跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-15 20:15 — 2026-11-16 20:15(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

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

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

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

浏览论文库

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

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.01259

Clique counts under degree and matching constraints

Rajat Adak

原文摘要

We study the maximum number of $t$-cliques in graphs with maximum degree at most $D$ and matching number at most $M$, with no restriction on the number of vertices. For $t\ge 3$, we determine this maximum whenever $D\ge 2M-1$ and characterize all extremal graphs when the maximum is positive. Up to isolated vertices, these are complete or complete split graphs for $D\ge 2M$, while $K_{2M}$ is uniquely extremal when $D=2M-1$. We also derive a general upper bound from the Chvátal-Hanson edge theorem and refine it for even $D$. For fixed even $D$ and $3\le t\le D+1$, every extremal graph consists, apart from isolated vertices, of copies of $K_{D+1}$ together with a remainder whose order is bounded independently of $M$. When $D/2$ divides $M$, this remainder is empty and the extremal graph is unique. This structure yields an eventual recurrence, reducing the determination of all extremal values and graphs to finitely many matching bounds.

math.CO · cs.DM

版本更新 · v2arXiv:2601.21514

Transversal gates for quantum CSS codes

Eduardo Camps-Moreno, Hiram H. López, Gretchen L. Matthews, Narayanan Rengaswamy, Rodrigo San-José

原文摘要

In this paper, we focus on the problem of computing the set of diagonal transversal gates fixing a CSS code. We determine the logical actions of these gates and characterize the subgroups that induce tensor products of single-qubit logical gates and logical identities. We describe these groups through explicit linear equations given by componentwise products of basis vectors of the underlying classical codes, which is the key difference from previous approaches. We compute the complete set of diagonal transversal gates fixing the code, and of transversal logical gates, for any CSS code arising from monomial codes, a family that includes decreasing monomial codes and polar codes. As a consequence, we recover and extend some results in the literature on CSS-T codes, triorthogonal codes, and divisible codes. We also extend these results to diagonal gates acting transversally on several code blocks and use them to characterize addressable gates.

cs.IT · quant-ph

新论文 · v1arXiv:2611.01257

A Numerical Refinement of an Exact Discrete Fourier Transform Bound

Zhihao Yao, Sichao Liu

原文摘要

We refine the numerical bounds in Kartal's instantiation of Sussman's exact discrete Fourier transform construction. For every integer n >= 1, the resulting algorithm computes the length-n transform with work O(n (log n)^(1 - delta)), where delta = 0.0030201659. The bound holds in an exact complex-arithmetic RAM model with a supplied canonical root of unity. This final exponent saving exceeds the earlier certified parameter C_0 = 0.00302016 by 5.9 x 10^(-9). We retain the underlying circuit, tighten rational bounds for sums of powers of its block and target ranks, and increase the fixed tensor power from 7760 to 11640. These bounds establish the inequalities for Sussman's recursion at the intermediate certificate parameter C = 0.00302016595. The gap C - delta absorbs the overhead of recursion and Fourier reduction. The resulting transform theorem is proved in Lean and checked against the reference problem statement.

cs.CC · cs.DS

新论文 · v1arXiv:2611.01256

LoRAForge: Co-Designing Post-Hoc Compression and Execution for Efficient Multi-LoRA Serving

Shenghui Li, Thiemo Voigt

原文摘要

Multi-LoRA serving allows many task-specific adapters to share a common base model, but scaling to large adapter fleets introduces substantial storage, loading, and execution overheads. Post-hoc compression can reduce the memory footprint of trained LoRA adapters, yet smaller ranks do not automatically translate into faster serving. For instance, padding, factor access, and generic kernels can obscure the retained low-rank structure, while independently recompressing thousands of modules also incurs significant preparation overhead. We present LoRAForge, a system connecting batched factor construction to rank-specialized execution through an explicit retained-rank representation. It supports two allocation policies: uniform retention ratios (LoRAForge-U) and spectral-energy budget allocation (LoRAForge-S). Both share FlashTSQR factor construction and the same serving backend. FlashTSQR exploits parallelism across modules and row tiles, accelerating factor construction by up to $2.28\times$ over matched library QR. In a fixed-work Qwen control, the shared runtime adds $1.17$--$1.22\times$ throughput across both compressed policies, with negligible gains on original adapters. Across 85 trained open-weighted Qwen and Llama adapters, the spectral policy's floored quality configuration retains about 7.7% of adapter parameters with fleet-average score drops of at most 1.2 points on a 0--100 scale. The same rank-floored $1/12$ spectral exports achieve substantial token-throughput gains on both AMD and NVIDIA GPUs.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01255

AdapBench: Adaptive Early-Stopping and Prioritization for Efficient Microbenchmarking in Cloud-based CI/CD

Sebastian Koch, Jonas Heisterberg, Nils Japke, Trever Schirmer, David Bermbach

原文摘要

Cloud-based software systems frequently release new versions, a fact further accelerated through agentic coding. Each new release, however, brings the risk of performance regressions which can irritate end users, increase infrastructure costs, and increase carbon footprints. Therefore, developers strive to catch such regressions in testing stages, usually through so-called continuous benchmarking. The standard way of doing this is using microbenchmark suites which, however, take notoriously long to execute. Optimizing the execution of microbenchmark suites is, hence, an active field of research. In this paper, we propose AdapBench, an online scheduling system for reducing the execution duration of microbenchmark suites. AdapBench is the first approach which dynamically makes at-runtime decisions for prioritizing the most informative benchmarks and early-stopping each one once enough evidence has accumulated to accept or reject a performance change hypothesis. We evaluate our prototype on eight popular Java projects, commonly used by microbenchmark research, and four additional Go projects. At matched 90% change detections and false-positive rate compared to an optimistic uniform run, AdapBench saves 42% of the aggregate execution duration on the Java projects, with negligible scheduling overhead (below 0.001% of the total runtime). On the Go projects, AdapBench finds every performance change with zero false positives while saving 85% of the full run.

cs.SE · cs.DC · cs.PF

新论文 · v1arXiv:2611.01252

Context-Shielded Backdoor Attack against Large Vision-Language Models

Zhifang Zhang, Qiang Huang, Chenpeng Wang, Weitong Chen, Olaf Maennel, Wei Emma Zhang, Lei Feng, Lei Zhang 等 9 位作者

原文摘要

Large vision-language models (LVLMs) routinely use inference-time visual-token compression to prune hundreds of patch tokens down to a compact budget. Existing LVLM backdoors fire whenever a triggered image appears, whereas prior deployment-triggered attacks activate only when model weights are quantized or pruned. However, conventional LVLM backdoors exhibit nearly 100% attack success rate (ASR) under full-token inference, immediately exposing compromised checkpoints during pre-deployment auditing. We reveal context stripping: surrounding clean visual tokens suppress an embedded trigger at full length, whereas token pruning strips this context away and activates the backdoor. Motivated by this finding, we propose StripWake, a projector-only backdoor that remains dormant under full-token auditing yet activates across unseen compressors. Specifically, StripWake pairs clean-supervised full-token views with target-supervised randomized compressed views, and aligns early visual attention with a frozen benign teacher to preserve clean utility. On LLaVA-1.5-7B across nine unseen compressors, StripWake stays dormant at 0.4% full-token ASR yet achieves 94.0%-99.7% compressed ASR across five primary compressors without CIDEr loss.

cs.CV

新论文 · v1arXiv:2611.01251

Entropic Column Generation and Lehmer Branch-and-Price for Bin Packing Problem

Masoud Ataei

原文摘要

We introduce Lehmer branch-and-price, an exact algorithm for bin packing and cutting stock problems built on the Lehmer transform, the ratio of Mellin transforms of item weights at consecutive orders. The transform maps each bin, a finite multiset of item weights, to a smooth increasing curve, and so gives the discrete problem a continuous representation on which the tools of analysis, such as convexity, exponential families and smoothing, can act. Read along this curve, the problem yields an explicit dual solution, a monotone representation of the dominance order, a family of constructive heuristics with first fit decreasing as its limit, and an integer identity that tells when the linear relaxation can decide an instance and when only a perfect packing can improve the best solution known. Lifted from items to patterns, the transform gives entropic column generation, a new form of column generation that bounds the relaxation from both sides at every iteration without solving the pricing problem exactly, maximizes a smoothed dual at an explicit rate, and measures by an entropy how much the relaxation leaves undecided. We show that the proposed algorithm outperforms the state-of-the-art methods on the standard benchmark in both the number of instances solved and the computational time.

math.OC · cs.DM

新论文 · v1arXiv:2611.01250

Shades of Success: Evaluating Manipulation Quality from Object-Centric Constraints

Lorena Maria Genua, Sarvesh Prajapati, Ananya Trivedi, Taskin Padir

原文摘要

As learned manipulation policies become increasingly capable of solving practical manipulation tasks, assessing how well a task is performed becomes a fundamental challenge. While binary labels confirm task success, they cannot distinguish successful executions with different levels of geometric precision. To address this, we introduce SPECTRA, an object-centric framework for quantifying execution quality in manipulation of rigid objects. From a small set of oracle demonstrations generated in simulation, SPECTRA represents object interactions through progress-aligned relative poses. SPECTRA identifies which relative-pose directions are constrained and their admissible variations from demonstrations. These constraints establish a reference for evaluating robotic manipulation tasks. To score an unseen execution, deviations beyond the admissible variation are summarized by a Task Quality Index Q in [0,1]. Across seven simulated tasks, SPECTRA recovers constraints with 94% accuracy using 30 demonstrations per task. On rollouts from three learned policies, its scores achieve pooled Spearman correlations with human judgments of p=0.81 over all rollouts and p=0.61 among successful rollouts, exceeding all baselines in both subsets. Using the task reference learned in simulation, we use SPECTRA to select the highest-scoring demonstrations for training a diffusion policy on hardware. Exploratory results show higher success rate than training on randomly selected demonstrations.

cs.RO

版本更新 · v3arXiv:2510.25069

TOPol: Reconstructing and Interpreting Multidimensional Semantic Polarity Fields

Lucia Gomez, Gabin Taibi, Julius Sipke Kooistra

原文摘要

Polarity in natural language processing has long been operationalized as a single axis: the sentiment construct. We challenge this one-dimensional view by asking what a topic's documents are bipolar about, without specifying an answer in advance. TOPol inverts the usual concept-direction paradigm: rather than mapping a named construct to one direction, it maps a topic to the full set of statistically reproducible bipolar semantic axes its documents support in a transformer's residual stream, and asks only afterwards which of them correspond to a known construct. These axes need not be evaluative. The method is a recursive, orthogonal-by-construction bipartition of each topic's document cloud, with a candidate axis promoted to a finding only if it survives one pre-specified split-half stability gate. We calibrate against a known answer first: on 9,986 Amazon reviews (14 discovered topics) in Gemma 3 4B, the star-rating difference-in-means vector serves as a ruler known by construction to be sentiment. Discovery blindly re-derives the sentiment axis in every topic (cosine 0.71-0.97) without ever seeing the rating label, while the same gate certifies 543 axes, of which 106 are near-orthogonal to sentiment yet equally reproducible; each topic supports 33-45 mutually orthogonal axes, and sentiment axes resolve in later layers than the rest. Differential vocabulary, an internals-grounded natural-language decoder and vocabulary-based clustering agree on what the non-sentiment axes contrast; clustering by shared vocabulary surfaces 99 families, 9 recurring across topics. Direction similarity to the ruler predicts an independent sentiment estimate only weakly ($r=0.243$). Polarity is better treated as a property of a topic's representational geometry, with a measurable rank and a per-axis depth, than as one universal scalar.

cs.CL

版本更新 · v3arXiv:2605.07746

Flow Matching for Count Data

Ganchao Wei, John Pearson

原文摘要

High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mappings between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based deep generative models for images, video, and text motivates extending these ideas to count-valued settings, but many existing methods either treat each count as a categorical state or transform counts into a continuous space, neither of which is natural or efficient when the count range is large. We propose count-FM, a flow-matching framework for count data based on a continuous-time birth-death process with local unit jumps. Count-FM learns marginal transitions efficiently in count space through simulation-free training of conditional transition rates, allowing transport between arbitrary count-distributed source and target populations. In simulation, count-FM variants achieve strong sample quality while using substantially fewer parameters. We further apply count-FM to scRNA-seq and neural spike-train data for unconditional generation, transport, and conditional generation. Across these tasks, count-FM yields improved sample quality, greater modeling efficiency, and interpretable transport paths.

stat.ML · cs.LG · q-bio.QM

新论文 · v1arXiv:2611.01245

Learning What to Ask and What to Believe: Distilling a Variational Bayesian Agent into Language Models

Baichuan Li, Yanling Chang, Alfredo Garcia

原文摘要

Interactive tasks such as eliciting a user's preferences or diagnosing a hidden mechanism require an agent to track its uncertainty over a latent state, ask informative questions and act on the answers. Language models have no explicit mechanism for this, whereas Bayesian information seeking provides one through posterior inference and expected information gain (EIG), and we ask whether it can be distilled into an 8B language model. Our teacher, a lightweight Bayesian agent with a sequential variational belief and EIG query selection, matches or approaches exact and particle references on three task families. We generate synthetic interactions with the teacher on episodes disjoint from the benchmark and fine-tune \Student{} to reproduce its queries and its belief state as a structured scratchpad. On three Multi-Turn Puzzles tasks the student raises Circuit Decoding from 0.00 to 0.93 success, lowers the normalized rank of the recommended film from 0.50 to 0.10 and cuts word guessing from 32 to 3.4 attempts, exceeding the strongest reported language models on the two comparable tasks. Exposing the belief state closes much of the gap where the decision is an implicit computation rather than a read-out of the interaction; in matched teacher contrasts, EIG supervision consistently outperforms random querying, whereas greater inference fidelity does not uniformly improve the distilled student; a 70B language-model teacher does not match the Bayesian teacher in downstream student performance, and the learned skill does not transfer to an unseen task family. Variational Bayesian information seeking can thus be amortized into a language model by transferring the belief state that drives its questions and decisions.

cs.LG

版本更新 · v4arXiv:2605.26236

DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation

Ferdinand Paar, Lanmiao Liu, Aslı Özyürek, Serge Thill, Esam Ghaleb

原文摘要

Co-speech gesture generation requires both semantic expressivity and biomechanically plausible rhythmic motion. Existing holistic gesture models mix lexically grounded semantic gestures with frequent prosody-aligned beat gestures. This limits semantic grounding, speech-motion alignment, and kinematic smoothness. We propose DuoGesture, a neuro-inspired and biomechanically informed approach that decomposes co-speech gesture synthesis into semantic and beat streams. The two streams are coordinated by a Semantic Variational Information Bottleneck, a stochastic frame-level gate that learns when semantic gestures should override rhythmic beat motion. The semantic stream is controlled by Motion-Grounded Semantic Conditioning, which replaces purely linguistic word embeddings with motion-language representations to provide motion-aligned semantic priors for long-tailed lexical triggers of gestures. The beat stream is further regularised by an Inertial Beat Prior, an anthropometry-weighted arm-chain module that reduces jitter and improves rhythmic consistency without constraining semantic frames. Objective evaluations and subjective experiments show that DuoGesture outperforms strong baselines, while component ablations confirm the complementary roles of semantic grounding, stochastic stream selection, and biomechanical regularisation. We encourage readers to view our demos and qualitative illustrations, which are available on the project page: https://ferdinandpaar.github.io/DuoGesture/.

cs.CV · cs.SD

版本更新 · v2arXiv:2510.01691

Can MLLMs Perceive and Describe Medical Image Quality Beyond Scores?

Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Jiafan Zhang 等 19 位作者

原文摘要

Medical Image Quality Assessment (IQA) serves as a critical safety gate for clinical AI, yet existing approaches rely on scalar metrics that fail to capture the descriptive, expert-like evaluation process central to clinical practice. We introduce MedQ-Bench, a comprehensive benchmark for language-based medical IQA evaluation with MLLMs, establishing a perception--description paradigm across 5 imaging modalities and over 40 quality attributes. The benchmark comprises two complementary tasks: MedQ-Perception probes low-level visual attribute discrimination via 2,600 expert-annotated perceptual queries; MedQ-Description covers both no-reference and comparison description sub-tasks with 708 expert-annotated samples, evaluated through a four-dimensional judging protocol. Comprehensive evaluation of 23 state-of-the-art MLLMs reveals that current models exhibit only preliminary and unstable capabilities, and highlights the urgent need for targeted optimization of MLLMs in medical IQA. Project & Dataset: https://github.com/liujiyaoFDU/MedQ-Bench

cs.CV

新论文 · v1arXiv:2611.01240

Learned Warm Starts for Steady Transonic RANS Simulations of Wing and Aircraft Configurations

Muhammad Irfan Zafar, Saleh Abuhanieh, Şahin Yiğit

原文摘要

Neural surrogates can accelerate many-query aerodynamic analyses, but their standalone predictions may be insufficiently accurate or robust to support reliable design evaluations. We develop a learned warm-start formulation that predicts mean-flow and turbulence fields directly on native CFD meshes for subsequent correction by the RANS solver. A common architecture and objective structure are used across subcritical and transonic flows, including challenging conditions with shock-induced separation. A condition-modulated Transolver combines Fourier and wall features with target-gated regularization, a Sobolev-type loss, adaptive loss weighting and sampled training. Prediction requires no preliminary flow solution, and training requires no solver-residual evaluation. Extensive 3D CFD evaluations on SuperWing, the NASA Common Research Model (CRM) and DLR-F6 assess geometric and operating-condition generalization, including interpolation, extrapolation and cross-mesh deployment, using Spalart-Allmaras and $k$-$ω$ SST closures on million-cell meshes. Unseen nominal cases achieve geometric-mean iteration speed-ups of approximately $2$-$4\times$ under a common convergence criterion based on cold-run aerodynamic coefficients. On CRM, learned initialization provides greater aggregate acceleration than nearest-condition restarts using the same solution library. Resolution invariance enables direct deployment of coarse-mesh models on finer meshes without retraining, solution interpolation or target-condition coarse solves. Including data generation and training, estimated campaign speed-ups reach $2.1$-$2.3\times$. No warm run diverges; fewer than $2\%$ fail to satisfy the cold-reference convergence criterion. These results support learned initialization for repeated aerodynamic analyses, while highlighting initialization sensitivity near separation as a remaining limitation.

cs.CE · physics.flu-dyn

新论文 · v1arXiv:2611.01239

Mathematical Formulation and Comparative Performance Evaluation of Machine Learning Algorithms for Maize Land Suitability Prediction

Haimanot Bitew, Ayisheshim Almaw, Habtamu Zegeye, Demeke Alene

原文摘要

Addressing the food needs of a growing population is one of the major challenges of developing countries like Ethiopia. Various policies aimed at increasing food production have been enacted by governments and development partners. Although efforts in this regard have been made, there is still inadequate emphasis on increasing food production through the use of high technology practices. Precision agriculture using technology has been utilized to increase crop yield. Precision agriculture also relies on identifying land for a crop, which is a key factor that affects crop yield. Traditional methods of assessing land suitability for crop production are time-consuming, costly and unreliable. Against this background, the aim of this study was to assess the potential of machine learning (ML) in improving the speed and accuracy of assessing land suitability for maize, a staple crop in Ethiopia, as compared to traditional methods. The study is investigated in three areas (Burie, Shindi and Tilili) in the Amhara region. Data collection was done through the local agriculture offices and survey teams. The data were coded, scaled and balanced. Various feature extraction techniques, which included Univariate Feature Selection(UFS), Recursive Feature Elimination with Cross-Validation(RFECV) and Sequential Feature Selection(SFS), and various classifiers, which were K-nearest neighbor (KNN), gradient boosting (GB),random forest (RF) with mathematical formulations were employed. The best models were constructed through combining GBOOST and SFS and achieved an accuracy of 99.41% and 99.35% for both precision and recall. Our results showed that using machine learning is a reliable method of assessing land suitability for maize in Ethiopia. Keywords: Maize, Gradient boosting,Land suitability,Machine learning, Mathematical formulations

cs.LG · cs.AI

新论文 · v1arXiv:2611.01234

How Much Can Approximate Equilibria Change the Social Cost of Selfish Routing?

Yu Cheng, Tianle Jiang

原文摘要

We study approximate Nash equilibria in nonatomic congestion games, with the goal of understanding how much the social cost can change when the equilibrium condition is relaxed. We consider $ε$-approximate Nash equilibria ($ε$-NE), in which each player uses a strategy whose cost is at most $1 + ε$ times the minimum available cost. We compare the social costs of $ε$-NE and exact Nash equilibria. This lets us quantify, for example, how much a navigation app can reduce total travel time when drivers tolerate routes slightly slower than the fastest available route. For degree-$d$ polynomial latencies in both general nonatomic congestion games and single-commodity routing games on series-parallel networks, we give tight lower and upper bounds on the relative change in social cost from an exact Nash equilibrium to any $ε$-NE, with matching instances for every $ε$. For small $ε$, the largest possible relative reduction and increase in general congestion games are both $Θ(\sqrt{dε})$, independently of the number of resources and populations. In contrast, on series-parallel networks of depth $h$, the largest possible relative reduction is $Θ(hε)$, while the largest possible relative increase is known to be $ε$. For the classes of games we study, these results give a tight and quantitative characterization of the possible changes in social cost and establish a separation between general and series-parallel networks.

cs.GT · cs.AI · cs.DS · math.OC

新论文 · v1arXiv:2611.01233

STLT: A Novel System for Energy-Aware Distributed Inference in the Edge-Cloud-Space Continuum

Andrija Stanisic, Milos Gravara, Juan Luis Herrera, Stefan Nastic

原文摘要

Low Earth Orbit satellites are pivotal for Earth observation tasks such as wildfire detection, capturing imagery for analysis by Deep Neural Networks (DNNs). On-board analysis reduces downlink volume, but severe energy constraints force a trade-off between computation and data transmission. Splitting the DNN between satellite and ground turns this balance into a design choice, where the split point determines combined computation and downlink energy. Existing approaches typically rely on static split-point decisions that fail to account for dynamic space conditions, or on complex algorithms, historical data, or prediction models that introduce significant overhead. To address these shortcomings, we present STLT, a two-stage system for energy-aware distributed inference between LEO satellites and a ground station. First, an offline analyzer characterizes the DNN architecture to identify a set of favorable split points, consequently reducing the search space. Second, an on-board algorithm performs lightweight energy-aware split selection, dynamically choosing from this pre-computed set based on the current state of the environment. We evaluate STLT on a real-world satellite telemetry dataset, showing that it reduces the split-candidate search space by 30.7% on average, lowers decision latency by 25.1% and energy by 27.5% on average, and delivers up to 20.1% more inference tasks than a state-of-the-art satellite-ground co-inference baseline while consuming 8.8% less energy overall.

cs.DC · cs.AI

版本更新 · v3arXiv:1704.04538

A Simple Randomized Estimator for Harmonic Numbers and Logarithms

Ali Dasdan

原文摘要

Scanning a list of $x$ distinct numbers in uniformly random order for its maximum replaces the running maximum $H_x$ times on average, where $H_x$ is the $x$th harmonic number. Run backwards, this gives an estimator: the replacement count of a random list is an unbiased Monte Carlo estimate of $H_x$, and since $H_x = \ln x + γ+ O(1/x)$, a corrected estimate of $\ln x$. We give the exact variance of the count, an error decomposition with sample-size rules, and an exact sampler of the count using $H_x$ integer draws on average instead of a scan of length $x$. Coupling two counts estimates $\ln(a/b)$ without $γ$, and a binary range reduction then bounds the standard error by $\sqrt{\ln 2/n}$ for every $x$ at fewer than $1.7$ draws per repetition on average. A classical deterministic series on the same reduction reaches the rounding floor with sixteen terms in the reported experiments, quantifying the gap between the two approaches. The purpose is pedagogical: the analysis of an algorithm becomes an estimator of the quantity that analysis produces, with exact variances, finite-sample error bounds, reproducible experiments, and machine-checked algorithm contracts and moment identities. The ingredients are classical; the contribution is their assembly.

cs.DS

新论文 · v1arXiv:2611.01230

Reproducing INP-Former: Reconstructing Intrinsic Normal Prototypes for Industrial Anomaly Detection

Yunfei Liang, Juan Pablo Osorio Rivera

原文摘要

We reproduce the central claims of INP-Former, a reconstruction-based method for multi-class industrial anomaly detection. INP-Former extracts Intrinsic Normal Prototypes (INPs) from each test image and uses them to guide a decoder that reconstructs normal features, without a stored memory bank. Using the authors' released code, we reproduce the reported performance on MVTec AD and VisA and extend the evaluation to MVTec AD 2, where image AUROC with the default settings is 63.4, compared with 99.7 on MVTec AD. On MVTec AD, a five-seed ablation shows that most of the performance comes from the INP mechanism, while the two auxiliary losses add small changes whose direction depends on the metric. A paired comparison with both losses disabled confirms the benefit of INP on MVTec AD 2. The default of six prototypes transfers less well: the plateau beyond four prototypes reproduces on MVTec AD and VisA, but on MVTec AD 2 a single prototype outperforms six in AU-PRO on the public split and on both hidden test splits. We also measure practical trade-offs in resolution, backbone size, training length, and LoRA adaptation, and examine performance by defect size, lighting condition, and a stricter AU-PRO limit. Several conclusions from the original benchmarks, including the default prototype count, do not carry over to harder data. Code: https://github.com/garasnote/Repro-INPFormer

cs.CV · cs.LG

新论文 · v1arXiv:2611.01229

Precision Through Play: Enhancing Fundamental Laparoscopic Skill Acquisition Via Gamified XR and Pseudo-Haptics

Bita koohestani, Ashkan Rezaei, Azam Bastanfard

原文摘要

Extended Reality (XR) technologies have shown potential to improve laparoscopic skills acquisition. Among fundamental skills in laparoscopic surgery is accurate instrument handling. Appropriate instrument alignment and a perpendicular path ensure movement efficiency and improved performance. This work introduces an interactive XR platform designed to support an immersive, engaging, and accessible environment that facilitates continuous practice. This platform incorporates a gamification layer enriched by pseudo-haptics that generate a motivational feedback loop, allowing trainees to continuously practice instrument manipulation and angle control. The platform monitors instrument orientation, computes angular deviation from an ideal reference vector, and assigns scores based on user performance. A point-based scoring component reinforces correct technique and penalizes deviations in tool alignment beyond predefined thresholds. Furthermore, a pseudo-haptic feedback mechanism is integrated to provide real-time tactile feedback when deviation exceeds tolerance. Combined with low-cost hardware and accessible deployment, the framework aims to increase training scalability, engagement, and improve skill acquisition. Preliminary evaluations indicate that integrating gamified feedback significantly improves precision, reduces angular variance, and encourages sustained practice.

cs.HC · cs.GR

新论文 · v1arXiv:2611.01225

When Benign Is Unverified: Label-Signal Mismatch and Abstention-First Triage in Graph-Based Memory Forensics

Viraj Rajeshbhai Chudasama, Eduardo Palmieri, Dipo Dunsin, Aisha Junejo, Mohamed Chahine Ghanem

原文摘要

Machine-learning triage for memory forensics is usually validated on corpora whose benign class is asserted by provenance and never verified. We report a validation study of a graph-based triage pipeline for Windows memory images: Volatility 3 output is compiled into typed heterogeneous graphs and scored by a temperature-scaled GINE classifier and two one-class encoders, fused with rule risk under an abstention gate. On MalVol-25 a transparent rule layer contradicts the benign label on every control (15/15 and 18/18 flagged; at least 11 of 15 paired controls rated HIGH or CRITICAL), and mean injection and command-and-control counts run higher on controls than on infected captures. We call this rule-label discordance label-signal mismatch; it shows the benign class is unverified, not compromised. Leave-one-family-out AUROC over matched pairs is provably three-valued, so a reported mean and standard deviation identify the fold composition. The learned model (0.786 +- 0.311; 9/4/1, scored in-sample by a frozen checkpoint) equals a logistic model over rule-derived attributes (0.786 +- 0.410; 11/0/3) in mean only, and its significance rests on dropping four saturated ties. The fusion path sends 97.7% of snapshots to analyst review, 95.3% with every gate disabled. Two public feature-level corpora show the same defect: on CIC-MalMem-2022 every benign row carries injected regions and one host-population feature reaches AUROC 0.997 under leave-one-family-out validation; on the Sihwail et al. (2021) sample the injection indicator fires on 53% of benign rows. We close with seven reporting artefacts for learned triage on corpora whose ground truth is asserted.

cs.CR · cs.OS

新论文 · v1arXiv:2611.01222

Modeling Fat-shift for Improved Head Segmentation from MRI Scans using a Probabilistic Model

Merle Diedrichsen, Koen Van Leemput, Douglas N. Greve, Oula Puonti, Axel Thielscher

原文摘要

Personalized computational head models for biophysical simulations rely on accurate whole-head segmentations from T1-weighted (T1w) magnetic resonance imaging (MRI) scans. While T1w scans provide excellent contrast for intracranial anatomy, extracerebral tissues have partly almost no signal (compact bone) and also suffer from the so-called chemical shift artifact, which affects the fatty tissues in MRI and causes them to spatially shift in the frequency encoding direction of the scan. This artifact occurs primarily in two structures of the head: the spongy bone, a fatty compartment inside the compact bone, and the subcutaneous fat, located directly underneath the skin. The frequency-encoding direction is often set in the superior-inferior direction, causing the fatty tissues to shift down and, as a result, making the skull appear thinner than it actually is. Existing segmentation methods do not model this artifact, consequently leading to inaccurate labeling of the skull and scalp, which introduces a bias in biophysical simulations. The direction and magnitude of the fat-shift can be determined from the scan parameters, thus making it possible to explicitly model the shift and to recover the correct anatomy. This study introduces a probabilistic model that uses variational inference to segment head and brain structures from a T1w scan while accounting for the fat-shift artifact. The proposed Fat-shift-informed Label Optimization of the Whole head (FLOW) method reconstructs extracerebral anatomy more accurately than a fat-shift-agnostic segmentation approach while maintaining high segmentation accuracy in all other structures. FLOW-based fat-shift corrected segmentations significantly reduce bias in electric field simulations compared to a segmentation method that does not model the shift.

cs.CV

版本更新 · v4arXiv:2510.06445

A Survey on Agentic Security: Applications, Threats and Defenses

Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed, Farig Sadeque, Md Rizwan Parvez

原文摘要

In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of 274 papers that covers red-teaming, blue-teaming and domain-specific applications, attack surfaces on agentic systems, defense techniques, and both offensive and defensive evaluation frameworks. For each pillar, we first discuss the literature around the taxonomy and then perform a quantitative analysis to understand the patterns across these works. For the applications, we show their security-lifecycle coverage map, compare between red-teaming and blue-teaming agents, and analyze the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. Finally, we provide a deatiled cross-cutting analysis, where we map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, and data modality coverage. Taken together, these findings give a researcher a structural understanding of how agentic capabilities, vulnerabilities, and countermeasures relate to one another, and to identify where the field is concentrated and where it is thin.

cs.CL · cs.AI · cs.CR

新论文 · v1arXiv:2611.01220

Differentiable Iterative Learning Control for Black-Box Position-Commanded Manipulators

Mohammed Al-Ghaili, Yakoop Qasim, Hassan Almubarak

原文摘要

High-accuracy repetitive tracking is challenging for position-commanded manipulators whose low-level controllers are inaccessible, while constrained model-based iterative learning control (ILC) can require substantial manual parameter tuning. We present Differentiable Iterative Learning Control (Diff-ILC), an online bilevel framework that adapts the parameters of a constrained ILC update between physical robot executions. A closed-loop differential model is identified once from paired smooth perturbations and subsequently kept fixed. At each trial, a constrained quadratic program computes a feasible command correction, while a real-anchored next-trial prediction defines a task-level objective. Hypergradients are obtained by implicitly differentiating the locally active KKT system, enabling multiple computational parameter updates without additional robot executions. Experiments on a 6-DoF DOBOT CR3 across unseen planar and three-dimensional trajectories show substantially faster physical-trial convergence than fixed-parameter model-based ILC. Across the four primary trajectories, after only two trial-to-trial updates, Diff-ILC achieves 78.8% and 76.4% lower mean joint-vector and Cartesian RMSE, respectively, than fixed-parameter model-based ILC.

cs.RO · eess.SY

新论文 · v1arXiv:2611.01219

The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse

Samuel Harvan, Jaroslav Kopčan, Marek Šuppa, Andrej Findor

原文摘要

In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak) prompts yield a modest, task-dependent gains, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions (system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.

cs.CL

版本更新 · v3arXiv:2601.18706

Health-SCORE: Improving Open-Ended Health LLMs Using Scalable Rubric-Based Rewards

Zhichao Yang, Sepehr Janghorbani, Dongxu Zhang, Jun Han, Qian Qian, Andrew Ressler, Gregory D. Lyng, Sanjit Singh Batra 等 9 位作者

原文摘要

Reinforcement learning is a powerful approach for improving language models, but applying it to open-ended domains such as healthcare remains challenging because high-quality responses are often multidimensional, context-dependent, and difficult to capture with a single reward signal. Rubrics offer a natural form of supervision by providing a structured representation of the criteria that define a strong response. Existing rubric-based approaches, however, often rely on instance-specific criteria, creating two important limitations: (1) such rubrics are typically unavailable for unseen examples at test time; and (2) constructing new rubrics for every instance incurs substantial reward design costs. We introduce Health-SCORE, a scalable framework that captures recurring principles of response quality in the form of reusable meta-rubrics. Rather than relying on manually constructed instance-level criteria, Health-SCORE captures generalizable principles that can be applied across examples, tasks, and healthcare datasets. These meta-rubrics support two forms of model improvement: they can serve as structured, safety-aware reward signals for reinforcement learning during post-training, and they can be incorporated directly into prompts to guide model behavior at inference time. Across several open-ended healthcare benchmarks, models trained with Health-SCORE achieve performance competitive with models trained using human-authored instance-level rewards, while substantially reducing reward-design costs and improving generalizability.

cs.AI · cs.LG

版本更新 · v2arXiv:2606.04177

A Systematic Analysis of Linguistic Features in AI-Generated English Text Detection Across Domains and Models

Yassir El Attar, Esra Dönmez, Maximilian Maurer, Agnieszka Falenska

原文摘要

Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users. However, existing findings on which features reliably indicate LLMgenerated text remain fragmented across feature sets, models, and text domains. To address this gap, we conduct a large-scale empirical study assessing the robustness of linguistic signals for characterizing AI-generated text. Our analysis covers 284 interpretable linguistic features across outputs from 30 LLMs and 10 text domains under cross-model and cross-domain generalization settings. We show that classifiers based solely on linguistic features can reliably distinguish AI-generated from human-written text. However, many previously proposed indicators prove strongly context-dependent, with the exception of measures of lexical richness, which remain robust signals across model families and text domains. These results demonstrate which linguistic signals generalize across contexts and provide a foundation for more reliable, interpretable analyses of AI-generated language.

cs.CL · cs.AI

新论文 · v1arXiv:2611.01218

Optimal Conversion from Zero-Concentrated to Gaussian Differential Privacy

Yu-Wei Chen, Aaradhya Pandey, Jordan Awan

原文摘要

Gaussian differential privacy (GDP) and zero-concentrated differential privacy (zCDP) are two competing privacy accounting frameworks, but they share similar minimax lower bounds in various estimation problems. Moreover, it is known that a mechanism satisfying $μ$-GDP satisfies $(μ^2/2)$-zCDP, whereas the converse fails to hold at the same calibration. In this paper, we establish the optimal reverse conversion, showing that every $ρ$-zCDP mechanism satisfies $μ_{\mathrm{zCDP}}(ρ)$-GDP, where $μ_{\mathrm{zCDP}}(ρ)=2Φ^{-1}((1+e^{-t_ρ})^{-1})$ and $t_ρ$ uniquely solves the equation $ρ=t_ρ\tanh(t_ρ/2)$. We also obtain simplified bounds $\sqrt{πρ}\leqμ_{\mathrm{zCDP}}(ρ)\leq\sqrt{8ρ}$, with sharp constants, which imply equivalence of the two frameworks up to constants. This explains why their minimax risks agree up to a constant rescaling of the privacy budget. We show that the squared conversion is strictly convex, which implies that converting zCDP to GDP before applying composition or group privacy yields a tighter GDP guarantee than converting afterward. We also derive the sharp conversion from bounded-range and logistic DP mechanisms (e.g., exponential mechanism) to GDP, where converting before composition but after group privacy gives the tighter guarantee.

cs.CR · math.ST

版本更新 · v2arXiv:2609.18272

Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI

Mohamed Chahine Ghanem, Baidaa Al-Bander

原文摘要

Agentic AI systems plan, invoke tools, and act with limited supervision; they are now both the subject of audits and, increasingly, the auditor. Independence-the foundation of assurance-is still applied to them as a binary. We argue that it must be graded along three orthogonal axes: principal independence (who controls the auditor), substrate independence (an auditor that shares the auditee's foundation-model family, toolchain, or guardrails fails with the auditee), and evidence independence (whether evidence is attestable rather than self-reported). Each axis has precedent; the contribution is to grade all three on a single audit, aggregate them by the weakest link, and apply the same rubric when the auditor is itself an agent. We give the model a formal basis by transplanting the beta-factor model of common-cause failure from reliability engineering. We also provide a seven-step protocol whose outputs a third party can verify, a structural detectability analysis of a procurement-controls agent audited at three grades, and a closed-form study of the model in which, at a declared common-mode share of 0.90 for a same-family auditor and a declared reporting probability of 0.6 for an internal team, a conventional internal audit of an agent-a real audit team, a second agent, and provider logs-surfaces 5.9% of the faults it could in principle see and, independently of those two values, none at all in half of the fault classes. Because an evidence grade says who could have altered a record, not what the record covers, every load-bearing record also carries a declared-scope predicate, and reports carry a false-flag rate beside the detection floor wherever the auditor's own performance has been measured. We map the triple to the EU AI Act as amended, ISO-IEC 42006, UK public-sector risk-management guidance, and audit-regulator practice.

cs.AI · cs.CR · cs.ET

新论文 · v1arXiv:2611.01216

Adaptive Optimizers Can Get a Policy Ranking Wrong: Momentum, Dependent Data, and a Two-Run Remedy

Sunyoung An, Xiaoming Huo

原文摘要

Operators choosing among decision rules, such as when a battery charges or where an idle taxi goes, rank them by estimated long-run value. A standard estimator, linear temporal-difference (TD) learning, fits values from one stream of correlated observations. Large fits often use an adaptive optimizer, such as adaptive moment estimation (Adam), with fixed averaging rates. We show that these rates can change what is estimated, not just how fast: the same observations drive the updates and the optimizer's step-size scaling, moving the fit away from the intended TD value. The shift differs across rules, so it need not cancel in a comparison, and more data only makes a wrong ranking look more certain. Our remedy refits the same data at a second averaging rate that halves the effective gain, the number to which the leading shift is proportional. Twice the new fit minus the original removes that shift. In New York taxi and battery models calibrated to real data, common optimizer settings leave the selected rule unchanged but order close rules wrongly and misstate its value. Our remedy corrects nearly every wrong ordering, with one extra fit when the shift is moderate and two when it is larger.

stat.ML · cs.LG · math.OC · math.ST