跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1352新增论文
+1083其中 AI 相关
+143已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 15:04各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 16:14 — 2026-11-19 16:14(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:2026-11-19 06:59最近发现新增版本:2026-11-19 15:04库内论文最新更新时间:2026-11-19 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。

27,409 已收录论文22,787 AI 相关8,342 有修订112 HF 社区发现

论文修订列表

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 8,342 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2607.27428

Rethinking AI in Medical Imaging: Assumptions, Reality, and Reframing; Towards Physician-Centered Agentic Reasoning

Arman Rahmim, Nourhan Bayasi, Xiaoxiao Li, Babak Saboury, Fereshteh Yousefirizi

原文摘要

Medical imaging has served as primary proving ground for clinical AI, yet a decade of intense research has not translated into proportionate bedside impact. We argue that this gap is not primarily a product of insufficient algorithmic performance, inadequate regulation, or limited explainability. Rather, it reflects a structural misalignment, between how AI systems are designed and evaluated, and how clinical decisions are made. This work identifies 8 interconnected dimensions of this misalignment: 1) the dominance of pixel-only models in a multimodal clinical world; 2) the erosion of physician trust through opaque and inflexible systems; 3) the unfulfilled promise of foundation models in data-sparse medical domains; 4) the persistent bottleneck of non-shareable under-curated datasets; 5) the gap between validated algorithms and deployable clinical platforms; 6) the slow, unmonitored translation of evidence into routine practice; 7) the risk of AI displacing rather than extending physician judgment; and 8) the failure of prediction-centric AI to generate actionable, agentic clinical guidance. For each dimension, we reframe the problem and propose a path forward, culminating in a vision of physician-centered AI solutions with agentic reasoning that extend, rather than replace, clinical judgment.

physics.med-ph · cs.AI

版本更新 · v2arXiv:2610.28397

MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas, Miguel Ballesteros, Yassine Benajiba, Sujith Ravi, Dan Roth

原文摘要

Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and adversarial manipulation. Multi-agent systems further expand these capabilities through specialization and collaboration, but distributed authority, heterogeneous roles, and opaque or potentially compromised participants make safeguarding even more challenging. Existing defenses address important individual threats but provide fragmented coverage across local execution, system-level interactions, and enforcement mechanisms. We introduce MAS-Guard, a unified framework that closes this gap for safeguarding single- and multi-agent AI applications containing both instrumentable and opaque agents. Within instrumentable agents, the proposed local Agent Guardrail (A-Guard) layer applies task-specific experts to assess agentic events. At the system level, developer-owned Agent Charters and a Control Plane combine deterministic structural checks of routes, agent capabilities, and message formats with semantic assessments of roles and message content. These complementary layers enable enforcement through a shared set of interventions: allow, reflection, confirmation, and block. Evaluated across six benchmarks covering diverse single- and multi-agent scenarios with three agent LLMs from different providers, MAS-Guard reduces the overall attack success rate by 71.5-86.3% relative to unguarded agents, while meeting the utility reference criterion on benign tasks.

cs.CR · cs.AI · cs.CL

版本更新 · v2arXiv:2610.13201

Compact Quantitative Equational Theories as Monad Restrictions

Matteo Mio, Colin Riba

原文摘要

Proofs in quantitative algebra are, generally, infinite objects due to the presence of infinitary rules in the deductive apparatus. A quantitative equational theory is called compact if all its consequences are derivable by means of finite proofs, that is, proofs not using any instances of the infinitary rules. This definition is purely logical. In this work we give an equivalent, but categorical, characterisation based on the notion of monad restriction.

cs.LO

版本更新 · v2arXiv:2606.25990

SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models

Liang-Yuan Wu, Zih-Ching Chen, Tongshuang Wu, Chao-Han Huck Yang, Hua Shen

原文摘要

As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critical bottleneck for natural human-AI communication. However, existing evaluations of machine emotional intelligence assess reasoning exclusively through isolated text or passive acoustic perception, overlooking the complex cross-modal reasoning required for active, multi-turn dialogue. We introduce \textsc{SpeechEQ}, a comprehensive framework designed to evaluate the sociolinguistic reasoning of Speech-Language Models (SLMs). The framework includes a validated dataset of 2,265 dialogues across 15 Emotional Quotient (EQ) subscales grounded in EQ-i 2.0 theory, along with a multi-turn evaluation protocol measured by our proposed Spoken EQ (SEQ) score inspired by human EQ assessments. Experiments show limitations in how both existing Speech Emotion Recognition and end-to-end Speech-Language Models understand and apply paralinguistic cues through speech. While end-to-end architectures outperform cascaded systems, \textsc{SpeechEQ} reveals that current multimodal models remain bottlenecked by a text-reliant ``modality shortcut,'' an alignment-induced ``safety trap,'' and ``contextual amnesia,'' highlighting the barriers to truly emotionally aware AI. Our benchmark can be accessed at https://huggingface.co/datasets/SpeechEQ/SpeechEQ and demo page at https://speecheq.github.io

cs.CL · cs.AI · cs.SD

版本更新 · v2arXiv:2111.08222

Impact of Model Interpretability and Outcome Feedback on Trust in AI

Daehwan Ahn, Abdullah Almaatouq, Monisha Gulabani, Kartik Hosanagar

原文摘要

This paper bridges the gap in Human-Computer Interaction (HCI) research by comparatively assessing the effects of interpretability and outcome feedback on user trust and collaborative performance with AI. Through novel pre-registered experiments (N=1,511 total participants) using an interactive prediction task, we analyzed how interpretability and outcome feedback influence users' task performance and trust in AI. The results counter the widespread belief that interpretability drives trust, showing that interpretability led to no robust improvements in trust and that outcome feedback had a significantly greater and more reliable effect. However, both factors had modest effects on participants' task performance. These findings suggest that (1) interpretability may be less effective at increasing trust than factors like outcome feedback, and (2) augmenting human performance via AI systems may not be a simple matter of increasing trust in AI, as increased trust is not always associated with equally sizable performance improvements. Our exploratory analyses further delve into the mechanisms underlying this trust-performance paradox. These findings present an opportunity for research to focus not only on methods for generating interpretations but also on techniques that ensure interpretations impact trust and performance in practice.

cs.AI · cs.HC

版本更新 · v5arXiv:2605.03639

Diffusion Masked Pretraining for Dynamic Point Cloud

Zhuoyue Zhang, Yiding Sun, Chaowei Fang, Haozhe Cheng, Jian Liu, Ajmal Saeed Mian, Jihua Zhu

原文摘要

Dynamic point cloud pretraining is still dominated by masked reconstruction objectives. However, these objectives inherit two key limitations. Existing methods inject ground-truth tube centers as decoder positional embeddings, causing spatio-temporal positional leakage. Moreover, they supervise inter-frame motion with deterministic proxy targets that systematically discard distributional structure by collapsing multimodal trajectory uncertainty into conditional means. To address these limitations, we propose Diffusion Masked Pretraining (DiMP), a unified self-supervised framework for dynamic point clouds. DiMP introduces diffusion modeling into both positional inference and motion learning. It first applies forward diffusion noise only to masked tube centers, then predicts clean centers from visible spatio-temporal context. This removes positional leakage while preserving visible coordinates as clean temporal anchors. DiMP also reformulates point-wise inter-frame displacement supervision as a DDPM noise-prediction objective conditioned on decoded representations. This design drives the encoder to target the full conditional distribution of plausible motions under a variational surrogate, rather than collapsing to a single deterministic estimate. Extensive experiments demonstrate that DiMP consistently improves downstream accuracy over the backbone alone, with absolute gains of 11.21\% on offline action segmentation and 13.65\% under causally constrained online inference. Code is available at https://github.com/InitalZ/DiMP.

cs.CV

版本更新 · v3arXiv:2608.01693

Money Burning Mechanism Design: From Welfare to Surplus

Tomer Ezra

原文摘要

We study mechanism design for consumer-surplus maximization, where the objective is the total value generated minus the payments charged to agents. This objective captures settings in which incentives rely on costly actions, such as waiting or effort, whose costs are lost rather than transferred. We settle the welfare-approximation question of Hartline and Roughgarden [HR08] by determining the exact worst-case loss from money burning in general multidimensional environments. For $n$ agents with arbitrary nonnegative valuations over a finite outcome space, we give a universally truthful, ex-post individually rational mechanism with nonnegative payments whose expected consumer surplus is at least a $1/H_n$ fraction of optimal welfare for every valuation profile, where $H_n=\sum_{k=1}^n 1/k$. The mechanism requires no knowledge of the agents' value distributions. Nevertheless, the factor $H_n$ is worst-case optimal, including its constant, even for a single-item auction with a known i.i.d.\ prior and Bayesian incentive compatibility. Thus, the optimal worst-case loss is exactly the same for arbitrary multidimensional preferences as for a single item: neither the number of goods nor the complexity of preferences increases this loss. We further give black-box reductions from welfare approximation to consumer-surplus maximization. On valuation domains closed under scaling, any truthful, ex-post individually rational $α$-approximation for welfare with nonnegative payments yields an $O(α\log n)$-approximation for surplus while preserving these incentive properties. For known finite-support product priors and exact interim-value access, a Bayesian reduction converts arbitrary allocation algorithms, even nontruthful ones, into Bayesian incentive-compatible, ex-post individually rational mechanisms with nonnegative payments and an $H_n+\varepsilon$ loss for every $\varepsilon>0$.

cs.GT

版本更新 · v2arXiv:2609.22695

A Survey on the Linear Representation Hypothesis

Sewoong Lee, Marc E. Canby, Ikhyun Cho, Julia Hockenmaier

原文摘要

The term "linear representation hypothesis" (LRH) has appeared across diverse subfields of artificial intelligence, neuroscience, and cognitive science. But previous works have not consistently treated the LRH as a falsifiable scientific hypothesis; we analyze these inconsistencies and examine their implications for how prior theoretical and methodological results should be interpreted. Based on this analysis, we argue that claims regarding linear representations become well-defined only through careful examination of the model, representation location, feature definition, and evaluation dataset. We therefore propose a more rigorous formalization of the LRH that makes these dependencies explicit and allows the hypothesis to be evaluated as a falsifiable scientific claim. Finally, we identify some non-trivial open problems that warrant further attention from the research community.

cs.AI

版本更新 · v2arXiv:2609.18823

Using OCR Heads to Verbalize Image Semantics

Sheridan Feucht, Benno Krojer, Sarah Wang, Henry Abrahamsen, Byron C. Wallace, David Bau

原文摘要

How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Across four models, we identify attention heads causally necessary for OCR, and discover that these are in fact general-purpose heads that output interpretable semantic features across all image tokens. For example, pointing these heads at an image token containing the word "bike" causes Qwen3-VL-8B to output "bike," but pointing them at a bird wing causes the model to output the token "feathers." We collapse these heads' attention weights into a single verbalization lens transformation that reveals interpretable semantic features in hidden states across all layers. When combined with projection to vocabulary space, we can obtain interpretable labels starting from layer 0, showing that image representations are in fact aligned with language in early layers. We find that we can also use the inverse of this transformation to edit non-word concepts, e.g., replacing a tractor with a revolver in a naturalistic image, providing causal evidence that this subspace is useful for more than just OCR. Our results are an example of how the study of specific mechanisms can shed light on broader interpretability problems.

cs.CV · cs.AI · cs.CL

版本更新 · v4arXiv:2602.05786

Selecting Hyperparameters for Tree-Boosting

Floris Jan Koster, Fabio Sigrist

原文摘要

Tree-boosting is a widely used machine learning technique for tabular data. However, its out-of-sample accuracy is critically dependent on multiple hyperparameters. In this article, we empirically compare several popular methods for hyperparameter optimization for tree-boosting including random grid search, the tree-structured Parzen estimator (TPE), Gaussian-process-based Bayesian optimization (GP-BO), Hyperband, the sequential model-based algorithm configuration (SMAC) method, and deterministic full grid search using $59$ regression and binary classification data sets. We find that the SMAC method clearly outperforms all the other considered methods on average, and it gives stable performance across a diverse collection of tabular data sets under a fixed tuning budget, which is relevant for users who cannot afford extensive manual trial-and-error tuning. We further observe that (i) a relatively large number of trials larger than $100$ is typically required for accurate tuning, (ii) using default values for hyperparameters or a full search over a small grid often yields very inaccurate models, (iii) all considered hyperparameters can have a material effect on the accuracy of tree-boosting, i.e., there is no small set of hyperparameters that is more important than others, and (iv) choosing the number of boosting iterations using early stopping yields more accurate results compared to including it in the search space for regression tasks.

cs.LG · stat.AP · stat.ML

版本更新 · v6arXiv:2302.03569

Consensus in label propagation on binomial random graphs

Marcos Kiwi, Lyuben Lichev, Dieter Mitsche, Paweł Prałat

原文摘要

Understanding how local update rules amplify small random fluctuations into global consensus is a central challenge in the study of network dynamics and decentralized processes. A prominent family of examples is given by label propagation algorithms, widely used heuristics for community detection whose analysis is complicated by the strong dependencies created as the process evolves. Despite the simplicity and practical success of this class of algorithms, a rigorous understanding of their convergence remains limited. In this paper, we study a specific variant, which we refer to as LPA, on the binomial random graph $\mathcal{G}(n,p)$ - a canonical null model with no planted community structure. We show that LPA reaches consensus asymptotically almost surely when $np\ge n^{5/8+\varepsilon}$ for any fixed $\varepsilon>0$, thus breaking the current best $n^{3/4+\varepsilon}$ analytical barrier. More remarkably, we uncover a phase transition governing \emph{which} label survives: when $np\gg n^{2/3}$, the surviving label is asymptotically almost surely the smallest initial label, whereas for $n^{5/8+\varepsilon}\le np\ll n^{2/3}$, the surviving label is asymptotically almost surely not the smallest one. We further show that, in the critical window $np=Θ(n^{2/3})$, both outcomes have probability $Θ(1).$ Our analysis has several important ingredients. We analyze a staged exploration that progressively reveals information about the random graph while preserving some randomness needed to track the amplification of label advantages across multiple rounds. This analysis is complemented by novel coupling and decoupling arguments that control the dependencies inherent to the process. Along the way, we establish a monotonicity result for competing binomial random variables that we believe is of independent interest.

math.PR · cs.CC

版本更新 · v2arXiv:2610.10474

Fast Almost-Uniform Sampling of Random $k$-SAT Solutions

Kun He, Zhidan Li, Kuan Yang

原文摘要

We study approximately uniform sampling of satisfying assignments from random $k$-SAT formulas. Fix a constant $B>0$. For every $k\ge 2^{20}$ and density $0<α\le 2^k/k^{16}$, we prove that, with high probability over a random formula on $n$ variables, every accuracy $n^{-B}\le\varepsilon\le 1/2$ admits a sampler whose output distribution is within total variation distance $\varepsilon$ of the uniform distribution on satisfying assignments with expected running time $$\widetilde O_B\left(\mathrm{poly}(k,α+1)n^{2+η}\right),\quad 0<η\le 2^{16-k}.$$ In particular, the exponent of $n$ is $2+O(2^{-k})$ while the dependence on the width and density is polynomial with a universal degree. This improves the parameter-dependent polynomial exponent of the sampling algorithm of Chen, Lonkar, Wang, Yang, and Yin (STOC 2025) in the density regime $2^k/\mathrm{poly}(k)$. Our algorithm separates a high-degree core from the remaining variables. Every residual formula on the good variables is a deletion subformula of a common bounded-dependency formula. Adapting the rejection--repair framework of Liu, Wang, Yin, Zhang and Zhou (arXiv 2026), we construct an executable sampler for all such residual formulas using ordinary connected violation sets replacing weighted 2-tree witnesses and use it to simulate approximate block heat-bath updates on the core. To analyze the resulting core chain, we integrate out the good variables, represent the core marginal by an absolutely convergent polymer expansion and combine a component-swap variance comparison with an adaptive exploration bound. Absorbing single-component interactions into the local weights leaves interactions of cluster size at least two; retaining their additional decay gives a spectral gap of at least $1/(2s n^{2^{12-k}})$ where $s$ counts core components. Together with the residual sampler, this yields the stated running time.

cs.DS · cs.DM · math.PR

版本更新 · v2arXiv:2609.37815

Concurrent Strategies as Street Fibrations

Hugo Paquet, Glynn Winskel

原文摘要

Concurrent games and strategies based on event structures are an established and expressive model of interactive computation. In this paper we revisit the problem of equipping this model with symmetry. Symmetry is essential for many applications, but it is also a source of mathematical complexity, not least because strategies with symmetry can be compared up to several distinct notions of equivalence. Our first contribution is a complete characterization of two classes of strategies for which composition admits an identity. For these two classes the identity laws hold, respectively, up to a "weak" and a "strong" notion of equivalence. The main result is that the weak class of strategies corresponds precisely to those inducing Street fibrations over the game. We also show how the established "thin" approach to symmetry also fits in this general framework. A second contribution is a formal connection between games and setoid-valued profunctors. This follows a long tradition of relating games and relational models, but here additionally includes a very general model of symmetries. Our characterization of strategies as Street fibrations makes the connection to profunctors significantly easier to establish.

cs.LO · math.CT

版本更新 · v2arXiv:2604.06942

Empirical Ciphertext Distinguishability Testing of KEMs and Hybrid Encryption via Deep Learning

Simon Calderon, Niklas Johansson, Onur Günlü

原文摘要

We model indistinguishability under chosen-plaintext attack (IND-CPA) games as binary classification tasks for deep neural networks (DNNs). We apply this methodology to the public-key encryption (PKE) schemes used to construct PQC key encapsulation mechanisms (KEMs) such as ML-KEM and HQC, and to cascaded symmetric algorithms, demonstrating methodological generality. Moreover, we present a novel extension of this approach to empirical distinguishability testing of hybrid KEMs. For IND-CPA-secure schemes and their combinations, no DNN achieves accuracy significantly different from random guessing (measured via Bonferroni-corrected binomial tests), consistent with theoretical security guarantees. For insecure schemes, such as plain RSA, AES-CTR and AES-CBC with IV or counter reuse, or RC4, the DNNs classify the ciphertexts better than random guessing. Thus, this framework is shown to serve as a practical, scheme-agnostic tool for flagging distinguishable ciphertexts in both individual and composed constructions.

cs.CR · cs.IT · cs.LG · cs.NE · eess.SP

版本更新 · v3arXiv:2602.14960

EMAR: Efficient Multi-domain Adaptive Retrieval

Pranav Kasela, Marco Braga, Ophir Frieder, Nazli Goharian, Gabriella Pasi, Raffaele Perego

原文摘要

Neural retrieval systems are increasingly deployed in multi-domain settings, where each domain may have its own vocabulary and word distribution. A common approach is to fine-tune separate models for each domain, achieving strong in-domain performance while increasing training costs and storage requirements. In contrast, a single model trained jointly across domains avoids model duplication but weakens robustness under domain shift. This creates a trade-off between effectiveness and resource-efficiency. To address this issue, we propose EMAR, a retrieval system that employs a single frozen model shared across all domains and introduces lightweight domain-specific adapters. At inference time, a learned routing mechanism dynamically selects the most suitable adapter for each query. EMAR enables efficient domain-specific retrieval by sharing the computationally expensive backbone across multiple domains and without maintaining multiple full models. Experimental results on three multi-domain benchmarks spanning seventeen domains and three retrieval architectures show that EMAR achieves retrieval effectiveness on par or even better than fully fine-tuned domain-specific models while requiring storing only a small fraction of parameters per domain. Furthermore, EMAR exhibits strong generalization to previously unseen domains, highlighting its effectiveness as an extensible solution for multi-domain retrieval.

cs.IR

版本更新 · v2arXiv:2603.04743

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang

原文摘要

Large Language Model (LLM) agents excel at automating data science workflows, yet often underutilize rigorous statistical methods in R. Existing Retrieval-Augmented Generation (RAG) approaches rely on semantic similarity, ignoring the data-distribution and structural characteristics crucial for determining a statistical method's applicability. To address this, we propose DARE (Distribution-Aware Retrieval Embedding), a representation learning framework incorporating these data characteristics into R function retrieval. Our contributions are fourfold: (i) RPKB, a curated knowledge base of 8,191 high-quality R functions; (ii) DARE, the distribution-aware retrieval framework; (iii) RCodingAgent, an R-oriented agent integrating DARE for end-to-end analysis; and (iv) RStatBench, a comprehensive benchmark of 100 statistical tasks. Experiments demonstrate that DARE improves NDCG@10 by 13.43 to 32.65 percentage points across evaluated embedding models, with a MiniLM-based DARE achieving 93.92% NDCG@10 alongside high efficiency. Furthermore, integrating DARE into RCodingAgent nearly doubles mean downstream accuracy on RStatBench, increasing from 31.8% to 62.2% across ten LLMs. This work helps bridge modern LLM automation with R's established statistical computing ecosystem.

cs.IR · cs.AI · cs.CL

版本更新 · v2arXiv:2609.08850

Matching in Context: Temporal Fusion and Query Adaptation for Training-Free Video Temporal Grounding

Zhuo Cao, Bingqing Zhang, Sen Wang, Xue Li

原文摘要

Text-guided Video Temporal Grounding (VTG) localizes moments in an untrimmed video that correspond to a text query. Supervised approaches require costly temporal annotations and task-specific training, yet can generalize poorly under distribution shift. To reduce this dependence on task-specific supervision, training-free approaches use pretrained vision-language models to localize moments by measuring the similarity between video and query features. However, independently encoded frames provide limited temporal context, while a fixed query embedding can assign similar scores to different candidate moments within the video. To address these limitations, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that combines visual evidence across temporal granularities with video-specific query adaptation, without task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the query side, Query-level Test-Time Adaptation (Q-TTA) uses pseudo-labels to optimize a lightweight additive offset for more discriminative matching within the video, without fine-tuning the backbone or calling external large language models. Experiments on three standard and two out-of-distribution (OOD) benchmarks show gains over the prior training-free methods. On Charades-STA, DSE-VTG improves mIoU by 5.89 percentage points over the strongest compared baseline under the same backbone. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.

cs.CV

版本更新 · v2arXiv:2607.16193

UAV-DualCog: A Dual-Cognition Benchmark for Grounded UAV Agent-World Reasoning with MLLMs

Like Liu, Zhengzheng Xu, Hongzhe Li, Lin Wang, Dian Shao

原文摘要

Multimodal large language models (MLLMs) perform strongly across vision-language tasks, yet remain insufficiently explored in UAV scenarios. Recent UAV-oriented benchmarks have begun to evaluate MLLMs in aerial scenarios, but typically focus on scene understanding, event recognition, or navigation completion, rather than jointly assessing the dual-cognition capability required for UAV agents: reasoning about the UAV's own position, behavior, and observation state alongside external landmark states under continuously changing viewpoints, supported by explicit spatio-temporal grounding. To address this gap, we present UAV-DualCog, the first benchmark to formulate UAV dual cognition as the coordinated evaluation of Agent-State Reasoning and World-State Reasoning across multi-view images and egocentric videos, with explicit spatial or temporal grounding. The State-aware UAV Simulation Platform (SUSP) and the DualCog-aware Capture System (DCCS) construct 4,096 image and 2,048 video samples from 12 scenes, pairing complementary state questions within shared Agent-Landmark contexts. Extensive evaluations on 45 models show that current MLLMs remain far from reliable in UAV dual cognition: Agent-State Reasoning is generally weaker than World-State Reasoning, semantic answers do not reliably coincide with spatial or temporal grounding, and coordinated abilities remain limited. Thinking-mode comparisons, open-ended analyses, and sim-to-real validation show that these limitations persist across inference settings, formats, and environments. We further construct UAV-DualCog-Train and improve UAV dual-cognition performance through a lightweight optimization probe. Supplementary website, code, and dataset: https://smartdianlab.github.io/UAV-DualCog/

cs.CV

版本更新 · v2arXiv:2511.02386

Monadic Second-Order Logic of Permutations

Vít Jelínek, Michal Opler

原文摘要

Permutations can be viewed as pairs of linear orders, or more formally as models over a signature consisting of two binary relation symbols. This approach was adopted by Albert, Bouvel and Féray, who studied the expressibility of first-order logic in this setting. We focus our attention on monadic second-order logic. Our results go in two directions. First, we investigate the expressive power of monadic second-order logic. We exhibit natural properties of permutations that can be expressed in monadic second-order logic but not in first-order logic. Additionally, we show that the property of having a fixed point is inexpressible even in monadic second-order logic. Secondly, we focus on the complexity of monadic second-order model checking. We show that there is an algorithm deciding if a permutation $π$ satisfies a given monadic second-order sentence $\varphi$ in time $f(|\varphi|, \operatorname{tw}(π)) \cdot n$ for some computable function $f$ where $n = |π|$ and $\operatorname{tw}(π)$ is the tree-width of $π$. On the other hand, we prove that the problem remains hard even when we restrict the permutation $π$ to a fixed hereditary class $\mathcal{C}$ with mild assumptions on $\mathcal{C}$.

math.CO · cs.LO · math.LO

版本更新 · v2arXiv:2610.33941

TurboWAM: Learning What Matters for Fast World Action Models

Guile Wu, Shuangzhi Li, Xingxin Chen, Chengjie Huang, Sam Hosseini, Tongtong Cao, Yingxue Zhang, Dongfeng Bai

原文摘要

World action models have demonstrated promising performance in robot policy learning, yet their high inference latency remains a critical bottleneck for real-world deployment. Recent approaches have sought to improve inference efficiency by eliminating test-time future-frame imagination or accelerating action prediction. However, aggregating representations from all video world model layers can introduce redundant computation, while standard backpropagation may distribute action-supervision gradients unevenly across layers, limiting the effectiveness of world representation learning. In this work, we propose TurboWAM, a fast world action model that learns to efficiently aggregate and optimize world representations for action prediction. Specifically, TurboWAM introduces an efficient world representation aggregation mechanism that restricts aggregation to a bounded range of relevant world model layers identified through layer relevance analysis. Within this bounded range, TurboWAM estimates aggregation weights for different world model layers based on the current action denoising state and combines them with learnable layer-wise weights to fuse world representations. Moreover, TurboWAM employs a world model gradient modulation mechanism that decomposes action-supervision gradients into a layer-shared component and layer-specific residual components, enabling more balanced gradient propagation across world model layers. This mechanism operates exclusively during training and introduces no additional inference computation. Together, these designs enable more efficient world representation learning and low-latency action prediction. Extensive experiments on multiple robot manipulation benchmarks and real-world manipulation tasks show that TurboWAM achieves low inference latency while maintaining competitive task success rates compared with state-of-the-art methods.

cs.CV

版本更新 · v3arXiv:2501.19214

A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization

Wei Liu, Yangyang Xu

原文摘要

Many real-world problems, such as those with fairness constraints, involve complex expectation constraints and large datasets, necessitating the design of efficient stochastic methods to solve them. Most existing research focuses on cases with no {constraint} or easy-to-project constraints or deterministic constraints. In this paper, we consider nonconvex nonsmooth stochastic optimization problems with expectation constraints, for which we build a novel exact penalty model. We first show the relationship between the penalty model and the original problem. Then on solving the penalty problem, we present a single-loop SPIDER-type stochastic subgradient method, which utilizes the subgradients of both the objective and constraint functions, as well as the constraint function value at each iteration. Under certain regularity conditions (weaker than Slater-type constraint qualification or strong feasibility assumed in existing works), we establish an iteration complexity result of $O(ε^{-4})$ to reach a near-$ε$ stationary point of the penalized problem in expectation, matching the lower bound for such tasks. Building on the exact penalization, an $(ε,ε)$-KKT point of the original problem is obtained. For a few scenarios, our complexity of either the {objective} sample subgradient or the constraint sample function values can be lower than the state-of-the-art results by a factor of $ε^{-2}$. Moreover, on solving two fairness-constrained problems and a multi-class Neyman-Pearson classification problem, our method is significantly (up to 466 times) faster than the state-of-the-art algorithms, including switching subgradient method and inexact proximal point methods.

math.OC · cs.CC · cs.LG · math.NA

版本更新 · v3arXiv:2605.14746

Selective Safety Steering via Value-Filtered Decoding

Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano

原文摘要

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using a safety score. However, existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model. Such unnecessary interventions are undesirable, as they can distort key properties of the base model such as helpfulness, fluency, style, and coherence. We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of responses. Our approach filters tokens using a value-based safety criterion and provides an explicit bound on the probability of false interventions. A single threshold hyperparameter controls this bound, allowing practitioners to trade off higher rates of unnecessary intervention for better output safety. Across multiple datasets and experiments, we show that our value-filtered decoding method outperforms existing baselines, achieving better trade-offs between safety, helpfulness, and similarity to the base model.

cs.LG

版本更新 · v2arXiv:2606.07688

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

Ziheng Chen, Jiali Cheng, Zezhong Fan, Hadi Amiri, Diyuan Wu, Gabriele Tolomei, Yang Zhang

原文摘要

Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern recommender systems structurally similar to large language models (LLMs). As privacy and safety concerns grow, these systems increasingly require concept unlearning to remove sensitive or harmful concepts associated with items. However, existing LLM unlearning methods cannot be directly applied to generative recommendation. Unlike word tokens with explicit semantics, SIDs are abstract identifiers that are often shared by both forget and retain items, leading to severe conflicts between concept removal and recommendation utility preservation. To address this challenge, we propose TRACER, an end-to-end concept unlearning framework based on token reassignment. Rather than directly suppressing shared SIDs, TRACER reassigns concept-related items to alternative tokens that better facilitate forgetting while minimizing side effects on retained items. We further introduce a coherence regularizer to preserve semantic consistency among retain items during unlearning. Experiments on real-world recommendation datasets demonstrate that TRACER effectively removes target concepts while substantially better preserving recommendation utility than existing unlearning baselines.

cs.IR · cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2405.01708

A deep causal inference model for interpretable travel behaviour analysis

Kimia Kamal, Bilal Farooq

原文摘要

Transportation policy assessment often involves causal questions, yet traditional travel behaviour lacks the ability of distinguishing causal association from non-causal correlations. We present the deep CAusal infeRence mOdel for traveL behavIour aNAlysis (CAROLINA), a novel framework that addresses both observed and unobserved confounders in discrete choice modelling through causal discovery and the strengths of deep neural networks. Within this interpretable framework, we also introduce a Generative Counterfactual model for forecasting individuals' behaviour by adapting the Normalizing Flow method. Through the case studies of virtual reality-based pedestrian crossing behaviour, revealed preference travel behaviour from London, and synthetic data, we demonstrate the effectiveness of our proposed models in isolating causal relationships from confounding associations. Our proposed causal framework enhances predictive accuracy by employing data-driven algorithms, while maintaining interpretability. In addition, the counterfactual results show that intervention mechanisms that can reduce pedestrian stress levels lead to a 35.35% increase in individuals experiencing shorter waiting times. External interventions that reduce travel distances of non-mandatory trips in London lead to a 47% increase in the possible use of active and public transit modes.

cs.LG

版本更新 · v3arXiv:2609.12352

Spatial Mixing and Deterministic Approximate Counting of Multi-spin Systems beyond Bounded Degree Graphs

Zhidan Li, Kuan Yang

原文摘要

We develop a framework for deterministic approximate counting of multi-spin systems beyond bounded-degree graphs. The algorithm recursively constructs rational polytopes containing the true marginal vectors and uses linear-fractional programming to obtain certified bounds on marginal ratios. For positive interactions on graphs of polynomial connective constant $D$, we establish strong spatial mixing whenever $Dc<1$, where $c$ bounds the Birkhoff contraction coefficients of the interactions. Under the same condition, we also give a deterministic fully polynomial-time approximation scheme (\textbf{FPTAS}) for the partition function. We further extend the framework to proper colorings of sparse Erdős-Rényi random graphs using recursion on permissive blocks. For every fixed $η\in(0,1)$, sufficiently large fixed $d$, and fixed integer $q\ge(2+η)d$, we obtain an \textbf{FPTAS} for counting proper $q$-colorings of $G\sim\mathcal G(n,d/n)$ with high probability over $G$. This improves the leading constant $3$ in the earlier counting guarantee of Yin and Zhang (APPROX/RANDOM, 2016) to $2$, and asymptotically matches the spatial mixing regime established by Yin (ICALP, 2014).

cs.DS · math.PR

版本更新 · v2arXiv:2609.40278

Computational Bounds for $f$-Routing

Oren Renard, Nicholas Spooner

原文摘要

The $f$-routing protocol is a leading candidate for quantum position verification (Kent, Munro, and Spiller, Physical Review A, 2011), but security guarantees for explicit functions remain limited. We prove unconditional resource lower bounds for uniform attackers. Our techniques bypass communication-complexity bounds central to previous works, which are inherently at most linear in the input length. We show that, for input length $n$ and a sufficiently small constant $ε>0$, a uniform strategy running in time $T$ and succeeding with probability at least $1-ε$ on every input implies the following computational bounds on $f$. 1. If the strategies are arbitrary quantum channels, then $f\in \mathrm{QSZK}(\mathrm{poly}(T))$, where $\mathrm{QSZK}(T)$ is the class of languages having quantum statistical zero-knowledge proofs in which the verifier runs in time $T$ and the simulator in time $\mathrm{poly}(T)$. 2. If the strategies are Clifford+T circuits using at most $t$ magic gates, then $f\in \mathrm{DTIME}(\mathrm{poly}(T2^t))$. 3. If the strategies are explicit Pauli-sparse unitaries acting on at most $T$ qubits and having at most $s$ nonzero Pauli coefficients, then $f\in \mathrm{DTIME}(\mathrm{poly}(Ts))$. Time and space hierarchies then yield explicit functions secure against superlinear and even all polynomial-time adversaries under our computational restrictions. These bounds exceed the bounded-storage qubit bound $q\leq\log n$ of Bluhm, Christandl, and Speelman (Nature Physics, 2022) for the inner product function $f=\mathrm{IP}$, at the cost of restricting adversarial computation and increasing honest evaluation complexity.

quant-ph · cs.CC

版本更新 · v3arXiv:2610.20840

A Phenomenology of Neural Geometry in Vision-Language-Action Models

Mozes Jacobs, Aiden Swann, Mathilde Papillon, Siddharth Boppana, Fenil R. Doshi, Usha Bhalla, Thomas Icard, Matt Feiszli 等 19 位作者

原文摘要

Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes that task-relevant variables are linearly readable from activations, yet readability certifies only that a variable is present and says nothing about the shape its values trace, which may be curved and multi-dimensional. Using controlled sweeps, natural rollouts, linear probes, and activation interventions, we build a taxonomy of seven task-relevant concepts in VLA models. We find that realized geometry is predominantly multi-dimensional and is shaped by the constraints under which the policy acts. Physical joint limits, for example, leave wrist orientation an open arc rather than a circle, and distance to the target, a single scalar, is realized in two orthogonal subspaces, a coarse ruler for the approach and a fine ruler for the grasp. The same geometries reappear in two further VLA models on real-world robot data, indicating that they are neither model-specific nor artifacts of simulation. We demonstrate how the findings are actionable by steering along the geometry a concept realizes. Overall, this work lays out an initial phenomenology of realized geometry in VLA policies and demonstrates that a concept's shape carries as much importance as its readability.

cs.RO · cs.LG

版本更新 · v2arXiv:2601.07342

From Structured Graphs to Unstructured Evidence: Agentic Root Cause Analysis on Digital Twins

Nicolas Tacheny

原文摘要

Root cause analysis over telecom and datacenter infrastructures is commonly addressed by methods that consume structured data, from graph traversal and rule-based correlation to probabilistic and learned models. Yet a digital twin of such an infrastructure cannot model everything at a reasonable cost. Operators therefore record much of what changes as unstructured data attached to the graph, where the discriminating evidence often sits. Methods restricted to structured attributes cannot use it. A diagnosis needs a layer that interprets this data. An agentic layer is a natural candidate, since which fragment matters depends on hypotheses that emerge during the investigation. We demonstrate its feasibility with ReAct, the most widely used agentic architecture. A single LLM interprets the descriptions and explores the graph through a typed tool interface exposed via the Model Context Protocol (MCP). On a benchmark of nine synthetic scenarios covering single-node, multi-node and distractor-heavy evidence (360 runs across four LLMs), a frontier-tier model names the root cause and its type on every run. It reaches 96.7% end-to-end diagnostic accuracy, which also requires the exact supporting evidence. A mid-tier model reaches 86.7%. Accuracy drops for every model when the evidence must be combined across several resources.

cs.AI

版本更新 · v2arXiv:2606.14348

Detecting Historical Turning Points in Italian Media: A Complex Systems Approach to a Diachronic News Corpus

Dario Zarcone, Salvatore Miccichè, David Sanchez

原文摘要

Introduction: The increasing availability of large-scale textual corpora has opened new possibilities for data-driven, quantitative approaches to historical analysis using Natural Language Processing (NLP). However, diachronic corpora with historical relevance from the pre-digital era remain scarce and often incomplete. Methods: We present a quantitative approach to historical analysis based on the reconstruction and exploration of a diachronic corpus of around 600,000 articles from the Italian newspaper "La Repubblica", covering all the articles published from the first of January 1985 to the 31st of December 2000 - a period of major political, social, and geopolitical change in Italy and globally. Using NLP techniques, we analyze the text at both lexical and semantic levels; we then apply tools from complex systems and statistical physics to trace shifts in media discourse over time. Results: The word usage in the corpus is bursty, with a heavy-tailed distribution of Fano factors that is robust across timescales. Changepoints in word salience and the block structure of semantic similarity allow us to detect key transition periods, such as the transition from the First Republic to the Second Republic in Italy, or major international conflicts like the Gulf War or the Kosovo War, without relying on prior labeling. Periods of war correspond to lower entropy in the semantic space, indicating a more focused discourse. Discussion: The results show how combining computational linguistics with ideas from complex systems can offer new quantitative insight into historical changes, opening up new paths for studying the dynamics of media and society through large-scale textual data.

physics.soc-ph · cond-mat.stat-mech · cs.CL

版本更新 · v4arXiv:2510.12405

Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystals

Masahiro Negishi, Hyunsoo Park, Kinga O. Mastej, Aron Walsh

原文摘要

To address pressing scientific challenges such as climate change, increasingly sophisticated generative models are being developed to efficiently sample the large chemical space of potential functional materials. The proliferation of these models has necessitated the establishment of rigorous evaluation metrics. While uniqueness (U), novelty (N), and stability (S) of samples serve as standard metrics, their current formulations show several limitations. U and N rely on binary comparisons of crystals, rendering them dependent on heuristic thresholds, incapable of quantifying the degree of similarity, sensitive to atomic coordinate perturbations, and not invariant to sample permutation. Similarly, the binary assessment of S risks a premature exclusion of marginally unstable yet potentially novel candidates. These limitations are addressed by making the aforementioned metrics continuous. Furthermore, we integrate them into a unified metric ``continuous SUN" (cSUN), which offers a smoother score distribution and greater tunability than the conventional binary SUN metric. Experimental results demonstrate that our continuous metrics provide granular insights into sample distributions and secondarily serve as a soft screening score for selecting samples for further analysis. Finally, the use of cSUN as a reward signal in reinforcement learning is explored, showing that its adjustable weighting scheme effectively enhances sample diversity and convergence to a better optima in a Chemeleon2 case study.

cs.LG · cond-mat.mtrl-sci