跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 05:26 — 2026-11-09 05:26（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：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
版本更新 · v2arXiv:2610.22225

Safe and Fuel-Efficient Motion Planning for Lunar Propulsive Drones

Elena Wittemyer, Grace Gao

原文摘要

Propulsive drones are a promising new technology for generating high-resolution terrain models of the Moon. In future lunar missions, propulsive drones will complete a series of hops across the lunar surface while capturing images with downward-facing cameras. We present an autonomous motion planning framework that uses a vision-guided optimal control strategy for performing safe, efficient hops between specified waypoints. The drone plans parabolic hops between waypoints generated by a global-level planner; if a nominal waypoint is unsafe or unreachable, the drone then completes a diversion maneuver to safely land. To evaluate the validity of potential landing sites, we develop a custom semantic segmentation model for identifying obstacles from aerial images, and we introduce an approach for rapidly calculating reachable terrain. We then use model predictive control (MPC) to robustly track hop trajectories that guide the drone towards safe landing sites. We test the optimal hop planner in a high-fidelity lunar simulation environment. Our results demonstrate that our unified motion planning framework yields safe, fuel-efficient hop trajectories which can be tracked rapidly and with low error via MPC.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33745

POD-RoPE: Rotary Position Encoding over Physical Observation Distributions for Embodied AI

Xiaodi Huang, Zilin Wang, Jinpeng Liu, Pengchuan Xiao, Zhenlei Shao, Zhang Zhang

原文摘要

Embodied perception requires positional representations that capture both physical geometry and the spatial and temporal extent of observations. We introduce POD-RoPE (Physical Observation Distribution RoPE), which represents token observation footprints as distributions over camera centers, viewing directions, and sampling times. Under independent sampling, expected rotations encode relative relationships between distributions; when each distribution collapses to a single address, the construction recovers pointwise RoPE. The same rotation statistics support Q/K matching and coherence-dependent V/O transformations, allowing observation geometry to guide both information selection and content aggregation. Per-token pre-aggregation avoids increasing sequence length or processing pairs of observation nodes. We evaluate POD-RoPE across four robot policy architectures, simulation and real-world manipulation, and complementary reconstruction, depth-estimation, and novel-view-synthesis tasks. Integrating POD-RoPE into Fast-WAM improves mean success from 91.83% to 92.88% across all 50 RoboTwin 2.0 tasks, and from 32.5% to 52.5% on two real-robot tasks on Sharpa North. Controlled reconstruction ablations support the contributions of distribution encoding and V/O transformations. In H20 model-block benchmarks, POD-RoPE achieves median forward-plus-backward speedups of $1.91\times$ over P-RoPE and $5.34\times$ over RayRoPE, with a median latency overhead of 17.4% over Standard RoPE. These results support physical observation distributions as an effective and computationally efficient basis for geometry-aware attention.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38658

Larger Crossing Families

Joachim Orthaber, Patrick Schnider

原文摘要

We give the first explicit constant for crossing families of linear size by showing that every set of $n$ points in general position in the plane contains a crossing family of size approximately $\frac{n}{79}$. We further identify some conditions where there are even larger crossing families. The first such condition forbids the existence of a large different pattern, namely non-convex 4-clusters: We show that every point set contains either a large non-convex 4-cluster or a large crossing family. The second condition is the existence of many crossings: We give a bound for the size of a crossing family in terms of the number of crossings of the complete geometric graph drawn on the point set.

math.CO · cs.CG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38657

Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation

Jacob Levy, Arthur Bouton, Tristan D. Hassler, Hari Nayar, David Fridovich-Keil

原文摘要

Future planetary rovers will traverse steep, deformable terrain where slip, sinkage, and terrain deformation can threaten mobility. Although simulation can capture some wheel-soil effects, unmodeled deformable-terrain phenomena create sim-to-real gaps requiring deployment-time adaptation. Yet, rover operations leave little room for extensive trial-and-error. We introduce TERRA (Targeted Exploration for Reward-Relevant Adaptation), an online adaptation framework that efficiently seeks deployment data exposing task-relevant model errors and corrects them. TERRA adapts a simulation-trained world model with a reward-weighted prediction loss and trains a loss predictor to estimate where future performance-relevant errors are likely to occur, using this signal to guide exploration during MPC. In simulation, TERRA reaches approximately 90% slope-climbing success within five trials under severe out-of-distribution pretraining conditions, outperforming exploration baselines in reward, completion time, and energy to first success. On the ERNEST rover, TERRA recovers coordinated active-suspension locomotion on a deformable Mars-simulant slope within three to five real-world trials. Project website: https://terra-explore.github.io

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38656

Wav2Aug: A Drop-In Speech Augmentation Policy

Gianfranco Dumoulin Bertucci, Mirco Ravanelli

原文摘要

SpecAugment is the dominant speech augmentation policy, but researchers have studied it primarily for automatic speech recognition (ASR), and it operates on spectrograms, limiting its applicability to other speech tasks and waveform models. We propose Wav2Aug, a drop-in waveform augmentation policy that randomly samples two augmentations from a calibrated pool of waveform transformations. We calibrate the augmentation hyperparameters once and reuse them across tasks and architectures, eliminating task-specific tuning. Experiments on ten speech benchmarks show that Wav2Aug achieves ASR performance comparable to SpecAugment while improving over it on average across non-ASR tasks, yielding an average relative error reduction of 12.8% over the strongest compatible SpecAugment baseline. We further show that multi-view training provides additional gains, with two augmented views offering the best tradeoff between performance and computational cost.

eess.AS · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.28421

Learning unified control of intrinsic nonlinear spin dynamics in atomic qudits for magnetometry

C. Z. Cao, J. Z. Han, M. Xiong, M. Deng, L. Wang, Q. Liu, X. Lv, M. Xue

原文摘要

Generating and preserving metrologically useful quantum states is a central challenge in quantum-enhanced metrology. In low-field atomic magnetometry with multilevel atoms, the nonlinear Zeeman (NLZ) effect is both a resource and a limitation. It can generate internal spin squeezing within a single atomic qudit, but under fixed readout it also rotates and distorts the measurement-relevant quadrature, limiting the usable metrological gain. The problem is further complicated by the time dependence of both the squeezing axis and the nonlinear evolution itself. Here we show that reinforcement learning can transform NLZ dynamics from a source of readout degradation into a sustained metrological resource. Using only experimentally accessible low-order spin moments, a trained agent identifies a unified control policy for this class of intrinsically nonlinear sensing dynamics. We illustrate the approach in the \(f=21/2\) manifold of \(^{161}\mathrm{Dy}\), where the learned policy rapidly prepares strongly squeezed internal states and stabilizes more than \(4\,\mathrm{dB}\) of fixed-axis spin squeezing under continuous NLZ evolution. Including state-preparation overhead, the learned protocol yields a single-atom magnetic-field sensitivity of \(13.9\,\mathrm{pT}/\sqrt{\mathrm{Hz}}\), approximately \(3\,\mathrm{dB}\) beyond the standard quantum limit. Our results establish learning-based control as an experimentally feasible route for converting unavoidable intrinsic nonlinear dynamics in multilevel atomic sensors into operational metrological advantage.

quant-ph · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.02677

Eliciting ESG Preferences for Reinforcement Learning-Based Portfolio Optimization

Giovanni Dispoto, Marcello Restelli, Carmine Ventre

原文摘要

Modern portfolio management increasingly demands a balance between traditional risk-adjusted returns and strict Environmental, Social, and Governance (ESG) mandates. Current Reinforcement Learning (RL) approaches typically optimize for a single ESG provider, neglecting the significant divergence in rating methodologies across the industry and the unintuitive nature of manually weighting conflicting objectives. This paper addresses these limitations by formulating ESG-aware portfolio optimization as a Multi-Objective Reinforcement Learning (MORL) problem that simultaneously incorporates ratings from three distinct ESG agencies. To bridge the gap between high-dimensional algorithmic trade-offs and human decision-making, we integrate a Preference Elicitation framework using Gaussian Processes. This system enables practitioners to align the RL policy behavior with their preferences through intuitive pairwise comparisons of candidate portfolios based on their Sharpe ratios and aggregate ESG scores. We systematically evaluate our framework by employing prompt-conditioned LLMs as synthetic preference oracles under varied regional conditions and assess how the methodology adapts to heterogeneous investment behaviors and sustainability preferences. The experiments demonstrate feasibility in a controlled synthetic setting and characterize sensitivity to oracle and prompt design.

q-fin.PM · cs.CE · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38651

Information-Theoretic Reliability--Safety Bounds and Finite-Alignment Dynamics in AI Knowledge Distillation

Miao-Miao Yi, Zhen-Yu Cai, Y -M. Du, C. P. Sun

原文摘要

The reliability and safety of artificial intelligence (AI), together with their transfer and evolution through knowledge distillation, have attracted growing attention. We establish an information-theoretic bound on the reliability--safety trade-off and characterize the dynamics of this trade-off under knowledge distillation. We first prove a universal trade-off inequality that is independent of the specific model form. Its boundary is determined solely by a single parameter Kh, which quantifies the hidden layer's ability to distinguish benign from hazardous inputs. We then develop a canonical Boltzmann-machine model of AI response behavior and derive two exact relations between reliability and safety. The trade-off curve is determined by the hazard discrimination capacity K, while the overall answer tendency controls the operating point along the curve. These relations agree well with existing experimental data. In knowledge distillation, we find that teacher responses induce a renormalization of the student model's trade-off parameters. We further use a renormalization-group approach to study multigenerational distillation, deriving exact recursion relations and the associated renormalization-group-like flows for two representative direct intergenerational distillation protocols at arbitrary teacher--student alignment strength. These flows reveal fixed-point structures, long-term dynamics, and critical behavior, yielding testable predictions for the critical transition between capability loss and stable transmission.

cond-mat.stat-mech · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.23254

Optimal In-context Adaptivity and Distributional Robustness of Transformers

Tianyi Ma, Tengyao Wang, Richard J. Samworth

原文摘要

We study in-context learning problems where a Transformer is pretrained on tasks drawn from a mixture distribution $π=\sum_{α\in\mathcal{A}} λ_α π_α$, called the pretraining prior, in which each mixture component $π_α$ is a distribution on tasks of a specific difficulty level indexed by $α$. Our goal is to understand the performance of the pretrained Transformer when evaluated on a different test distribution $μ$, consisting of tasks of fixed difficulty $β\in\mathcal{A}$, and with potential distribution shift relative to $π_β$, subject to the chi-squared divergence $χ^2(μ,π_β)$ being at most $κ$. In particular, we consider nonparametric regression problems with random smoothness, and multi-index models with both random smoothness and random effective dimension. We prove that a large Transformer pretrained on sufficient data achieves the optimal rate of convergence corresponding to the difficulty level $β$, uniformly over test distributions $μ$ in the chi-squared divergence ball. Thus, the pretrained Transformer is able to achieve faster rates of convergence on easier tasks and is robust to distribution shift at test time. Finally, we prove that even if an estimator had access to the test distribution $μ$, the convergence rate of its expected risk over $μ$ could not be faster than that of our pretrained Transformers, thereby providing a more appropriate optimality guarantee than minimax lower bounds.

stat.ML · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.25184

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

Jiahao Wu, Ning Lu, Shengcai Liu, Kun Wang, Yanting Yang, Baijiong Lin, Chen Jason Zhang, Li Qing 等 9 位作者

原文摘要

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility. To address this problem, we investigate how to select high-utility prompts before the rollout phase. Our experimental analysis reveals that sample utility is non-uniform and evolving: the strongest learning signals concentrate at the ``learning edge", the intersection of intermediate difficulty and high uncertainty, which shifts as training proceeds. Motivated by this, we propose HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL. HIVE utilizes historical reward trajectories for coarse selection and employs prompt entropy as a real-time proxy to prune instances with stale utility. By evaluating HIVE across multiple math reasoning benchmarks and models, we show that HIVE yields significant rollout efficiency without compromising performance.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38648

Logical Guidance of Stochastic Interpolants

Gerrit Gerhartz, Francesco Alesiani, Jonathan Warrell, Henrik Christiansen, Matheus Ferraz, Mathias Niepert

原文摘要

Guidance and composition of generative models have applications in visual design, chemistry, and biology. Logical guidance composes conditional scores exactly for diffusion models. However, Flow Matching (FM) and Stochastic Interpolants (SI) learn velocity fields. We show that negation and exclusive disjunction admit exact conditional velocity composition on any interpolant, whereas conjunction, and therefore any formula containing one, is exact on Gaussian paths but in general incurs a drift-interaction error, so composed velocities need not sample the logical target. LOGSI solves this by using score-based re-equilibration as our principled mechanism and falling back to the Gaussian-path velocity rule as an approximate transport predictor. In non-Gaussian bridge problems, generation alternates transport steps with score re-equilibration steps. On image trans fer (EMNIST to CMNIST, CelebA) and QM9 source-to-target molecular editing with logical attribute constraints, LOGSI improves rule conformity at the same network-evaluation budget over composed-velocity baselines, while also improving fidelity on the image tasks. More broadly, LOGSI applies wherever stochastic interpolants need guidance and logical combinations of constraints are natural.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38647

When AI performs, what remains? An integrative review of generative AI and cognitive capital in individuals and organizations

Giuseppe Riva, Stefania La Rocca, Brenda K. Wiederhold, Andrea Gaggioli

原文摘要

Generative artificial intelligence is rapidly entering knowledge work, and its short-term productivity benefits are increasingly documented. Less is known about what happens, over time, to the knowledge, skills and judgment that remain in people and organizations. This integrative narrative review addresses that question through the construct of cognitive capital: the accumulated, renewable and depletable stock of knowledge, cognitive and metacognitive capabilities, and practices that enables an individual or an organization to learn, interpret information, exercise judgment, solve problems and adapt. We distinguish individual and organizational cognitive capital from the capability of the human-AI system, so that gains in joint performance and losses in human capability can be observed at the same time. Drawing on experimental, field and conceptual work, we propose four mechanisms through which interaction with AI affects cognitive capital: substitution of practice, scaffolding and feedback, metacognitive calibration, and organizational aggregation. Seven principles summarize the current evidence, including that assisted performance differs from retained competence, that the same technology can support or displace learning depending on design and use, and that individual gains can coexist with reduced collective diversity. For each mechanism we derive testable propositions, and we discuss five design levers for organizations as proposals to be validated rather than established practice. We conclude that cognitive capital offers a multilevel frame for governing AI adoption and outline a research agenda centered on longitudinal, multilevel measurement.

cs.HC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38644

CFKS: Continuum-Feature Kernel PDE Solvers

Vikas Dwivedi, Balaji Srinivasan, Monica Sigovan, Bruno Sixou

原文摘要

Neural-network-based PDE solvers require architectural choices, particularly the number of layers and neurons per layer. Fixing a single Gaussian radial basis function (RBF) feature layer and taking the number of features to the continuum limit removes the need to prescribe a finite feature count or select individual feature centers, thereby reducing representation arbitrariness. Motivated by this principle, we introduce Continuum-Feature Kernel Solver (CFKS), a deterministic framework for PDEs obtained by analytically marginalizing a bounded continuum of Gaussian RBF features. CFKS works directly with the resulting continuum-feature mean kernel and its operator-applied counterparts, parameterized by prescribed Gaussian widths and bounded center distributions. For linear PDEs, CFKS leads to symmetric operator-kernel collocation systems with null-space enforcement of physical constraints. Nonlinear PDEs are addressed through linearized initialization and nonlinear least-squares residual minimization using analytical kernel derivatives and Jacobians. Residual-guided collocation enrichment and sequential space--time-slab marching provide additional resolution strategies, while prescribed multiscale kernel refinement helps resolve localized nonlinear structures. Finite-feature experiments confirm convergence of empirical value and operator Gram matrices toward their continuum counterparts. Numerical studies include oscillatory and multiscale ODEs, irregular-domain Poisson and biharmonic problems, singular perturbations, transient transport equations, and viscous Burgers' equation. The results establish CFKS as a direct computational connection between finite Gaussian-RBF representations and continuum-feature kernel PDE solvers. Codes: https://github.com/vikas-dwivedi-2022/CFKS_Codes

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38642

Measuring the Inaccessible: Can AI Evaluate Accessibility in Heritage Tourism?

Sabrina Armenio, Manuele Leonelli

原文摘要

Accessibility assessment underpins the right to participate in heritage tourism, yet evaluation of archaeological sites remains artisanal: fieldwork does not scale, is often carried out without accessibility training, and is reported in forms that reach neither the sector nor disabled visitors. AI appears to offer a shortcut. We argue that assessment is measurement and inference under sparse, expert-mediated evidence: AI transforms how that evidence is captured and communicated, whereas evaluation, which turns evidence into defensible judgements, demands properties current generative systems lack. In a five-park field study in Spain and Italy, an AI desk audit scored only 66% of dimension-site combinations, could not observe embodied and organisational dimensions, and mirrored sites' online self-presentation. Simple Bayesian models instead quantify the confidence rankings deserve and calibrate desk evidence against fieldwork. We propose a separation of roles between AI and interpretable statistical evaluation as the basis for a reliable accessibility atlas.

cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38639

Enhanced image forensics through partial C2PA-based provenance information

Riccardo Ziglio, Eleonora Marchesini, Andrea Montibeller, Giulia Boato, Silvio Ranise, Cecilia Pasquini

原文摘要

Cryptographically verifiable C2PA-based Content Credentials (CCs) can be attached to freshly acquired or generated digital images but also to already existing ones with no previous provenance information, for instance after processing through trusted C2PA-enabled software tools. The latter case leads to images with so-called partial CCs, which capture only the last operations applied, while prior provenance remains unknown and can be investigated through signal forensics. This paper addresses the forensic analysis of such images, highlighting the opportunity to leverage the partial CCs as additional trusted knowledge to adapt forensic detectors towards the statistical characteristics of the image under analysis and mitigate potential distribution shifts. To this end, a two-step strategy is envisioned: (i) reconstructing the operations applied by the last signer through a structural analysis of the partial CCs; (ii) exploiting the obtained reconstruction to enhance the forensic detector of the analyst through an adaptation process. An empirical analysis on partial CCs produced by commercial C2PA-enabled software tools through different editing operations is carried out, providing evidence on the feasibility of the reconstruction in practical cases. An experimental case study on the forensic task of synthetic image detection is then presented, showing that the proposed strategy can significantly enhance the performance of state-of-the-art detectors on test images that are postprocessed via C2PA-enabled software tools after being generated/acquired.

cs.CR · cs.AI · cs.MM · eess.IV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38637

On-Policy Self-Distillation with Teacher Evolution

Shufan Shen, Zhongni Hou, Chao Bi, Yufei Zhang, Guojun Yin, Shuhui Wang

原文摘要

On-Policy Self-Distillation (OPSD), which aligns a student model's token-level distribution with that of its self-teacher prompted by privileged context, has emerged as a promising direction to mitigate reward sparsity in sequence-level post-training paradigms. However, OPSD often fails to achieve continuous performance gains during training. In this paper, we find that the model's limited self-teaching capability underlies this phenomenon by generating unreliable guidance on certain samples. To address this problem, we propose Teacher-Evolution Self-Distillation (TESD), which enables the self-teacher to generate rollouts and receive environmental feedback based on task correctness and context independence. First, using these rewards as training objectives, we perform teacher-oriented optimization to continuously enhance the model's self-teaching capability during distillation. Second, by estimating teacher guidance reliability from these rewards, we apply adaptive student-oriented optimization to down-weight samples with unreliable guidance. Extensive experiments across multiple datasets and model scales show that TESD consistently outperforms representative token-level and sequence-level methods, highlighting the necessity of improving supervision quality in OPSD.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38636

Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty

Atin Chowdhury, Piyush Joshi

原文摘要

Autonomous far-range rocket landing is a challenging control problem because navigation, descent-rate regulation, attitude management, and fuel use must be coordinated in the presence of uncertain atmospheric and vehicle dynamics. This paper presents a curriculum-driven proximal policy optimization (PPO) framework for three-dimensional rocket landing in a stochastic environment incorporating altitude-dependent aerodynamic drag, wind shear, temporally correlated turbulence, discrete gusts, uncertain propulsion and aerodynamic parameters, thrust-vector misalignment, engine lag, actuator-gain variation, noisy observations, and command latency. Learning is organised into far-range approach, soft descent, and integrated landing stages. Policy transfer, critic warm-up after reward changes, rehearsal of earlier tasks, and progressive expansion of weather severity are used to support learning across these coupled phases. Across 100,000 evaluation episodes, the policy achieves 96,656 successful landings, corresponding to a success rate of 96.656\% and a 95\% Wilson confidence interval of 96.543--96.766\%. Success decreases from 98.84\% under zero-disturbance conditions to 88.07\% in the highest weather-severity band. Successful touchdowns exhibit small miss distances and low residual horizontal and vertical velocities. An exploratory logistic-regression analysis identifies mean wind speed as the strongest measured correlate of success, with initial distance, initial altitude, initial vertical velocity, and wind-shear exponent also associated with outcomes. The results quantify both the effectiveness of the learned policy over the evaluated disturbance distribution and the degradation that occurs under severe compound atmospheric conditions.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.00391

Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps

Michael Vasilakakis, Dimitris K. Iakovidis

原文摘要

Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinical data is restricted due to privacy, ethical, or data availability limitations. Existing probabilistic and deep generative models often lack interpretability and fail to preserve clinically meaningful dependencies, limiting their suitability for safety-critical applications. This paper proposes a novel application of Fuzzy Cognitive Maps (FCMs) in a framework for synthetic medical tabular data generation with explicit causality and privacy preservation. Clinical features are described using linguistically interpretable fuzzy sets, and inter-feature dependencies are encoded as FCM edge weights computed from fuzzy set intersections. Synthetic patient records are generated by propagating randomly initialized linguistic activation vectors through the FCM until convergence, followed by defuzzification to produce clinically coherent numerical values. The approach natively handles mixed data types, and domain constraints common in health records. Experimental evaluation on UCI medical benchmark datasets demonstrates competitive performance under a Train-on-Synthetic-Test-on-Real (TSTR) protocol. The proposed method achieves accuracy of up to 0.81 and AUROC of up to 0.90 on the Heart Disease dataset, matching or exceeding TVAE and Gaussian Copula baselines while running exclusively on CPU. Fidelity metrics including KS Complement (up to 0.91) and Correlation Similarity (up to 0.95) confirm strong statistical coherence, and DCR Baseline Protection scores consistently exceed those of TVAE, confirming adequate privacy guarantees. These results demonstrate that causally grounded, interpretable fuzzy modeling offers a computationally efficient and transparent alternative to deep generative models for trustworthy synthetic data generation in CBMSs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38634

"Close enough?" An investigation into multiplication errors in LLMs

William Bolton, Bezawit Tilaye, Huw Day

原文摘要

Large language models (LLMs) frequently fail at multi-digit arithmetic, but the underlying mechanisms governing these failures remain poorly understood. While recent work demonstrates that addition errors follow a "noisy quantisation" model localised around carry boundaries, whether this framework generalises to multiplication remains an open question. In this work, we evaluate multiplication capabilities across several small base LLMs on a dataset of 16,991 problems spanning varied operand lengths. We show that multiplication errors do not conform to the addition-style noisy quantisation model. Instead, we uncover a novel error regime in small Qwen models: errors in lower-order columns predominantly preserve parity. Conversely, higher-order digit errors shift toward off-by-one carry failures. Our findings suggest that arithmetic computation in LLMs relies on distinct, multi-periodic internal representations where parity is tracked more robustly than exact digit identity, providing new mechanistic insights into numerical reasoning in transformers.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38632

The use of post-quantum cryptography in the automotive context

Mariana do Carmo Barata Gonçalves, Valderi Reis Quietinho Leithardt

原文摘要

This study comparatively evaluates post-quantum cryptography (PQC) in automotive communication scenarios, considering the threat posed by quantum algorithms such as Shor's and Grover's algorithms. The simulations use OMNeT++, Veins, INET, and SUMO on two hardware platforms and examine ML-KEM/CRYSTALS-Kyber, ML-DSA/CRYSTALS-Dilithium, and FALCON. ML-KEM and ML-DSA are finalized NIST standards, whereas FALCON is a NIST-selected candidate pending final standardization. The evaluation considers a rural V2V scenario and an urban V2X scenario supported by a roadside unit. Kyber exhibits low {key encapsulation mechanism (KEM)}\color{black} operation latency, Dilithium provides balanced signature performance, and FALCON has high key-generation and signing costs but efficient verification. The results are interpreted as a comparative assessment among the evaluated PQC schemes under the reported simulation conditions; {a conventional ECDSA/ECDH baseline measured in the same simulation setup is also reported for reference.}\color{black} The resulting dataset can support future studies of cryptographic selection in automotive systems.

cs.CR · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38631

Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries

Radha Yadav, Prasanna Devadiga, Peeyush Mishra, Apoorv Singh

原文摘要

Financial assistants answer questions that sound factual but depend on what the user leaves unsaid: what a data figure measures, which product variant is meant, and the investor's situation and the rules that apply. An assistant that ignores these can still answer with a real number from its data, one that answers a different question. We call this frame collapse. We study it in Indian mutual funds, where product variants and tax rules are formally defined, so the correct answer can be computed for every reading. One study tests each challenge. Given an ambiguously labelled figure, models used it, often under the user's label. Given every alternative labelled, they listed them all, but the layout decided which came first. Missing a fact about the investor, weaker agents assumed a default or an outdated tax rule; requiring the fact did not guarantee its use. Because such answers match their data, checks against the data pass them. An AI judge caught mislabelled figures only when told what each field means, and still passed answers that silently chose another reading. We show how these failures arise, not how often, and propose controls for financial assistants.

cs.AI · cs.CL · q-fin.GN

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38629

ItemCompass: Real-Time Edge-AI Wearable Vision for Tag-Free Domestic Object Retrieval

Tsz Lok Cheung, Jeff Kai-Tai Tang, Anthony Kong, Zackary P. T. Sin

原文摘要

Misplacing household objects disrupts daily routines, especially for elderly users. ItemCompass addresses this with a real-time, tag-free wearable AR system that builds a persistent digital twin of the home for natural language object retrieval. A custom eyewear node streams visual and inertial data to an edge server, where YOLOv11n detection, Siamese re-identification, and a Pedestrian Dead Reckoning engine log object locations as Spatial Anchors in InfluxDB. Voice queries are resolved by a local Faster-Whisper and Qwen2 LLM pipeline, delivering concise spoken and AR guidance on a heads-up display. Evaluation shows 0.40 m localization drift, 97.5% step precision, and mAP@0.5 of 0.874, with users rating Accuracy and Trust at 4.6/5.0. The system highlights always-on sensing, conversational spatial memory, and privacy-by-design for wearable computing.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38628

The Reality Gap in Automated Driving Systems Testing: Landscape, Challenges, and Research Directions

Stefano Carlo Lambertenghi, Oliver Weissl, Johannes Betz, Andrea Stocco

原文摘要

Simulation is essential for testing automated driving systems (ADS), but discrepancies between simulation and reality can undermine testing conclusions. It remains unclear which discrepancies the literature addresses and what evidence supports correspondence claims. We present a systematic mapping of 235 primary studies that measure or mitigate the reality gap in ADS testing, selected from 4,195 publications. We characterise objectives, targets, approaches, experimental setups, and evaluation evidence. Our classification distinguishes simulated and real-world execution across six ADS test components, separately for each approach and its evaluation reference. This distinguishes real-world information used to construct an approach from evidence used to evaluate its claims. Of the included studies, 76% address mitigation, primarily targeting scenario and actor realism and perception, while 94% report validation or measurement procedures. Only 61 studies report metrics from multiple families covering sensor/perception correspondence, ADS behaviour, vehicle dynamics, or safety outcomes; this coverage does not establish causal links between discrepancies and test verdicts. The synthesis highlights that real-world content and physical execution must be interpreted against the claim evaluated. The findings motivate claim-specific evaluation and component-level reporting to establish which discrepancies affect testing conclusions and when simulation evidence supports conclusions about real-world ADS behaviour.

cs.SE · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38624

SelectSep: Target-Selective Video Queries for Audio Source Separation

Suyeon Lee, Doyeop Kwak, Joon Son Chung

原文摘要

Video-queried sound separation (VQSS) aims to isolate a target sound from an audio mixture using its corresponding video as a query. However, scene-level video queries can become ambiguous when multiple sounding objects are visible, particularly when the target and interferer are semantically similar. We propose SelectSep, a target-selective VQSS framework that jointly uses text and a single click coordinate to specify the target source and instance without requiring segmentation at inference time. We adapt the visual encoder through target-feature distillation with text and click conditioning, and then fine-tune the separator using the adapted visual features. We also introduce an on-screen interference setting, where both the target and interferer are visible, to evaluate target selectivity. Experiments on standard benchmarks and the on-screen interference setting demonstrate consistent improvements in separation quality and target selectivity, particularly for mixtures containing semantically similar sources.

eess.AS · cs.MM · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38623

Cross-Primitive Consistency in Jev

Xu Liu, Guikun Chen, Kanzhi Wu, Wenguan Wang

原文摘要

Jev enables efficient decision-making with large language models (LLMs) through typed querying primitives, allowing the same semantic state to be expressed in different formats, such as binary and multiple-choice queries. However, the consistency of decisions across primitives has not been systematically evaluated. This work introduces PrimaCons, a four-axis benchmark for assessing cross-primitive consistency while preserving the semantics of the query. Evaluations across three Jev sizes reveal consistency violations across all four axes. Our analysis shows that these violations follow systematic patterns and that cross-primitive discrepancies predict decision failure with a ROC-AUC of 0.91. To mitigate these inconsistencies, we propose the Cross-Primitive Residual Calibrator (CPRC), which attaches a lightweight residual network to a frozen backbone and jointly optimizes predictive accuracy and cross-primitive consistency. Under a leave-one-domain-out protocol, CPRC reduces cross-primitive inconsistency by 58.57% and improves accuracy by +2.97%., demonstrating its effectiveness in both in-domain and out-of-domain settings. Our findings establish cross-primitive consistency as a key dimension for evaluating Jev and provide a practical approach to improving the reliability of its decisions. Code and benchmark is available at https://github.com/67L1/PrimaCons-CRPR.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38621

When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study

Gerardo Iuliano, Gabriele De Vito, Dario Di Nucci

原文摘要

Smart contracts are immutable programs deployed on blockchain platforms, where vulnerabilities can translate directly into financial loss. Among the techniques proposed for their detection, recent work has relied increasingly on Large Language Models (LLMs) guided by carefully crafted prompts. However, the evidence accumulated so far rests almost entirely on the dense Transformer architecture behind the GPT line and on model snapshots already scheduled for deprecation, leaving open the question of whether the reported behaviors reflect a general property of LLMs or an artifact of that specific design. This paper presents an extended replication of the empirical study by Chen et al. on LLM-based smart contract vulnerability detection. We replicate the original protocol on GPT-4 as a baseline, followed by a differentiated replication, executing the protocol on representative models based on Mixture-of-Experts and RNN-like designs, together with an attempted preliminary evaluation of State Space Models. The exact replication confirms the findings of Chen et al., including the high-recall, low-precision detection pattern they report on GPT-4. Nevertheless, the differentiated replication shows that this pattern does not transfer uniformly across the evaluated models. Those from the same architectural family may also exhibit different behaviors, indicating that architectural family alone is insufficient to predict the resulting detection profile. We observe the same qualitative dense-Transformer profile in both GPT-4 and Gemma-3, despite a gap of roughly two orders of magnitude in parameter counts, whereas two Mixture-of-Experts models from different lineages exhibit qualitatively divergent behaviors, indicating that architectural family alone is insufficient to predict the detection profile.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38620

Think Before You Act: Decision Gate for LLM Agents

Iftach Shoham, Yuval David, Offer Akrabi, Erez Bilgory, Ido Levy, Sami Marreed, Sergey Zeltyn, Segev Shlomov

原文摘要

LLM agents increasingly perform consequential actions through external tools, yet their proposed actions are often executed without independent verification of policy compliance or task completion. We introduce JevAct, a runtime verification framework that intercepts selected agent actions before execution and enables feedback-driven correction. JevAct compiles domain policies into executable state checks and structured questions evaluated by a prefill-only decision model, which produces probability-based judgments without relying on LLM generation. By combining deterministic verification of tool-state facts with probabilistic assessment of conversational context, the framework identifies potentially invalid actions and premature task termination, providing targeted feedback for bounded revision. JevAct operates independently of the underlying agent model and requires no modifications to its parameters or tools. We evaluate JevAct across eleven LLM agents on $τ^2$-bench Airline and Telecom tasks and BFCL. Results show improvements in agent reliability across multiple models and benchmarks, with particularly consistent gains on Telecom and BFCL, while performance on Airline is more mixed. Overall, these findings suggest that combining structured decision models with executable verification can improve the reliability of tool-using LLM agents.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38617

How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0

Liran Tal, Chris Liu, Charlotte Fereday, Sebastian Roth, Brian Clark

原文摘要

We ask what AI coding agents and AI security harnesses find that deterministic static application security testing (SAST) does not, and what they miss that SAST catches. VulnBench 2.0 is a benchmark of 108 hand-curated, attacker-reachable vulnerabilities in 20 open-source web applications in Go, JavaScript/TypeScript, Python and Java; 62 flow across more than one file. A finding is credited only if it locates the vulnerability's attacker-controlled source and its dangerous sink, each within two lines. We evaluate nine productized configurations under one blind protocol: the Snyk Code static analyzer, Claude Code's /security-review with three model and effort settings (one with the Snyk MCP server), Codex Security with GPT-5.6 Luna, Terra and Sol, and the DeepSec scanner with two model backends. Snyk Code reached 82.4% macro recall (89 of 108) and Claude Code with Opus 5 at xhigh effort 79.3% (85 of 108); they disagree on 28 vulnerabilities, split 16 to 12, too few to tell them apart. Neither engine was sufficient alone: together they reached 101 of 108, the ceiling of all seven comparable configurations combined, and the AI configurations also reported at least seven real vulnerabilities that the reference set did not contain and Snyk Code did not report. What an AI engine misses depends on its harness as much as on its model: without Claude Code's built-in review policy, the same model matched 16 instead of 9 of the 20 vulnerabilities in the classes that policy excludes or restricts (supplementary run on 19 of 20 applications); Codex Security with GPT-5.6 Sol located 80 vulnerabilities at file level but 34 at line level; DeepSec's model-free file selection kept a file from only 56 of the 108 flows. Coverage and cost were only loosely related. The harness, fixtures, reference sets and all run data are public.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38616

Order Maintenance in Worst-Case Constant Time, Verified

Denis Firsov

原文摘要

Order maintenance asks for a data structure that keeps a sequence of elements under insertions and deletions and tells which of two elements comes first. We give an algorithm, assembled from published components, that performs each operation in worst-case constant time, and verify it in Lean 4. The algorithm is a program for a random-access machine deeply embedded in Lean, whose interpreter counts every instruction. We prove that the program answers every query as a simple reference specification does, that each operation takes at most a fixed number of steps, independent of the number of elements and of the history, and that after $t$ operations no value it has computed has more than $O(\log t)$ bits, so it runs unchanged on a machine with words of that size. A verified translation that preserves step counts exactly connects the high-level proofs to the machine program, so the interpreter is the only cost model to trust. An unverified native implementation shows the algorithm's practical cost.

cs.LO · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.21320

Adaptive Allele-Haplotype Incidence Indexing for Pangenome Queries: Representation, Reconstruction, and Benchmarking

Roberto Garrone

原文摘要

Population-scale analysis of phased genetic variants requires both allele-carrier retrieval and ordered haplotype context. We examine H1, an adaptive allele-haplotype incidence-row index, and H2, a canonical edge-path representation derived from a fixed, nonoverlapping variant catalog. We prove conditional reconstruction of abstract H2 walks and distinguish this property from unrestricted equivalence to genomic variation graphs. A completed local notebook experiment used a chromosome 1 interval (20-22 Mb), 200 diploid individuals, 24,921 SNV/indel records, and 45 SVTYPE-annotated records. For 24,966 extracted nonreference rows across 400 haplotypes, the serialized H1 incidence-row files occupied 0.872 MiB with a simple adaptive layout and 1.126 MiB with a custom Roaring-like layout, versus 1.190 MiB for a bitmap-payload baseline; a whole-file Zstandard archive of the adaptive layout occupied 0.207 MiB. For a separately constructed nonoverlapping SNV projection containing 22,727 sites, indexed H2 edge sequences occupied 75,130,882 bytes in a raw format and 5,156,418 bytes with context-Huffman encoding (14.57-fold reduction). Carrier-equivalence and graph-adjacency assertions passed in the notebook, but full crosscallset phasing, nucleotide-level SV reconstruction, and comparison with production indexes remain unresolved. The measurements establish a restricted implementation feasibility result, not superior end-to-end pangenome compression.

q-bio.GN · cs.DB · cs.DS

查看论文
arXiv ↗PDF ↗