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

+672新增论文
+517其中 AI 相关
+80已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 10:45 — 2026-11-17 10:45(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

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

24,106 已收录论文20,158 AI 相关7,049 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 17,909 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v3arXiv:2610.40625

Constant-Factor Approximation for Capacitated Clustering in Low Dimension with $(1+ε)k$ Centers

Kangke Cheng, Guanlin Mo, Hu Ding

原文摘要

In many applications of $k$-median and $k$-means, including load balancing and redistricting, each center can serve only a bounded number of clients. This leads to capacitated clustering, in which a client may be forced to use a distant center because all nearby ones are full. This loss of locality defeats the techniques behind approximation schemes, and no constant-factor approximation is known in general metrics even for capacitated $k$-median. A long line of work therefore opens $K=k+\lfloorεk\rfloor$ centers for a fixed $ε\in(0,1]$, while respecting the capacities exactly. We give a deterministic polynomial-time algorithm for uniform soft capacities in low dimension, that is, when the clients or the center locations have bounded doubling dimension. With $K$ centers, its ratio is $3-2ε$ for $k$-median and $9-8ε$ for $k$-means, or $5-4ε$ in $\mathbb{R}^d$. Apart from $k$-median in the plane, these are the first polynomial-time ratios bounded by a constant independent of $ε$; previously, the best ratio was $O(ε^{-2}\log(1/ε))$, even for $k$-median. We also obtain ratios that stay bounded as $ε\to0$ for non-uniform and hard capacities in low dimension, and ratios polylogarithmic in $1/ε$ in general metrics. Our approach starts from a simple structural observation: a near-optimal uncapacitated solution can be split into fewer than $2k$ capacity-respecting blocks, so $2k$ centers already suffice, one per block. Our main tool, the rescue lemma, shows that once every block that sends clients to a center of the optimal solution is rescued (given a private center), that center can be closed, so each extra center effectively rescues about two blocks. This lets $\lfloorεk\rfloor$ extra centers rescue nearly an $ε$-fraction of the blocks, yielding the linear dependence on $ε$ in our ratios.

cs.CG · cs.DS

新论文 · v1arXiv:2611.04834

Feeling of Knowing in Large Language Models

Zichuan Fu, Xian Wu, Jingtong Gao, Wenlin Zhang, Jiaxuan Li, Binhao Wang, Yimin Deng, Guojing Li 等 12 位作者

原文摘要

Post-training updates change what large language models (LLMs) can answer, but may leave their answerability judgments misaligned. We study this knowledge-judgment desynchronization through functional feeling of knowing (FoK), which supports selective generation, retrieval triggering, and model routing without implying subjective experience. We propose two trainable channels: a knowledge channel that changes answerability and a FoK channel that judges the current knowledge state. Three stages train them: on-policy supervised fine-tuning (OP-SFT) updates knowledge from corrected on-policy answers; knowledge-delta FoK training (K$Δ$-FT) adapts judgments across intermediate knowledge states; and FoK-guided policy optimization (FGPO) trains the subsequent answer or explanation. Factual-QA experiments, cross-dataset evaluation, and three sequential updates show that explicit FoK alignment improves judgment quality on updated knowledge. MMLU and ARC-Easy separately assess capability preservation.

cs.AI · cs.CL · cs.LG

版本更新 · v3arXiv:2610.05066

Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models

Shengyin Sun, Yiming Li, Yingzhao Lian, Xing Li, Xingzhi Zhou, Anxin Tian, Zhili Wang, Haoyang Li 等 10 位作者

原文摘要

Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation behavior. This motivates a complementary route beyond style-specific adaptation: drawing on the visual knowledge already encoded in step-distilled T2I models to elicit stylistic capabilities through language. Pursuing this direction requires textual guidance that captures how visual attributes jointly define a style and remain applicable as the depicted content changes. To explore this approach, we introduce StyleForge, a fully automatic, training-free framework that expresses reference styles as reusable rendering instructions. By integrating overall rendering characteristics with local color and lighting behavior, StyleForge organizes visual evidence from reference images into a coherent specification of how the target style should be expressed. The specification is then compiled into textual guidance that can be reused across content prompts, enabling frozen step-distilled T2I models to render different subjects and scenes in the reference style while retaining native few-step generation. Extensive experiments show relative gains of up to 29.47\% in generation quality scores over the strongest baseline, while Pareto analysis indicates that improved stylization is accompanied by strong adherence to the requested content. Code is available at https://github.com/sunshy-1/StyleForge.

cs.CV

版本更新 · v2arXiv:2610.06959

Nearly optimal Personalized PageRank computation

Rong-Hua Li, Quanqing Xu, Yichun Yang, Junjie Zhou

原文摘要

We study the fundamental problem of computing Personalized PageRank (PPR) on an undirected and unweighted graph $G$. We focus on the $\eps$-error guarantee introduced by Andersen, Chung, and Lang [ACL; FOCS 2006 $\&$ Internet Math 2007]. Their classic local push method computes an approximate PPR vector satisfying the ACL $\eps$-error guarantee in $O((α\eps)^{-1})$ time, where $α$ is the teleportation parameter. This problem has a lower bound $Ω(\eps^{-1})$. Working with idealized SDDM solves, we eliminate the dependence on $α$ and present an algorithm that achieves the same error guarantee in $O(\eps^{-1-o(1)})$ time. Consequently, we obtain a nearly optimal algorithm for PPR computation under the ACL error guarantee, and a nearly linear algorithm for local graph clustering with complexity independent of $φ$.

cs.DS · cs.CC

版本更新 · v2arXiv:2607.28610

Learning Arbitrary Lindbladians from Time Evolution

Zhili Chen, Zhan Yu

原文摘要

We study the problem of learning arbitrary $n$-qubit Lindbladians, the generators of Markovian open-system dynamics, from their time evolution. We give the first known efficient algorithm that learns arbitrary Lindbladians without any structural assumptions. For an $n$-qubit Lindbladian of dynamical strength at most $Λ$, the algorithm estimates every coefficient to error $\varepsilon$ using $\widetilde O(Λ^2/\varepsilon^2)$ experiments and $\widetilde O(Λ/\varepsilon^2)$ total evolution time, with classical running time polynomial in $n$ and $Λ/\varepsilon$. Both experimental costs match known lower bounds up to polylogarithmic factors. The algorithm identifies candidate labels through product Pauli experiments and estimates their coefficients using random stabilizer preparations and Clifford measurements. It requires no ancillas or control during the unknown evolution. For constant $k$, our algorithm learns generic $k$-local Lindbladians of local dynamical strength at most $Λ_{\mathrm{loc}}$ using $\widetilde O(n^2Λ_{\mathrm{loc}}^2/\varepsilon^2)$ experiments and $\widetilde O(nΛ_{\mathrm{loc}}/\varepsilon^2)$ total evolution time, improving the upper bounds of prior works in terms of the dependence on $n$. We further improve the lower bounds of Arad, Chen, Guo, Rebentrost, and Yu (SODA 2027) using a family of $3$-local Lindbladians. They already hold when the support is known, and only one Hamiltonian coefficient is requested, even for adaptive protocols with arbitrary ancillas and quantum memory. These lower bounds establish that our algorithm is optimal up to polylogarithmic factors in both experiment count and total evolution time for every fixed $k \geq 3$.

quant-ph · cs.DS

版本更新 · v4arXiv:2609.09940

NVV-Locator: From Transcript Tags to Acoustic Boundaries for Fine-Grained Nonverbal Vocalization Grounding

Yuang Cao, Bingshen Mu, Zhennan Lin, Guojian Li, Haoyue Zhan, Jie Liu, Chuan Xie, Qiang Zhang 等 10 位作者

原文摘要

Human speech includes nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, which convey affective and interactional information. Existing approaches typically represent NVVs as transcript-level tags, providing limited supervision for their waveform-time boundaries. We present NVV-Locator for fine-grained NVV temporal grounding. We first unify 26 NVV categories across public resources and construct large-scale timestamp-supervised training data through dual-LLM verification, transcript-guided forced alignment, and energy-based boundary refinement. We further introduce NVV-TimeBench, an expert-refined benchmark with 667 utterances and 1,094 events. NVV-Locator uses a non-autoregressive slot-filling architecture to jointly predict lexical timestamps, NVV categories, and event boundaries. On NVV-TimeBench, it achieves 71.0% Micro F1, 70.2% Macro F1, 80.4% Macro mIoU, and 59.6 ms Macro mMAE, outperforming the evaluated large audio model counterparts. Evaluation on an external corpus further demonstrates the cross-corpus generalization of NVV-Locator.

eess.AS · cs.SD

版本更新 · v2arXiv:2611.03393

TaoMate-FVSR: Audio-Guided Facial Video Restoration

Xinyang Li, Zeran Xu, Jingna Sun, Qijun Gan, Chenwei Zhang, Meiguang Jin, Junfeng Ma

原文摘要

Low-quality facial videos suffer from missing fine details, while AI-generated videos may additionally contain implausible teeth and lip movements that do not match the speech. Restoring the mouth region is particularly challenging: enhancing existing details can preserve structural errors, whereas regenerating them risks changing facial identity and articulation. We propose an audio-guided facial video restoration framework that reconstructs unreliable mouth details and aligns lip movements with the speech while preserving facial identity and temporal consistency. Built on a video diffusion transformer, our framework mixes input video latents with noise to retain useful source information while allowing corrupted details to be regenerated. Audio guides lip movements, reference images constrain facial appearance, and previously generated frames promote temporal consistency. We train the model in two stages, first learning visual restoration from degraded images and videos, then learning audio-guided lip correction from degraded dubbed videos. The resulting model supports both restoration with the original audio and visual dubbing with replacement audio. On talking-head restoration benchmarks, our method achieves the lowest LPIPS and DISTS and the best lip synchronization scores among the evaluated restoration baselines. Qualitative results on AI-generated videos further show improvements in facial detail and mouth-region appearance, including clearer tooth boundaries and lip contours.

cs.CV

版本更新 · v5arXiv:2508.21380

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek

原文摘要

Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents. But does algorithmic structure guarantee algorithmic behavior? We investigate this in Leela Chess Zero, the strongest neural chess engine, where prior work identified learned look-ahead. By extending the logit lens to its move-selecting policy network, we discover that correct puzzle solutions--including immediate checkmates--often appear in intermediate layers but are systematically overridden in the final output, a phenomenon we term "forgotten puzzles". Replicating prior analyses on these positions, we find that look-ahead operates normally--future moves of the correct continuation are represented, causally important, and linearly decodable--ruling out a failure of the algorithm. Instead, late layers increasingly shift toward safe play over aggression. To test whether this shift drives the override, we steer the model against these preferences and recover 71.7% of forgotten puzzles, providing causal evidence that safety priors override algorithmically computed solutions. These findings show that algorithmic structure does not guarantee algorithmic behavior: a model can internally solve a problem and still output the wrong answer.

cs.LG · cs.AI

版本更新 · v4arXiv:2601.21929

LoRIF: Pushing the Scalability Frontier of Training Data Attribution

Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann

原文摘要

Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA methods and exploit gradients. To overcome the scalability challenge arising from gradient computation, the most popular strategy is random projection (e.g., TRAK, LoGRA). However, this still faces two bottlenecks when scaling to large training sets and high-quality attribution: \emph{(i)} storing and loading projected per-example gradients for all $N$ training examples, where query latency is dominated by I/O; and \emph{(ii)} forming the $D \times D$ inverse Hessian approximation, which costs $O(D^2)$ memory. Both bottlenecks scale with the projection dimension $D$, yet increasing $D$ is necessary for attribution quality -- creating a quality--scalability tradeoff. We introduce \textbf{LoRIF} (\textbf{Lo}w-\textbf{R}ank \textbf{I}nfluence \textbf{F}unctions), which exploits low-rank structures of gradient to address both bottlenecks. First, we store rank-$c$ factors of projected per-example gradients rather than full matrices, reducing storage and query-time I/O from $O(D)$ to $O(c\sqrt{D})$ per layer per sample. Second, we use truncated SVD with the Woodbury identity to approximate the inverse Hessian term in an $r$-dimensional subspace, reducing memory from $O(D^2)$ to $O(Dr)$. On models from 0.1B to 70B parameters trained on datasets with millions of examples, LoRIF achieves up to 20$\times$ storage reduction and query-time speedup compared to LoGRA, while matching or exceeding its attribution quality. LoRIF makes gradient-based TDA practical at frontier scale. Code is available at https://github.com/doub7e/LoRIF.

cs.LG

新论文 · v1arXiv:2611.04826

Safe Portfolio Learning from Untrusted Predictions: Signed Trust, Abstention, and Cross-Universe Polarity Failure

Amirhossein MohammadpourAzari, Mohammad Zarei, MohammadAmin Fazli

原文摘要

Portfolio use of machine predictions must often proceed while the predictions' economic direction, reliability, and timing remain untrusted, and while feedback from overlapping multi-period positions arrives with delay. A controller chooses among Safe, Follow, and Reverse portfolio actions, so signal orientation is learned rather than assumed. A share-adaptive master updates action probabilities from matured Safe-relative rewards, an evidence gate can abstain by transferring unsupported directional probability to Safe, a delayed collateral budget reserves worst-case loss capacity before exposure is funded, and a protected split account caps the capital adaptive decisions may touch. The architecture carries a dual certificate, tracking regret against switching action sequences under delay and one-sided intervention, together with a pathwise collateral safety bound that holds when predictions fail. On a 24-stock development universe a conservative prediction-assisted overlay stays near equal-weight performance at a fraction of the turnover. On a frozen 82-stock holdout, the pre-specified Reverse orientation fails to outperform Equal Weight; a separately labeled post-holdout diagnostic shows that permanently flipping the sign to Follow also does not recover a return edge. Under the post-holdout controller, protected wealth remains within 15.9 basis points of the Safe benchmark throughout. The contribution is safe adaptive use of untrusted predictions, not demonstrated alpha.

q-fin.MF · cs.CE · q-fin.CP · q-fin.PM

版本更新 · v2arXiv:2601.20638

Supply Chain Insecurity: Exposing Vulnerabilities in iOS Dependency Management Systems

David Schmidt, Gabriel K. Gegenhuber, Edgar Weippl, Sebastian Schrittwieser

原文摘要

Dependency management systems are a critical component in software development, enabling the incorporation of existing functionality. However, misconfigurations and malicious actors in these systems pose security risks, leading to supply chain attacks. Despite the widespread use of smartphone apps, the security of dependency management systems in the iOS software supply chain has received limited attention. In this paper, we focus on CocoaPods, one of the most widely used dependency management systems for iOS app development, but also examine the security of Carthage and Swift Package Manager (SwiftPM). We demonstrate that iOS apps expose internal dependency names and versions. Attackers can exploit this information to register previously unclaimed dependencies in CocoaPods, enabling remote code execution (RCE) on developer machines and build servers. Additionally, we show that attackers can compromise dependencies by reclaiming abandoned domains and GitHub URLs. Analyzing 9,491 real-world iOS applications, we find that a significant fraction is vulnerable to these attacks, putting millions of users at risk, including applications from major organizations for which we confirmed exploitation via responsible disclosure. Finally, we compare iOS dependency management systems with Cargo, Go modules, npm, pip, and Maven, and discuss conceptual issues and practical mitigation strategies.

cs.CR

版本更新 · v2arXiv:2605.28048

SAFEVPR: Patch-Based Verification with Empirical FDR Control for Cross-Condition Sequence Visual Place Recognition

Ha Sier, Jiaqiang Zhang, Zhuo Zou, Xianjia Yu, Tomi Westerlund

原文摘要

Sequence-based visual place recognition (VPR) for loop closure and robot relocalization must decide whether the retrieved top-1 candidate should be accepted. Conformal calibration can set this accept/reject threshold, but its finite-sample guarantees require exchangeability between calibration and deployment, a requirement that cross-condition deployment violates. We therefore claim no formal guarantee under condition shift: this paper instead asks which verification score and calibration design keep a target false-discovery rate (FDR) empirically satisfied across realistic appearance change. We present SAFEVPR, a non-trainable pipeline that replaces the backbone cosine similarity with a mutual-nearest-neighbour (MNN) patch score from frozen DINOv2 features, and flat Learn-Then-Test (LTT) calibration with per-bin Clopper-Pearson thresholds. Across 23 cross-condition ground-vehicle setups (Oxford RobotCar, NCLT, St Lucia; three frozen backbones), SAFEVPR meets the FDR target on 23/23 setups at alpha = 0.10 (mean accepted FDR 0.014, mean TPR 0.75) and on 22/23 at alpha = 0.05 with 22 retaining non-trivial coverage (best cosine variant, cosine+LTT: 22/23 valid but 17 non-trivial); under leave-one-dataset-out calibration, validity drops to 20/23 with 14 retaining useful coverage (strongest cosine baseline: 16/23 and 10), and on texture-poor scenery (Nordland) the verifier is uninformative and the system abstains entirely, as it does everywhere at alpha = 0.01; we report these as limitations. In a pose-graph relocalization study, gating loop-closure constraints reduces erroneous constraints by 29.6x and cuts the median trajectory error from 95.5 m to 9.7 m. Code is available at https://github.com/TIERS/SafeVPR.

cs.RO

新论文 · v1arXiv:2611.04822

Radial distortion homography estimation from affine-covariant or orientation-covariant features

Marcus Valtonen Örnhag, Stefan Adalbjörnsson

原文摘要

We present minimal solvers for joint homography and radial distortion estimation using affine- or orientation-covariant features. The core contribution is a set of novel constraints that exploit local feature geometry inherent to affine descriptors, enabling solvers that require fewer correspondences than point-based methods. Using modern robust estimation frameworks, we demonstrate that the proposed solvers are advantageous to the current state-of-the-art with a significant speed-up in the presence of outliers while maintaining comparable or superior estimation accuracy. The proposed solvers are tested on both synthetic and real images containing challenging fisheye distortions.

cs.CV

版本更新 · v2arXiv:2605.18805

RecoAtlas: A Benchmark and RL Environment for LLM Recommendation Agents Optimizing Set-Level Utility

Imad Aouali, Flavian Vasile, Clijo Jose, Otmane Sakhi, Alexandre Gilotte, Benjamin Heymann

原文摘要

LLM recommender agents increasingly produce structured reports: sets of items accompanied by natural-language justifications. Yet existing benchmarks often focus on reranking small candidate sets or judging reports primarily by semantic plausibility, providing limited support for evaluating and training agents based on set-level utility. We introduce Recommender Atlas (Agentic Tasks for Learning and Assessment in Shopping), or RecoAtlas, a benchmark and reinforcement learning environment grounded in user behavior. RecoAtlas provides a shopping toolkit for product retrieval, complementarity, and diversity. Given a shopping query, an agent uses these tools to generate a structured recommendation report. Behavioral reference sets support exact-recovery evaluation and the training of a learned bundle-level reward that supplies feedback for policy optimization with RL. Its controlled tool environment exposes agents to semantic and behavior-aligned tools, enabling systematic analysis of how LLM reasoning, tool signals, and tool-use policies contribute to performance. Across controlled experiments, performance scales with model capacity and test-time compute, and improves with stronger tools, while semantic plausibility does not necessarily translate into behavior-grounded utility. RecoAtlas provides a foundation for training and evaluating shopping assistants to move beyond semantic plausibility toward coherent, behaviorally grounded recommendation sets.

cs.IR · cs.AI · cs.LG

版本更新 · v2arXiv:2604.11656

Scalable Exact Hierarchical Agglomerative Clustering via Sparse Geographic Distance Graphs

Victor Maus, Vinicius Pozzobon Borin

原文摘要

Exact hierarchical agglomerative clustering (HAC) of large spatial datasets is limited in practice by the $\mathcal{O}(n^2)$ time and memory required for the full pairwise distance matrix. We present GSHAC (Geographically Sparse Hierarchical Agglomerative Clustering), a system that makes exact HAC feasible at scales of millions of geographic features on a commodity workstation. GSHAC replaces the distance matrix with a sparse geographic distance graph containing only pairs within a user-specified geodesic bound $h_{\max}$, constructed in $\mathcal{O}(n \cdot k)$ time via spatial indexing, where $k$ is the mean number of neighbors within $h_{\max}$. Connected components of this graph define independent subproblems, and we prove that the resulting assignments are exact for all standard linkage methods at any cut height $h \le h_{\max}$. For single linkage, an MST-based path keeps memory at $\mathcal{O}(n_k + m_k)$ per component. Applied to a global mining inventory ($n = 261{,}073$), the system completes in 12 s (109 MiB peak HAC memory) versus $\approx 545$ GiB for the dense baseline. On a 2-million-point GeoNames sample, all tested thresholds completed in under 3 minutes with peak memory under 3 GiB. We provide a scikit-learn-compatible implementation for direct integration into GIS workflows.

cs.DS · cs.CG

版本更新 · v2arXiv:2611.01517

VLMs Read Aloud: The Gap Between Recognizing and Using Visual Text

Zhiyun Shi

原文摘要

Visual-text compression renders long contexts as images and is engineered around how much of the text a vision-language model (VLM) can recover. Yet recovered text is not usable text. VLMs can transcribe the text in an image word for word and still fail to answer from it; given back their own transcript, they answer nearly as well as from the original text. We call this difference the read-use gap. Recognizing and using visual text have different resolution requirements: Qwen3-VL-8B's recognition saturates at 15-pixel characters while use catches up only at 24 pixels, and scaling from 2B to 32B raises recognition without narrowing the gap. Putting the evidence into words closes it: thinking VLMs recite the evidence in their thinking, and their own transcript, written without seeing the question, recovers most of what thinking adds. In a preregistered held-out test, the gap ranks how much eight VLMs gain from their own words over pixels (Spearman $ρ$ = 0.86), which recognition rates do not. We propose ALOUD, which spends visual resolution on finding and recognizing evidence and language tokens on using it. Without keeping the source text, it doubles the accuracy of a frozen Qwen3-VL-8B on long documents compressed 5x and 10x: at 5x, from 27.7% to 54.8%, near the original text's 58.5%, with a context smaller than the compressed pages themselves. For less than the cost of reading the original text, it leads at equal budget every method that does without it, at every level, and beats AGAR and VERA, which paste the original text back; at 5x it also beats LensVLM-9B, which is trained and keeps the original text. Visual-text compression is limited not by how much text a model can recover, but by how much it can use.

cs.CV · cs.CL

新论文 · v1arXiv:2611.04820

AI for eGovernance: Leveraging Language Technologies For Digital Inclusion

Cynthia Jayne Amol, Lilian Wanzare

原文摘要

The Kenyan government has invested heavily in the digitisation of public service delivery, in line with the Kenya Digital Master Plan 2022-2032. The national eGovernment platform, eCitizen, hosts services that are vital to citizens' livelihoods, including business registration, youth enterprise lending, digital literacy and tax filing. However, the platform faces digital inclusion challenges that limit equitable access for marginalised groups, particularly youth in rural areas and persons with disabilities. This exclusion is driven by a language barrier, since the platform is primarily in English with limited Swahili support, and by a text-only interface that excludes low-literacy and visually impaired users. This paper reports findings from six one-on-one interviews and an eleven-person roundtable discussion across four platforms essential to youth livelihoods: Ajira Digital, Kenya Revenue Authority (KRA) iTax, Higher Education Loans Board (HELB) and the Youth Enterprise Development Fund (YEDF). Drawing on these findings, on Web Content Accessibility Guidelines (WCAG) 2.1 principles as a design lens for diagnosing eCitizen's accessibility gaps, and on comparator models such as Estonia's Bürokratt and India's Bhashini, the paper proposes a human-centred, systems-minded framework for embedding generative AI and language technologies into eCitizen, including text simplification, neural machine translation, text-to-speech and speech-to-text. The paper argues that, when deployed responsibly with appropriate human oversight, these interventions could meaningfully improve access to government services for linguistically excluded citizens. It also emphasises that AI alone cannot overcome the broader structural barriers, including unemployment and educational inequality, that shape digital exclusion.

cs.HC

新论文 · v1arXiv:2611.04819

Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning

Huilin He, Weiyu Han, Linbo Shao, Ruobing Zuo, Xiao Tan, Shuai Chen, Dawei Cheng

原文摘要

Payment fraud causes financial losses and undermines users' trust in web payment services. Although fraud detection is a critical defense for payment security, complex and diverse fraudulent behaviors can still evade detection. Generating fraud samples for data augmentation can broaden detectors' coverage of different fraud patterns. However, existing methods matching the distribution of transaction attributes alone do not ensure that generated sequences preserve the sequential relationships among transaction choices, payment feedback, and subsequent behavioral adjustments. To this end, we propose PaySeqGen, an interpretable inverse reinforcement learning framework that reconstructs fraud behavior policies from fraudsters' observed payment trajectories. We design a mechanism for constructing candidate actions to support plausible payment sequence generation while enabling exploration. The framework also learns interpretable behavioral rewards that capture fraudsters' preferences across different transaction contexts. By alternating between reward learning and policy optimization, the framework reconstructs policies that generate new fraud sequences for detector augmentation and learns interpretable rewards supporting sequential fraud-pattern analysis in real trajectories. Experiments in real-world payment scenarios at Ant International, a leading global digital payment provider, show that PaySeqGen outperforms state-of-the-art generative augmentation methods. Reward-based trajectory analysis also identifies fraud patterns of practical value, helping analyst locating suspicious segments and examine multistep fraud tactics. Evaluation in the deployed system of online payment further confirms its effectiveness.

cs.AI

版本更新 · v3arXiv:2609.22377

Forecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression and Flow Matching

Qinghui Liu, Jon André Ottesen, Thu Nguyen, Geir Ringstad, Ingrid Mossige, Siri Fløgstad Svensson, Sissel Riis Kalstad, Atle Bjørnerud 等 10 位作者

原文摘要

The brain fluid clearance system can be studied with intrathecal contrast-enhanced magnetic resonance imaging (MRI). By injecting a tracer into the spinal canal and performing MRI over 24--48\,h, one can measure how a tracer injected into the cerebrospinal fluid spreads through the brain. As this is an invasive procedure requiring several MRI scans, we ask how much of the later tracer distribution can be predicted from the pre-contrast scan and elapsed time alone. Using 104 training patients (878 MRI volumes), we compared a direct image-to-image regression model with a more complex generative model based on conditional flow matching, and tested both on 23 held-out patients and on 51 patients from a separate cohort with idiopathic normal pressure hydrocephalus (iNPH). Relative to simply copying the pre-contrast scan, the direct model reduced the mean absolute error (intensities normalized to $[0,1]$) from 0.089 to 0.036, about 60\%, in held-out patients and from 0.075 to 0.056, about 25\%, in the iNPH cohort. The reduction held in every sampled elapsed-time interval and brain compartment, and errors remained largest at 20--30\,h and in the ventricles, where enhancement is strongest. Its predicted change maps agreed with the observed tracer enhancement rather than only reproducing anatomy. The generative model was less accurate in both cohorts. A substantial part of the later tracer distribution is therefore predictable from the patient's brain anatomy as seen on pre-contrast MRI, and the added model complexity gave no benefit at this data scale. Whether this accuracy suffices for a given clinical use remains to be established; with prospective validation, such forecasts could help simplify the MRI protocol used to assess brain clearance.

eess.IV · cs.AI · cs.CV · cs.LG

版本更新 · v2arXiv:2611.00769

DramaVQA: Probing Detailed Understanding of Ultra-Long TV Dramas

Xinyue Huo, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Jiacheng Shao, Yunning Cao, Lingxi Xie, Qi Tian

原文摘要

Despite recent progress in long-form video understanding, current benchmarks mostly focus on short clips or hour-scale videos. This leaves a major gap in evaluating ultra-long video understanding, where videos often last tens of hours. To bridge this gap, we introduce DramaVQA, a large-scale benchmark built upon long-form TV dramas. Containing approximately 20K question-answering (QA) pairs, the scale of DramaVQA exceeds previous long-video datasets, such as Video-MME and LVBench, by an order of magnitude. Our benchmark has two main features that make it stand out from existing datasets. First, we establish a scalable, LLM-assisted annotation pipeline that uses multimodal large language models (MLLMs) to generate complex questions, followed by strict human checking to ensure high data quality. Second, DramaVQA introduces a multi-level time structure; queries are designed across different video lengths, with the hardest questions requiring overall understanding across the entire drama. Extensive evaluations show that state-of-the-art MLLMs face major challenges when tested on these very long videos, highlighting the need for agentic AI algorithms capable of managing long-term memory. The project is available at https://github.com/xinyuehuo/DramaVQA

cs.CV

版本更新 · v2arXiv:2610.34373

Tight Coreset Bounds for $(k,z)$-Clustering in Euclidean and Doubling Metrics

Junqiu Hu, Lingxiao Huang, Jian Li, Baoduo Xu

原文摘要

We determine the optimal worst-case size of strong coresets for $(k,z)$-clustering in Euclidean spaces and doubling metrics, up to polylogarithmic factors. In Euclidean space, previous lower bounds matched the best upper bounds only for $\varepsilon\gtrsim k^{-1/(z+2)}$. We close the gap for arbitrarily small $\varepsilon$, establishing the optimal size $\widetildeΘ(\min\{k^{(2z+2)/(z+2)}\varepsilon^{-2},\,k\varepsilon^{-z-2}\})$ for every fixed $z\ge1$, all $k\ge1$, and $0<\varepsilon<1$. Our lower bound replaces each offset in a previous hard instance by a group of distinct offsets. A fixed family of $k$-center queries and four-wise independent signs force a large relative cost error for every sufficiently small subset with arbitrary nonnegative weights. For doubling metrics of dimension $D$, we resolve the previously unmatched bounds for $z>2$. We prove an upper bound of $\widetilde O(k^{2-2/z}D\varepsilon^{-2})$ and a lower bound that, together with known upper bounds, establishes the optimal size $\widetildeΘ(kD\min\{k^{1-2/z}\varepsilon^{-2},\,\varepsilon^{-z}\})$ for fixed $z>2$, $0<\varepsilon\le\varepsilon_z$, and $D\ge C_z\log(2/\varepsilon)$, where $C_z>0$ and $\varepsilon_z\in(0,1)$ depend only on $z$. The lower bound exploits the ability to encode $Θ(D)$ independent signs per center without diluting relative cost discrepancy. For the upper bound, we use independent, unbiased two-point summaries that exactly preserve cluster mass and anchor cost, combined with iterative size reduction.

cs.DS · cs.CG

版本更新 · v2arXiv:2604.07233

How Does Machine Learning Manage Complexity?

Lance Fortnow

原文摘要

We provide a computational complexity lens to understand the power of machine learning models, particularly their ability to model complex systems. Machine learning models are often trained on data drawn from sampleable or more complex distributions, a far wider range of distributions than just computable ones. By focusing on computable distributions, machine learning models can better manage complexity via probability. We abstract away from specific learning mechanisms, modeling machine learning as producing P/poly-computable distributions with polynomially-bounded max-entropy. We illustrate how learning computable distributions models complexity by showing that if a machine learning model produces a distribution $μ$ that models the distribution generated by a cryptographic pseudorandom generator at least as well as the uniform distribution does, then $μ$ must be close to uniform. We view training as compression that removes the randomness from the data, keeping only its structure, and inference as adding randomness back to generate new outputs. A computationally bounded model cannot distinguish pseudorandomness from true randomness, so training removes both, treating anything it cannot efficiently predict as noise. The same holds at inference, where the randomness added back can be, and in practice is, pseudorandom. In the appendix, we make the connection to compression precise and, using a characterization of pseudoentropy by Vadhan and Zheng, show that the best loss achievable by an efficient model is the next-bit pseudoentropy of the data.

cs.LG · cs.CC

新论文 · v1arXiv:2611.04811

NightIQA: A Comprehensive Dataset and Benchmark for MLLM-Based Nighttime Image Quality Assessment

Yiding Tian, Jiaojiao Yi, Jiayuan Lu, Pufan Xu, Jinlin Wu, Changyuan Wen, Hongyuan Yu

原文摘要

Nighttime images are inherently susceptible to complex, compound degradations, making accurate quality assessment exceptionally challenging. Score-based IQA methods condense quality into a single number, lacking the multi-dimensional, language-grounded reasoning required for nighttime evaluation. Multimodal Large Language Models (MLLMs) offer a more comprehensive alternative, yet remain constrained by a critical data gap: existing real-world IQA datasets are overwhelmingly daytime-centric and often built from outdated captures, while synthetic alternatives lack nighttime-specific degradation modeling, yielding artifacts far removed from authentic nighttime conditions. To bridge this gap, we present NightIQA, a dataset and benchmark suite purpose-built for MLLM-based nighttime IQA. It comprises three core components: NightIQA-Real, a real-world dataset of 1,769 high-resolution images that we captured ourselves with modern equipment, encompassing six canonical distortion types and structured multi-dimensional annotations; NightIQA-Bench, a benchmark of 1,078 visually grounded multiple-choice questions tailored to MLLM-based nighttime IQA, organized around a four-level evaluation hierarchy spanning Perception, Technical Assessment, Localization, and Reasoning; and NightIQA-Syn, an inherently scalable, scene-aware synthesis pipeline that jointly models global-level and instance-level degradations, with an initial release of 80k high-fidelity images alongside the full generation code. Fine-tuned on NightIQA with Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), Qwen3-VL-8B outperforms open-source IQA methods and achieves higher overall accuracy than leading closed-source models, highlighting the value of domain-specific data and structured supervision.

cs.CV

新论文 · v1arXiv:2611.04807

Asymptotic Optimality of $cμ$-Rule for LLM Inference Scheduling under Memory Constraint

Zhenghao Li, Shengbo Wang, Nian Si

原文摘要

Large language model (LLM) inference, the process by which a pre-trained model receives an input prompt and generates output tokens sequentially, has become increasingly important with the widespread deployment of LLM-based applications. As inference workloads continue to scale, GPU memory has emerged as a critical bottleneck: the long input prompts and generation sequences common in agentic and reasoning workloads lead to substantial key-value (KV) cache usage. In this paper, we study the resulting online scheduling problem from a queueing perspective. Requests arrive stochastically with heterogeneous prompt and output lengths, undergo prefill and autoregressive decode, and compete for a finite KV-cache capacity. Unlike classical queueing models, the duration of a processing step depends on both prefill computation and KV-cache I/O, so service capacity is jointly determined by computation, memory access, and memory occupancy. We develop a fluid model that reduces the system to a multiclass single-server queue with effective service rates capturing computation, memory access, and memory capacity. This fluid analysis yields a $cμ$ priority rule, where the effective service rate $μ$ is jointly determined by computational speed, memory bandwidth, and memory capacity. We prove that this rule minimizes cumulative holding cost in the fluid model and, for a finite workload, also minimizes completion time and maximizes full-run output-token throughput. We then construct a feasible scheduling policy for the original finite system and prove that its scaled dynamics converge to the optimal fluid policy. Finally, experiments on a real LLM serving engine using an NVIDIA H800 show that practical implementations of the proposed priority rule substantially reduce average latency while maintaining high throughput relative to existing scheduling policies.

math.OC · cs.AI

新论文 · v1arXiv:2611.04806

On the Complexity of Finite-Sum Nonconvex-Strongly-Concave Minimax Optimization with Exact Proximal Oracles

Yuxing Peng, Zhiqing Tang, Weijia Jia

原文摘要

Finite-sum nonconvex-strongly-concave minimax problems arise in adversarial training and distributionally robust learning. Their known lower bounds cover only linear-span algorithms, zero-respecting algorithms, or a restricted proximal protocol. They leave open the power of exact component proximal steps, whose responses are global saddle points of regularized component problems and can expose directions that gradients do not reveal. We show that neither unrestricted adaptivity nor exact proximal access improves the polynomial complexity. We consider $n$ components with joint mean-squared smoothness $L$ and condition number $κ$, started from a point with primal gap at most $Δ$ and joint gradient norm at most $\sqrt{2LΔ}$. For $\varepsilon^2/(LΔ)$ below a universal constant, every randomized adaptive algorithm with exact component values, gradients, and proximal responses needs $Ω(n+\min\{\sqrt n\,κ,n^{3/4}\sqrtκ\}LΔ/\varepsilon^2)$ component queries in the worst case to find an $\varepsilon$-stationary point of the value function. A method using only component gradients attains this rate up to a factor $\log^2(2+κ)$, including initialization. Zhou (arXiv:2610.04944) concurrently proves the same rate for zero-respecting first-order methods. In our hard instances, every component admits proximal steps with the same step sizes, and a response for a component reveals hidden directions only up to the first one assigned to another component.

cs.LG

版本更新 · v3arXiv:2607.13284

Tight Bounds for $(1+ε)$-Approximation for Minimum Spanning Trees in Doubling Metrics

Jan Höckendorff, Felix Hommelsheim, Christian Sohler, Di Yue

原文摘要

The minimum spanning tree (MST) problem is one of the most basic optimization problems on metric spaces and graphs. We study the problem of computing a $(1+ε)$-approximation to the MST of an $n$-point metric space of doubling dimension $\mathrm{ddim}$. In doubling metrics, previous deterministic algorithms incur a running time with dependence $ε^{-O(\mathrm{ddim})}$. We give a deterministic algorithm that computes a $(1+ε)$-approximate MST in time $$ O_{\mathrm{ddim}}\left(n\log n+ \min\left\{n^2,\frac{n}ε\log(1/ε)\right\}\right) $$ in the standard real RAM model with a unit-cost exact-distance oracle. For bounded doubling dimension, this improves the previous dependence on $ε$ to essentially linear in $ε^{-1}$. We complement this algorithm with a lower bound of $$ Ω\!\left(n\log n+ \min\left\{n^2,\frac{n}ε\log(1/ε)\right\}\right) $$ on running time in the same model, already for metrics of doubling dimension at most seven, showing that our running time is essentially tight. For points in $\mathbb R^d$ with $d = O(1)$, exploiting Euclidean geometry allows us to further improve the dependence on $ε$. We obtain a $(1+ε)$-approximate MST in expected time $$ O_d\left( n \log n + \min\left\{n^2, \frac{n}{ε^{1 - β_d}} \log^{1-β_d}(1/ε) \right\} \right) $$ for some $β_d=Θ(1/d)$, improving the accuracy-dependent term $nε^{-2}\log^2(1/ε)$ of Arya and Mount [SODA'16].

cs.DS

版本更新 · v2arXiv:2606.31585

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

Shun Kenney, Teppei Suzuki

原文摘要

The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry. Recent advancements have established the practice of using camera parameters---such as extrinsics or projection matrices---as relative positional encoding into the query, key, and value vectors of the attention mechanism. However, when scaling up the training recipe of novel view synthesis (NVS) models with the camera-based positional encoding, we observe a significant issue: model performance stagnates in the late stages of training. In this paper, we investigate the cause of the performance bottleneck when scaling up and demonstrate that storing rotation and translation given by the positional encoding in the same dimensions of the value vector causes indeterminacy in their independent identification, hindering training scalability. To address this, we propose Decoupled Pose Positional Encoding (DPPE), a novel camera-based positional encoding that explicitly decouples rotation and translation. Extensive evaluations on NVS tasks demonstrate that DPPE enables stable long-term training even in scaled-up training setup. Furthermore, it exhibits superior generalization performance in extrapolation settings, such as handling an increased number of viewpoints and zoom-in scenarios. Code is available at https://github.com/sbintuitions/dppe.

cs.CV · cs.AI

版本更新 · v3arXiv:2610.40982

Strong Lower Bounds for Weak Epsilon-Nets

Sujoy Bhore, Reilly Browne, Da Wei Zheng

原文摘要

Let $P$ be a finite point set in $\mathbb{R}^d$. A weak $\varepsilon$-net for $P$ with respect to convex sets is a finite set $X\subset\mathbb{R}^d$ intersecting every convex set containing at least $\varepsilon|P|$ points of $P$. Determining their optimal worst-case size was described by Alon, Kalai, Matousek, and Meshulam [Adv. Appl. Math., 2002] as "one of the truly important open problems in combinatorial geometry." We give elementary constructions which establish the first polynomially superlinear lower bounds in fixed dimension. Already in $\mathbb{R}^3$, we construct point sets for which every weak $\varepsilon$-net has size $Ω(\varepsilon^{-3/2})$. More generally, for every fixed $d\ge3$, we obtain a lower bound of $Ω_d(\varepsilon^{-γ_d})$, where $γ_d=\sqrt{d/2}+O(1)$. Consequently, no upper bound of the form $O_d(\varepsilon^{-C})$ can hold with an absolute constant $C$ which is independent of the dimension. Despite the recent progress on upper bounds, the strongest previous general lower bound remained $Ω_d(\varepsilon^{-1}\log^{d-1}(1/\varepsilon))$, due to Bukh, Matousek, and Nivasch [Israel J. Math., 2011]. To obtain our results, we apply a quadratic lift to grid-based configurations with many point-line incidences. The bounds also yield polynomial separations between fractional and integral piercing numbers of convex families, and lower bounds for Hadwiger-Debrunner numbers.

cs.CG

版本更新 · v2arXiv:2605.03830

Identity-Consistent Multi-Pose Generation of Contactless Fingerprints

Zhiyu Pan, Zhaoliang Xu, Xiongjun Guan, Jianjiang Feng, Jie Zhou

原文摘要

Contactless fingerprint recognition has gained increasing attention due to its advantages in hygiene and acquisition flexibility. However, the absence of physical contact constraints introduces severe nonlinear geometric distortions caused by free finger poses in 3D space, resulting in a substantial cross-modal domain gap between contactless and conventional contact-based fingerprints. Existing solutions largely rely on explicit geometric correction or image enhancement, which are fragile under extreme pose variations. In this paper, we propose Identity-Consistent Multi-Pose Generation of Contactless Fingerprints (IMPOSE), a physics-inspired framework that synthesizes identity-preserving, multi-pose contactless fingerprint samples to empower recognition models. IMPOSE consists of three stages: (1) rolled fingerprint identity generation via latent diffusion with discrete codebook representations, (2) cross-modal translation from rolled to contactless modality guided by Sauvola-based local adaptive binarization as an identity anchor, and (3) physics-based multi-pose simulation through 3D finger model texture mapping and projection. The generated samples maintain strict identity consistency at the ridge topology level and spatial alignment with standard fingerprint coordinate space. Extensive experiments on the UWA and PolyU CL2CB databases demonstrate that fine-tuning fixed-length dense descriptors (FDD) with IMPOSE-synthesized data achieves state-of-the-art cross-modal matching, reducing EER to 8.74% on UWA and 2.26% on PolyU CL2CB. Synthetic data also yields consistent gains across mainstream representations including DeepPrint and AFRNet, and the hybrid strategy combining synthetic and real data achieves the best overall results. The code and generated samples are available at https://github.com/Yu-Yy/IMPOSE.

cs.CV

新论文 · v1arXiv:2611.04803

Extracting System Prompt of LLM Services in Complex (Agentic) Settings: Hierarchical Optimization and Reliable Evaluation Metrics

Shuaidong Li, Chenhao Lin, Xinshan Yang, Chao Shen, Yufei Chen, Zhengyu Zhao

原文摘要

System prompt is a critical intellectual property of large language model (LLM) services. To analyze its leakage, prompt extraction attacks have been extensively studied. However, we validate that existing attacks substantially degrade on recent LLM services, whose complexity has evolved in both the prompt itself and system-level constraints. Specifically, (1) system prompts become longer and more structured to contain pre-defined tool schemas, execution logic, safety guardrails, etc., and (2) only the final post-processed outputs (e.g., agent's actions) but not the raw textual response can be observed. In this paper, we address the above increased complexity by proposing Extraction with Hierarchical Optimization (ExtraHerO), which (1) decomposes the prompt extraction into a hierarchical reconstruction process with a pre-defined structural prompt template, and (2) iteratively updates the adversarial query with guidance of feedback-template differences to observe diverse outputs. In particular, we monitor the information gain of attack optimization to early stop or reset it for a good trade-off between effectiveness and efficiency. We also find that existing evaluation metrics for prompt fidelity can be misleading because they do not account for structural information. Therefore, we rely on global textual similarity and prioritize structural keywords. Moreover, we introduce a system-level metric, adversarial utility, to measure the help of prompt extraction for real-world downstream attacks. Experimental results demonstrate the consistent superiority of ExtraHerO, with average improvements of 12.5\% (fidelity), 2.3\% (functionality), and 6.0\% (adversarial utility) on chatbots, and 12.2\%, 34.3\%, and 30.5\% on agents.

cs.CR