rational sets of data vectors. In contrast to semilinear sets, nesting stars in rational sets add expressive power and thus star-height is a measure of complexity for this sets. It was previously established that languages accepted by one-register automata or one-register binary branching context-free grammars have rational commutative images. We refine this result by proving that the star-height of the commutative image of any one-register automaton is at most two. Using this extension, we prove rationality for all one-register context-free grammars, with arbitrary branching degree. Furthermore, we show that quasi-regular languages can have irrational commutative images already for a language accepted by a three-register automaton. Finally, we show that quasi-context-free languages can have commutative images that are different from the commutative image of any quasi-regular language, where the separation is witnessed again with three registers. Thus we conclude that Parikh's theorem fails over infinite alphabets for automata with registers.

cs.FL

新论文 · v1arXiv:2611.25980

Learning What Actions Change: Action Effect Matching for Dynamics-Faithful World Models

John Won, Yonghoon Dong, Jinwoo Shin

原文摘要

World models aim to predict environment dynamics under actions, enabling the prediction of action consequences without executing them in the real world. Yet despite producing increasingly realistic videos, current world models often fail to capture how small action changes affect future observations. This limits their use in tasks such as robotic policy evaluation and model-based planning, where nearly identical actions can lead to qualitatively different outcomes. To address this, we propose AFFECT, an auxiliary training objective for learning the distribution of visual changes induced by action perturbations. Specifically, we inject temporally correlated noise into the actions of a policy trained on task-agnostic human teleoperation. We then train the world model so that its generated videos respond to this noise as the recorded videos do, without requiring repeated executions from the same initial state. Across OGBench simulation and real-world DROID and ALOHA-2 setups, AFFECT makes world-model rollouts more faithful to real outcomes. On DROID, the Pearson correlation between policy success rates in the world model and on the real robot rises from 0.47 to 0.79, alongside up to 23% lower FVD. These gains carry over to planning, where selecting actions with AFFECT-trained world models improves task success by up to 8.3%.

cs.RO · cs.CV

版本更新 · v2arXiv:2608.24336

On the Maximum Number of Vertices that Belong to Every Metric Basis

Anni Hakanen, Ville Junnila, Tero Laihonen, Havu Miikonen, Ismael G. Yero

原文摘要

Resolving sets of graphs have been widely studied since their introduction in the 1970's by Slater and, independently, by Harary and Melter. The minimum cardinality of a resolving set of a graph $G$ is called the metric dimension of $G$ and is denoted by $\dim(G)$. In this paper, we concentrate on the existence of vertices in a graph $G$ that belong to all metric bases of $G$, i.e. resolving sets of cardinality $\dim(G)$. Such vertices are called basis forced vertices, and we denote the number of them by $\mathrm{bf}(G)$. We show that $\mathrm{bf}(G)\le 2/3(n-\dim(G)-1)$ for any connected nontrivial graph $G$ of order $n$. In addition, we show that this bound can be attained. Furthermore, it also implies that $\mathrm{bf}(G)\le 2/5(n-1)$ holds for any nontrivial connected graph $G$. This result answers a question posed by Bagheri \emph{et al.} in 2016. Moreover, we provide a complete realization of the parameters $n$, $\dim(G)$ and $\mathrm{bf}(G) \ge 1$ within the previous bounds. We consider some extremal cases related to basis forced vertices in a graph, in particular, we give a full characterization of the graphs with $\mathrm{bf}(G) = 2$ and $\dim(G) = n-4$.

math.CO · cs.DM

新论文 · v1arXiv:2611.25977

Blind tests of a simple-body model of submarine target strength on open benchmarks

Sunil Tyagi

原文摘要

Finite-element and boundary-element models of a submarine's sonar echo need a mesh and a solver, and their cost grows quickly with frequency. SSR-Sim takes an analytical route. The hull is cut into a few simple bodies, the echo of each is a closed-form result of geometrical acoustics or of the Kirchhoff approximation, the surface enters through a plane-wave reflection coefficient, and the echoes add in energy. This paper describes the method, including the reduction of a hull and its sail to simple bodies, and tests it on three open cases. (1) The reflection coefficient of a 50 mm rubber tile on steel plating, computed with finite elements by Yang et al., is reproduced to 0.02 rms or better at incidence angles from 0° to 75° once the layer is allowed to refract. (2) For the rigid full-scale BeTSSi submarine at 1 kHz, a prediction fixed before the reference was opened agrees with the boundary-element results of Venås and Kvamsdal to within 0.7 dB in every aspect sector from the bow to 150°; in the stern sector it is 5 dB high. (3) For a 1:15 BeTSSi model with 10 mm tiles measured in a lake, a second blind prediction is within -3.1, +1.4 and -0.5 dB of the measured level over aspects 0-120° at 5, 15 and 20 kHz, against -3.1, +3.1 and +3.5 dB for the Kirchhoff-finite-element computation published with the measurement. At 10 kHz, on a resonance of the tile, the prediction is 6.9 dB low, and in the bow sector it is 7 dB or more low at every frequency. The tests cover the specular component and the coating model only. The failures show what such a model lacks: edge diffraction and the returns that set the off-beam floor of a real model.

eess.AS · cs.SD · eess.SP

新论文 · v1arXiv:2611.25976

Energy estimates of open-weight large language models across stated food weights: a dose-response evaluation

Donato Riccio, Fabrizio Maturo, Iulia Brezeanu

原文摘要

We tested whether energy estimates of open-weight large language models (LLMs) scale proportionally with an exactly stated food weight, and whether computing energy density times weight removes the error. Under a prespecified protocol, seven open-weight LLMs estimated the energy of 168 randomly drawn foods from the USDA Food and Nutrient Database for Dietary Studies at nine stated weights, from 0.25 to 4 times the default amount. The primary outcome was the elasticity of the estimate with respect to weight (1: proportional scaling). A two-step estimate multiplied each model's own stated energy density by the weight in code. All seven models compressed their estimates, with elasticities from 0.548 to 0.979 (every 95% CI below 1); four compressed severely (0.548 to 0.709). These four overestimated a quarter of the default amount by 47% to 130% and underestimated four times it by 20% to 34%. Supplying the density restored near-proportional scaling in three of the four, and the two-step estimate cut the typical error factor at these extremes from 1.47-2.43 to 1.20-1.38. Compression persisted at full precision and grew in five of seven models under a plain question. The models hold the energy densities needed for proportional scaling and answer near a typical serving, reproducing the flat-slope syndrome of dietary recall. Accuracy at usual portions does not reveal it. Food-logging tools should compute the energy of weighed entries as density times weight, and evaluations should test fixed foods across stated weights.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25975

Sample-efficient end-to-end Optical Music Recognition through Active Learning

Eric Ayllon, Francisco J. Castellanos, Antonio Rios-Vila

原文摘要

End-to-end approaches to Optical Music Recognition (OMR) have recently shown promising results, but their performance often degrades on unseen data. A common solution is to pretrain and fine-tune models with annotated samples from the target domain, improving adaptation to new distributions. However, this process typically requires extensive manual annotation to yield competitive models, making it costly and time-consuming. In this work, we explore Active Learning to reduce this burden by selecting informative samples for labeling in low-resource scenarios, where the amount of manual annotation that can be performed is limited. We evaluate both uncertainty- and diversity-based sampling strategies on staff-level and full-page corpora. Results show that confidence-based sampling performs comparably to oracle selection (based on true error), and that each scenario benefits from a tailored strategy.

cs.CV

版本更新 · v3arXiv:2609.30059

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

原文摘要

Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted optimizers explore these opportunities through kernel generation and refinement; yet translating isolated kernel improvements into model-level gains remains a challenge. We present KernelOPT, a profiling-guided multi-agent system for GPU kernel optimization. It inspects generated Triton kernels and external library calls in compiler artifacts to guide synthesis and refinement, then assembles and evaluates the resulting model. Four stages of validation combine execution checks, multi-seed numerical comparison, model-level checking with a float64 fallback and end-to-end performance gating ($γ{=}1.03$). The system supports PyTorch nn.Modules, standalone Triton kernels, and Helion kernels. It is evaluated on all 250 KernelBench problems on NVIDIA H200 which includes 100 single-operator problems (Level1), 100 composite operators (Level2), and 50 model architectures (Level3). KernelOPT achieves geometric mean speedups over torch.compile of 1.40$\times$, 1.15$\times$ and 1.07$\times$ respectively across L1, L2 and L3. Among problems exceeding 1.03$\times$ speedup, the geomeans are 2.54$\times$ (36 L1), 1.84$\times$ (23 L2), and 1.37$\times$ (11 L3). These gains include arithmetic-precision changes and task-specific algebraic simplifications under the evaluated numerical tolerances. The evaluation also reveals discrepancies between isolated kernel improvements and end-to-end performance, motivating model-level measurement alongside kernel-level optimization. Code is available at https://github.com/TorchedHat/KernelOPT.

cs.DC · cs.AI · cs.LG

新论文 · v1arXiv:2611.25971

Kameleo: In-Situ Activation-Precision Selection for Bit-Serial LLM Accelerators

Robin Geens, Thomas Debelle, Marian Verhelst, Chao Fang

原文摘要

Weight-only quantization keeps the activations of large language models (LLMs) in a higher-precision format, pushing the on-chip inference cost to the activation arithmetic. Bit-serial, variable-length accelerators offer a promising path to reduce this cost by lowering activation precision while preserving model quality. They process only the mantissa bits that each layer needs. The length has to be chosen per layer and operator, and today it is chosen by offline calibration: a search driven by the perplexity of the full model on a representative dataset. The search is repeated for every model and workload, and its result degrades silently on other data. This paper presents Kameleo, an accelerator that selects the activation precision at runtime, on the accelerator, from the data it is processing. Kameleo replaces the global perplexity by a local proxy that compares the output of each GEMM at reduced and at full precision. It exploits the fact that a bit-serial datapath produces this comparison almost for free, because the reduced-precision result is an intermediate state of the full-precision computation. Two passes over the first tokens of a workload set the precision of every GEMM. On four LLMs and seven datasets, Kameleo stays within a 1% perplexity budget at a 2.11-2.34x reduction of prefill cycles on the matrix multiplication unit (MXU), close to the reduction of configurations calibrated offline on the evaluation data itself. Calibrated configurations transferred to other data, in contrast, often violate the budget. The selection hardware adds only 3.7% to the accelerator area. Kameleo thereby makes variable-length mantissas feasible in real deployments, where offline calibration for every model and workload is not.

cs.AR

版本更新 · v3arXiv:2604.15214

Optimal algorithmic complexity of inference in quantum kernel methods

Elies Gil-Fuster, Seongwook Shin, Sofiene Jerbi, Jens Eisert, Maximilian J. Kramer

原文摘要

Quantum kernel methods are among the leading candidates for achieving quantum advantage in supervised learning. A key bottleneck is the cost of inference: evaluating a trained model on new data requires estimating a weighted sum $\sum_{i=1}^N α_i k(x,x_i)$ of $N$ kernel values to additive precision $\varepsilon$, where $α$ is the vector of trained coefficients. The standard approach estimates each term independently via sampling, yielding a query complexity of $O(N\lVertα\rVert_2^2/\varepsilon^2)$. In this work, we identify two independent axes for improvement: (1) How individual kernel values are estimated (sampling versus quantum amplitude estimation), and (2) how the sum is approximated (term-by-term versus via a single observable), and systematically analyze all combinations thereof. The query-optimal combination, encoding the full inference sum as the expectation value of a single observable and applying quantum amplitude estimation, achieves a query complexity of $O(\lVertα\rVert_1/\varepsilon)$, removing the dependence on $N$ from the query count and yielding a quadratic improvement in both $\lVertα\rVert_1$ and $\varepsilon$. We prove a matching lower bound of $Ω(\lVertα\rVert_1/\varepsilon)$, establishing query-optimality of our approach up to logarithmic factors. Beyond query complexity, we also analyze how these improvements translate into gate costs and show that the query-optimal strategy is not always optimal in practice from the perspective of gate complexity. Our results provide both a query-optimal algorithm and a practically optimal choice of strategy depending on hardware capabilities, along with a complete landscape of intermediate methods to guide practitioners. All algorithms require only amplitude estimation as a subroutine and are thus natural candidates for early-fault-tolerant implementations.

quant-ph · cs.LG

新论文 · v1arXiv:2611.25968

Feedback-Free FDD Cell-Free Massive MIMO With Sparse AP Activation and Dual-Mode Precoding

Wei Jiang, Hans Dieter Schotten

原文摘要

This correspondence enables practical frequency-division duplex (FDD) operation in cell-free massive MIMO via two mechanisms. Sparse access-point (AP) activation reduces downlink pilot overhead to enable coherent detection, while angle-reciprocity precoding steers beams using only uplink-estimated angles, eliminating channel feedback entirely. A load-adaptive dual-mode optimizer further enhances performance: closed-form signal-to-leakage-and-noise-ratio precoding for high-load rate boosting, or semidefinite relaxation for low-load power minimization. Simulations verify its superiority over existing feedback-free FDD solutions in spectral and energy efficiency, and its robustness to angle errors, reciprocity mismatch, and multipath.

cs.IT · eess.SP

新论文 · v1arXiv:2611.25967

Barriers to GenAI Integration During Large-Scale Agile Transformation: An Exploratory Case Study

Nils Brede Moe, Marthe Berntzen, Astri Barbala, Viktoria Stray

原文摘要

Organizations undergoing large-scale agile transformations are increasingly introducing generative AI (GenAI) tools into everyday work. While GenAI promises to accelerate software development, less is known about how organizations integrate GenAI into existing large-scale agile ways of working and how it interacts with tensions related to autonomy, alignment, learning, and coordination. We examine barriers to GenAI integration through an exploratory case study of a large Nordic media organization undergoing a large-scale agile transformation. The findings reveal team-level barriers, including diverging AI beliefs, lack of shared practices, and limited experimentation capacity, and organizational-level barriers, including uneven AI maturity, weak organizational learning mechanisms, and cross-unit coordination and alignment challenges. Our findings suggest that GenAI does not create new organizational challenges but becomes intertwined with existing tensions in large-scale agile transformation and may intensify challenges related to learning, coordination, governance, and trust. We contribute to large-scale agile transformation research by showing how GenAI interacts with ongoing organizational change and by identifying conditions for sustainable GenAI integration at scale.

cs.SE

新论文 · v1arXiv:2611.25965

Power Setpoint Tracking for Large-Scale EV Charging: Transformer-Constrained Charging Policy Learning with Self-Tuning Constraint Prices

Daniyal Sajedi-Hosseini, Yoshihiko Fujisawa, Shubham Singh, Lei Zhou, Katsuki Fujisawa, Sebastien Gros, Mazaher Karimi, Xun Shen

原文摘要

In power setpoint tracking (PST), an operator follows a purchased charging profile without overloading shared transformers or undercharging vehicles. PST is cast as a constrained Markov decision process that minimizes tracking error subject to overload and mean user-satisfaction constraints. Transformer-Constrained Charging Policy Learning (TC-CPL) extends soft actor-critic with proportional-integral Lagrange-multiplier updates from measured violations, a residual on the incumbent dispatcher that is warm-started from its demonstrations, and a transformer-aware encoder shared by all ports. It observes no departure times or states of charge. Simulations (five seeds, 100 paired days) compare it with the incumbent, Round-Robin. On a 600-port, 122-substation district, raw overload falls from 3.59 to 0.0017 kWh/day (overloaded seed-days from 77% to 0.4%), and absolute tracking error falls by 27%. Delivered energy rises by 16%, and satisfaction rises from 0.959 to 0.989. On a 42-kW transformer with household load, overload falls from 1.86 to 0.0014 kWh/day and satisfaction rises from 0.974 to 0.985, but absolute tracking error is 22% higher. Against hand-set fixed multipliers, self-tuning is statistically indistinguishable on the district. On the single transformer, it raises satisfaction by 0.011 at similar overload, but a short sweep found a better-serving fixed pair. The overload multipliers stay below their cap.

cs.LG · eess.SY

版本更新 · v2arXiv:2611.24254

FedE2E: One-Shot Federated Learning for End-to-End Autonomous Driving with Closed-Loop Evaluation

Tao Lian, Antonio M. López

原文摘要

Federated learning enables collaborative model training without sharing datasets. However, existing federated learning methods for autonomous driving typically require multi-round communication and lack closed-loop evaluation, while one-shot methods mainly focus on perception tasks. To address these limitations, we propose \method, a one-shot federated learning method for end-to-end autonomous driving. It comprises multi-client calibration, anchor-based feature alignment, and token-wise consensus distillation to distill knowledge from heterogeneous models. Closed-loop evaluation on Bench2Drive demonstrates the effectiveness of \method in both one-shot and multi-round federated learning. In the one-shot setting, it achieves a Driving Score of 55.85, which is 4.07 points higher than prior work. In the multi-round setting, it reaches 60.35 after five communication rounds, the best performance among all compared methods under the same number of communication rounds.

cs.AI · stat.ML

新论文 · v1arXiv:2611.25963

MorphTwin: Enriching Deformable Material Responses from Videos for Morphable and Interactive Physical Twins

Haoqin Hong, Ding Fan, Fubin Dou, Tianyu Huang, Yuzhuo Chen, Zhemeng Zhang, Hanxiao Jiang, Congcong Zhu 等 11 位作者

原文摘要

Reconstructing interactive physical twins from video requires accurately capturing how objects deform while maintaining efficient simulation. We observe that reproducing motion in a video does not guarantee correct responses to new forces when the physical representation restricts how an object can deform. In spring-based twins, coupling between volume and shape responses creates such a limitation. We present MorphTwin, which enriches local deformation modes to capture and independently control these responses while retaining standard spring forces and explicit simulation. To support interpretable material editing and transfer, we use offline calibration to map shared relative response changes to stiffness updates on each reconstructed graph. Under identical inverse settings on synthetic scenes, MorphTwin reduces the mean absolute error of Poisson's ratio by 75.8% and the mean relative error of Young's modulus by 22.1% compared to PhysTwin. We introduce an egocentric stereo and RGB-D benchmark covering interactions with objects of varying stiffness. Real-world experiments demonstrate improved reconstruction accuracy and up to 14.4% lower future tracking error than PhysTwin at interactive speeds.

cs.CV