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 19:28 — 2026-11-16 19:28(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:2611.12527

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

Sang-Hoon Lee, Ha-Yeong Choi

原文摘要

This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TTS pipelines, WaveGen does not rely on separately trained or externally decoded intermediate representations, such as neural audio codecs, Mel-spectrogram vocoders, or VAE-based latent models. In addition, WaveGen performs internal text-speech alignment within a single model, eliminating the need for external alignment modules such as duration predictors. To preserve a truly end-to-end formulation, our framework further avoids dependence on self-supervised representations, such as BERT-based text embeddings and Wav2Vec 2.0-based semantic representations, as well as semantic distillation methods for training optimization. To achieve this, we carefully design Spectral Forcing, a model architecture with disentangled diffusion heads, and a training objective based on a multi-scale spectral $v$-loss. We further validate the scalability of end-to-end TTS models by scaling the model size from 0.1B to 0.6B parameters. Using a single architecture, open-source data, and one-stage training, without external modules such as duration predictor or REPA, WaveGen demonstrates fully end-to-end waveform generation achieving state-of-the-art performance on the Emilia training dataset. In particular, WaveGen achieves a WER of 1.47 and a SIM of 0.75 on the Seed-en benchmark. Source code and checkpoints are available at https://github.com/sh-lee-prml/WaveGen

cs.SD · cs.AI · eess.AS · eess.SP

新论文 · v1arXiv:2611.12526

Galilean Robots, Aristotelian Sensors: Joint Spatiotemporal Trajectory Estimation and Extrinsic Calibration

Abhishek Goudar, Jonathan Kelly, Timothy D. Barfoot

原文摘要

Multi-sensor state estimation requires accurate spatial and temporal calibration between heterogeneous sensors. Existing spatiotemporal calibration methods typically represent sensor extrinsic parameters as a rigid-body transformation together with a scalar temporal offset, causing the spatial and temporal parameters to enter the estimation problem through separate mechanisms. While the spatial transformation composes directly with the robot pose, accounting for the temporal offset requires evaluating the trajectory at a shifted time, typically through motion compensation, interpolation, or a continuous-time trajectory representation. In this work, we formulate joint trajectory estimation and spatiotemporal calibration using the special Galilean group for the robot trajectory and the Aristotelian subgroup for sensor extrinsics. This representation incorporates the coupling between motion and temporal offset directly through the group structure, avoiding the need for a separately parameterized continuous-time trajectory. We develop twist- and IMU-driven motion priors, accommodate both ideal and non-ideal clocks, and evaluate the framework with camera, position, and range measurements. Simulated and real experiments demonstrate calibration and trajectory-estimation performance comparable to established methods across heterogeneous sensor configurations. Our simplified framework therefore offers a quality-of-life improvement over existing methods without compromising performance.

cs.RO

新论文 · v1arXiv:2611.12524

EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth

Jens Parslov, Marco Schouten, Dim P. Papadopoulos

原文摘要

Vision-language models (VLMs) are increasingly used as automated judges for image-editing benchmarks, yet their reliability is poorly understood. Auditing these judges is difficult because real edited images lack controlled ground truth and entangle the requested changes with model artefacts, unintended side effects, and ambiguous degrees of success. In this paper, we introduce EditJudge-Bench, a diagnostic benchmark of 1,382 synthetic before/after image pairs rendered in Blender, with edits parameterised across nine categories derived from real user requests and exact ground truth from known 3D scene parameters. Because every edit is generated by a known intervention on a controlled scene, EditJudge-Bench evaluates VLM judges as binary verifiers of whether an instruction was correctly executed, isolating judge perception from editor quality. Across 25 judge configurations, we find substantial reliability gaps: (a) the widely adopted VIEScore template reaches only 69.0% AUROC with GPT-4o; (b) fine-tuned judges score 51.7-66.3%; spatial edits such as rotation and shape remain challenging; (c) prompt-formatting choices like image-text ordering shift performance by up to 14.1 points. Despite using only synthetic data, judge rankings on EditJudge-Bench correlate strongly with two real-image human-preference benchmarks ($ρ$=0.95 and $ρ$=0.71), indicating that controlled audits surface failure modes relevant to real evaluation.

cs.CV

新论文 · v1arXiv:2611.12521

Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision Models

Julien Delaunay

原文摘要

"System 1" decision models (pioneered by TypeSafe AI's Jev) replace autoregressive text generation with a single forward pass returning typed probability distributions over declared schemas (Choice, Score, Noul). While deployed for low-latency routing and automated triage, their statistical calibration and post-hoc explainability remain uncharacterized. We introduce an open, deterministic audit benchmark evaluating System 1 decision models across calibration under label-preserving perturbations, cross-question interference, and post-hoc attribution faithfulness. Evaluating five open-weight models (0.8B to 27B) alongside generative System 2 baselines -- both single-token logprob scoring and structured JSON/CoT decoding -- across NLI (e-SNLI), adversarial syntactic shortcuts (HANS), synthetic clinical triage (N=900), prompt injection defense (Tensor Trust, N=250), and an 86-case logic-gate trigger suite yields five findings: (1) provider confidence is an exact closed-form dispersion transform (1 - H(p)/ln K on sub-10B models; normalized margin on Clef-27B) rather than empirical accuracy; (2) bundling multiple questions in one request induces directional cross-question interference (11.7% to 22.4% binary flips on Tev1-0.8B, vs. 0.1% to 0.2% on Tev1-4B); (3) System 1 models with >= 4B parameters are faster and better calibrated under syntactic shifts (ECE_w = 0.030 to 0.087) than logprob (0.144) and JSON (0.378) baselines; (4) for prompt-injection defense (N=250), >= 4B models achieve 0.988 to 0.998 AUROC with up to 95.2% recall and 0.0% false alarms at 48 to 60 ms; and (5) single-pass inference makes 512-coalition XAI interactive (1.3 to 3.2 s/input), while KernelSHAP with a logit link (S1-SHAP) mitigates softmax saturation on disjunctive OR gates (89.3% to 100.0% gate recovery vs. 57.1% to 82.1% in prob space; p_adj = 0.004).

cs.LG · cs.CL

版本更新 · v4arXiv:2605.30732

How To Track Qubits Through Space and Time (Or: Sailing in a Quantum Boat)

James Bartusek, Zikuan Huang, Leo Orshansky, Henry Yuen

原文摘要

While quantum position verification aims to certify a prover's location using quantum information, existing security definitions only guarantee that part of the successful adversarial party is in the claimed location. This leaves open the possibility that a distributed team of adversaries can jointly simulate a prover in a way that defeats the intended meaning of `being at a location' in position-based cryptography. We introduce stronger notions of position verification that we call quantum localization, which requires that there is a specified, unclonable state at the verified spacetime point-and that this state can be found nowhere else. We show that quantum localization leads naturally to a meaningful notion of trajectory verification, in which quantum information is verifiably tracked through space and time. We construct quantum localization and trajectory verification protocols using quantum anchor states, which generalize coset states from unclonable cryptography. The security of our schemes is proven in the classical oracle (i.e. ideal obfuscation) model, which can be heuristically instantiated in the plain model using post-quantum indistinguishability obfuscation. We also introduce and instantiate the concept of functionality localization, which guarantees that the adversary has the ability to compute a secret function at the verified spacetime point, and this function cannot be computed anywhere else. This raises the intriguing possibility of localizing computational capabilities in space and time. More broadly, we believe our notions of quantum localization and subsequent feasibility results provide stronger foundations for position-based cryptography. At a conceptual level, our results also explore the tight link between two fundamental notions in physics-location and information-thus serving as a natural foundation for cryptographic capabilities tied to physical spacetime.

quant-ph · cs.CR

版本更新 · v2arXiv:2604.10009

Towards Multi-Source Domain Generalization for Sleep Staging with Noisy Labels

Kening Wang, Di Wen, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiale Wei, Kailun Yang, Rainer Stiefelhagen 等 9 位作者

原文摘要

Automatic sleep staging is a multimodal learning problem involving heterogeneous physiological signals such as EEG and EOG, which often suffer from domain shifts across institutions, devices, and populations. In practice, these data are also affected by noisy annotations, yet label-noise-robust multi-source domain generalization remains underexplored. We present the first benchmark for Noisy Labels in Multi-Source Domain-Generalized Sleep Staging (NL-DGSS) and show that existing noisy-label learning methods degrade substantially when domain shifts and label noise coexist. To address this challenge, we propose FF-TRUST, a domain-invariant multimodal sleep staging framework with Joint Time-Frequency Early Learning Regularization (JTF-ELR). By jointly exploiting temporal and spectral consistency together with confidence-diversity regularization, FF-TRUST improves robustness under noisy supervision. Experiments on five public datasets demonstrate consistent state-of-the-art performance under diverse symmetric and asymmetric noise settings.

cs.LG · cs.CV · cs.RO

新论文 · v1arXiv:2611.12512

Certifying the Error-Detection Value of Functional Dependencies without Ground Truth

Xiaolong Wan, Xixian Han

原文摘要

Functional dependencies are used to flag erroneous cells, but without error labels the value of these flags is unknown. Dependency strength cannot settle it, because identical data and flags can have positive value in one clean state and negative value in another. We treat this value as partially identified and certify a fixed detector when its value is positive in every clean state compatible with the observation under an error model and budget. The largest such budget is the certification radius. For a detector that flags departures from the unique mode of each class, the worst case reduces to a 0/1 knapsack over class flips, yielding sharp bounds on true positives and the exact radius in polynomial time. Allowing bounded legitimate exceptions in the clean data, we derive an exact threshold for the existence of a positive certificate and compute the radius with the same knapsack. Across five relations and 21,981 candidate dependencies, rules with nearly equal $g_3$ and flag rate can have certification margins differing tenfold. Error injection confirms sound certification and shows that, at equal error counts, changing the organization of errors reverses certification outcomes for every tested rule.

cs.DB

新论文 · v1arXiv:2611.12509

UniHam: A Large-Scale SOC-Complete Dataset and Benchmark for Hamiltonian Learning in Materials

Yuewen Huang, Pin Chen, Yutong Lu

原文摘要

Accurate prediction of electronic Hamiltonians would enable broad property inference while avoiding the high computational cost of Density Functional Theory (DFT). However, progress toward general-purpose materials foundation models is limited by a data bottleneck: existing Hamiltonian datasets are typically small, lack structural diversity, and often omit essential relativistic physics such as spin--orbit coupling (SOC). We therefore construct UniHam, a large-scale Hamiltonian dataset and benchmark suite comprising 100,000+ DFT-computed complex-valued Hermitian Hamiltonians with full SOC, covering 72 elements and a wide range of crystal geometries and symmetries (spanning diverse lattice types and space-group families). Building on UniHam, we benchmark two representative state-of-the-art models under a standardized protocol and introduce complementary evaluation metrics that jointly assess three dimensions: (i) Hamiltonian reconstruction accuracy, (ii) out-of-distribution (OOD) generalization across composition/symmetry shifts, and (iii) the ability to support downstream property prediction from the predicted Hamiltonians. Experiments on UniHam demonstrate that the proposed benchmark and metrics effectively differentiate model capabilities, revealing intrinsic SOC- and element-dependent failure modes, large variations in compositional OOD robustness, and the necessity of spectral-level evaluation to assess whether Hamiltonian predictions reliably support downstream electronic-structure properties. Overall, UniHam provides a reproducible, SOC-complete benchmark that can sharpen model comparisons and accelerate the development of next-generation foundation models for quantum materials.

cs.LG · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.12508

MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection

Ahmed Y. Radwan, Shaina Raza

原文摘要

Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43\%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99\% AUROC on GenVideo and 75.50\% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: https://vectorinstitute.github.io/mars/ Github: https://github.com/VectorInstitute/mars

cs.CV · cs.AI

版本更新 · v3arXiv:2608.12206

Exponential Lower Bounds for Horn Amalgamation

Jakub Rydval

原文摘要

The amalgamation decision problem asks whether the finite models of a given universal first-order sentence have the amalgamation property. We prove that this problem is ExpTime-hard for universal Horn sentences of maximum relation arity three, and 2ExpTime-hard when the arity is unbounded, thereby strengthening the previous best lower bounds for universal Horn sentences. The first reduction simulates runs of nondeterministic tree automata using a single ternary relation and unary and binary auxiliary relations. The second simulates finite winning strategies in an exponential corridor game. As a secondary contribution, we prove that deciding the winner remains 2ExpTime-complete for the game normal form used in our reduction, in which each move label determines a unique legal successor from every non-winning legal row.

cs.LO · math.LO

版本更新 · v3arXiv:2610.04510

ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching

Prashant Pandey, Devineni Sri Venkatraya Chowdary, Brejesh Lall

原文摘要

Diffusion models for structured scientific generation must produce samples satisfying hard geometric constraints imposed by physics, chemistry, or biology, yet inference in these settings is prohibitively slow, demanding hundreds to thousands of neural-function evaluations per sample. We unify eight state-of-the-art models spanning medical volumetrics, molecular conformations, protein backbone design, crystal structure prediction, and multi-view 3D scenes under a single abstraction, Constraint-Manifold Diffusion Models (CMDMs), in which the target distribution is supported on a manifold defined by an externally specified constraint map. All existing acceleration families fail on this class: quantization exhausts memory on high-dimensional volumetric operators; pruning breaks constraint fidelity; fast ODE solvers allow trajectories to drift off the constraint manifold; and feature-caching heuristics are blind to constraint geometry, inducing mode confusion in the high-noise regime. We introduce ManifoldCache, the first training-free, data-free accelerator designed from first principles for CMDMs. The key insight is that the conditional score decomposes orthogonally into a normal component, which enforces constraint satisfaction, and a tangential component, which navigates within the manifold. Exploiting this structure, we prove that the noise-schedule midpoint is a sharp safe-caching boundary: caching before it incurs provably bounded error, while caching after it guarantees a strictly positive fraction of trajectories suffer mode confusion, a gap that persists up to the boundary. We further prove that deeper network blocks admit provably larger certified cache strides within the safe phase, as a consequence of the score decomposition propagating through block Jacobians. The resulting schedule requires no calibration data, along with zero training overhead.

cs.AI · cs.LG

版本更新 · v3arXiv:2604.27644

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning

Chengcao Yang

原文摘要

We propose a paradigm shift toward open-ended curriculum self-play: rather than learning to answer on a fixed prompt set, a unified policy learns to question: generating verifiable problems, solving them, and turning verifier feedback into self-improvement. We introduce ANCORA, in which the policy alternates between a Proposer that synthesizes novel specifications and a Solver that produces verified solutions, anchored by three mechanisms: a two-level group-relative update coupling Proposer advantages across specifications with Solver advantages across solution attempts; iterative self-distilled SFT projecting the base model onto its valid-output manifold before RL; and a UCB-guided Curriculum DAG whose policy-induced problem set can provably expand under self-composition. Without these stabilizers, sparse verifier feedback drives Proposer collapse even under MLRL-aligned rewards; with them, ANCORA bootstraps a verifiable curriculum from curated seeds. Instantiated in Verus, ANCORA lifts Dafny2Verus pass@1 from a 26.6% SFT baseline to 81.5% in test-time training (TTT, 0-shot), outperforming PSV self-play (1-shot) by 15.8 points; in a transfer setting, training from Dafny2Verus seeds yields 36.2% and 17.2% pass@1 on MBPP and HumanEval.

cs.LG · cs.AI · cs.PL

新论文 · v1arXiv:2611.12501

Text Grouping Changes Completion-Time Comparisons in Long-Form Simultaneous Speech Translation

Hieu Minh Truong, Dung D. Le

原文摘要

Does grouping translation updates before speech synthesis change the measured completion gap between two translators? We compare StreamAtt with its fixed-audio-history baseline on ten English-German talks. For each translation, we keep the intended text and its availability times fixed and vary how updates are grouped for synthesis. Four-second grouping increases StreamAtt's mean completion lead from 106.6 to 229.1 seconds with XTTS-v2, but reduces it from 169.5 to 146.5 seconds with Piper. Both produce shorter audio; different changes in playback idle account for the opposite effects. These directions recur on a separately selected twenty-talk panel. In continuing CosyVoice 3 sessions, grouping instead leaves paired audio unchanged and delays completion on nineteen of twenty blocks. A speech-timing comparison therefore needs to specify how text enters synthesis, not just which synthesizer is used. Recognition and automatic word timing describe the outputs, but do not establish translation accuracy or intelligibility.

cs.CL · cs.AI

新论文 · v1arXiv:2611.12493

Textraction: Unified Text-Guided Speaker Extraction and Enhancement for Single- and Multi-Channel Audio

Aviad Eisenberg, Sharon Gannot, Shlomo E. Chazan

原文摘要

We present Textraction, a text-guided speaker extraction framework that enables the selective extraction of desired speakers or noise sources from an audio mixture using only natural-language descriptions. The proposed method operates within a single unified model that supports both single-channel and multi-channel inputs and it allows conditioning on either semantic textual descriptions of the target source or on its spatial description. Dedicated single- and multi-channel encoders feed a shared stack of time--frequency transformer blocks, which is conditioned on the prompt and on the recording configuration in every block through cross-attention and estimates the target directly from the mixture in one forward pass, without a separation stage or a source-selection stage. The system can extract an arbitrary subset of entities from a mixture, assuming up to two simultaneously active speakers and two noise sources, and interprets prompts specifying which entities to keep, which to remove, or both. In addition, we show that the framework naturally applies to a speech-enhancement setting, in which a single target speaker is present alongside background noise. To circumvent the application of computationally costly large language models used in prior work, we introduce a lightweight, task-adapted text encoder obtained by contrastively fine-tuning a compact text-retrieval model, which learns to be sensitive to instruction polarity (e.g., keep vs. remove) while remaining robust to paraphrasing. Experiments across attribute-based extraction, spatially guided extraction, and speech enhancement show that the proposed approach effectively isolates the desired entities under various acoustic and spatial conditions, and matches or surpasses dedicated spatial-extraction and enhancement baselines while offering substantially greater flexibility.

cs.SD

版本更新 · v2arXiv:2605.10458

QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space

Pablo Martínez Crespo, Stefano Ribes, Richard Beckmann, Marisa Gliege, Santiago Miret, Robert S. Jordan, Vijay Kris Narasimhan, Martin Rahm 等 9 位作者

原文摘要

Atomic properties such as partial charges or multipoles encode chemically meaningful information that can inform downstream molecular property prediction, but their evaluation as machine learning targets has been complicated by the absence of a principled out-of-distribution evaluation protocol at the atomic level. In this work, we propose a held-out evaluation protocol that clusters atomic environments by SOAP descriptors and computes metrics accounting only for cluster labels unseen during training. Following this procedure, we use 5$\times$5 cross-validation and Tukey's HSD to run a statistically rigorous comparison of E(3)-equivariant against non-equivariant, rotationally augmented models for predicting electron populations and multipoles of H, C, N, and O atoms. Building on our results, we introduce the Quantum Topological Neural Network (QT-Net), a rotationally augmented, non-equivariant graph neural network. We show that QT-Net can be used to infer properties of atoms in molecules from QM9 outside our training set, and that the atomic environments seen during training strongly affect the performance of molecular property prediction tasks. To further validate the framework, molecular dipole moments computed from QT-Net's per-atom outputs recover the ground-truth values reported in QM9. We release all code and data, including a JAX implementation of QT-Net.

cs.LG · cond-mat.mtrl-sci · physics.chem-ph

版本更新 · v2arXiv:2606.25480

Rate-Aware Quantum-Inspired Trajectory Learning for Interference-Limited Multi-UAV Networks

Khaoula Khaled, Muhammad Afaq, Zeeshan Kaleem

原文摘要

Placing unmanned aerial vehicles (UAVs) as aerial base stations is non-convex and combinatorial, so practical methods first discretize the continuous airspace into a finite set of candidate positions---a uniform grid or clustering centroids---and optimize over that set. Built from Euclidean distance alone, the candidate set is channel-blind: it ignores line-of-sight probability and the co-channel interference that limits achievable rate under full frequency reuse. No optimizer can select a position the candidate set omits, so good locations the geometry missed are lost before the search begins. We propose Rate-Aware Quantum-Assisted Graph Condensation (RA-QAGC), a two-stage framework that makes the candidate set itself the object of optimization. The first stage constructs it by annealing a cost that embeds tier-weighted achievable rate, mean co-channel interference, and an explicit minimum-rate penalty, yielding a compact, mobility-feasible waypoint graph. The second stage learns trajectories over that graph with decentralized independent Q-learning agents, replacing a centralized joint-action table with one compact table per UAV. RA-QAGC improves priority-tier throughput by 21--54\% over seven baselines, including recent graph-neural and deep Q-network schemes, at no significant cost in aggregate throughput, and the margin widens as the fleet densifies. We additionally examine the quantum-inspired acceptance rule that recent aerial-networking work advocates, and report that its tunnelling floor confers no measurable advantage over classical simulated annealing at any fleet size tested, while annealing itself clearly outperforms greedy and random placement.

cs.MA · cs.AI

新论文 · v1arXiv:2611.12487

Detecting AI-Authored Text in Authentic Student Writing: Evidence from PISA 2025

Nils-Jonathan Schaller, Thorben Jansen, Olaf Köller, Andrea Horbach

原文摘要

AI-text detectors reach near-perfect scores in evaluations that contrast fully human-written texts with texts generated from researcher-designed prompts. In authentic student writing, however, AI use is voluntary and often partial. We study this setting with the PISA 2025 FLA dataset, in which 15-year-olds in Germany wrote English argumentative essays with and without access to a gpt-4o-mini-based chatbot. Keystroke, clipboard and chat logs let us trace every character of the final essay to its origin. From this provenance, we derive text- and sentence-level labels for human-written, AI-generated and mixed text, and for text written after chatbot use without traceable AI material. We evaluate a feature-based detector and a classifier on frozen Llama-3.1-8B embeddings, both adapted from top-ranked shared-task systems. Both separate AI from human text reliably (macro-F1 up to 0.96 for texts and 0.95 for sentences), independently of spelling errors. The feature-based detector, however, relies on lexical complexity, which a simple student-style rewriting prompt removes (AI recall 0.92 $\to$ 0.60 with gpt-4o-mini, 0.41 with Qwen3). The embedding-based detector stays robust for whole texts (AI recall $\geq$ 0.94) but not for single sentences (AI recall as low as 0.59). Mixed text falls between the two classes, and text without traceable AI material is classified as human-written in about 95\% of texts.

cs.CL

版本更新 · v3arXiv:2604.22391

Conformalized Super Learner

Zhanli Wu, Fabrizio Leisen, Miguel-Angel Luque-Fernandez, F. Javier Rubio

原文摘要

The Super Learner (SL) is a widely used ensemble method that combines point predictions from a library of learners based on their predictive performance. Interval predictions are of considerable practical interest because they allow uncertainty in predictions produced by an individual learner or an ensemble to be quantified. Several methods have been proposed for constructing interval predictions based on the SL, however, these approaches are typically justified using asymptotic arguments or rely on computationally intensive procedures such as the bootstrap. Conformal prediction (CP) is a machine learning framework for constructing prediction intervals with finite-sample and asymptotic coverage guarantees under mild conditions. We propose coupling CP with the SL through a natural construction that mirrors the original SL framework, using individual learner weights and combining learner-specific conformal prediction sets via a weighted majority vote. We characterize the properties of the resulting SL-based prediction intervals for continuous outcomes. We cover settings under exchangeability, and data-generating mechanisms exhibiting heteroscedasticity, sparsity, and other forms of distributional heterogeneity. A comprehensive simulation study shows that the conformalized SL achieves valid finite-sample coverage with competitive performance relative to the true data-generating mechanism. We present an application of this methodology to predict creatinine levels using socio-demographic, biometric, and laboratory measurements. This example demonstrates the benefits of an ensemble with carefully selected learners designed to capture key aspects of complex regression functions, including non-linear effects, interactions, sparsity, heteroscedasticity, and robustness to outliers.

stat.ML · cs.LG · stat.CO · stat.ME

版本更新 · v2arXiv:2610.27908

Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing

Diego Miguel Lozano, Erik Derner, Juan Antonio Pérez-Ortiz, Nuria Oliver

原文摘要

Negation remains a persistent challenge for language models across NLP tasks and modalities. We show that this weakness can undermine LLM safety guardrails through a structural vulnerability we term polarity blindness: the failure to recognize harmful intent after polarity-altering linguistic transformations. We study two forms of polarity inversion: grammatical negation and antonym replacement, and use synonym replacement as a polarity-preserving control. We further test whether an adversarial textual wrapper amplifies these failures. Using a 260-prompt benchmark across 10 state-of-the-art LLMs and 3 languages (English, Spanish, Czech), stratified by harmfulness potential and evaluated on a validated 0-5 harm scale, we find that polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable model. The effect persists across typologically differing negation systems, suggesting that polarity blindness reflects a broader limitation in semantic robustness rather than a language- or grammar-specific failure.

cs.CL · cs.AI

新论文 · v1arXiv:2611.12486

Optimizing the Steady-State Travel Time of Nash Flows over Time with Capacity Increases

Niklas Dahlmeier, Paul Paschmanns, Laura Ritter, Ruben Skorupinski

原文摘要

We study budgeted capacity augmentation for single-source single-sink \NFOTs under constant inflow $u_0$. The goal is to increase capacities on arcs subject to a global budget constraint in order to minimize the steady-state travel time in the network. We show that this problem is weakly NP-hard on series-parallel networks and provide an exact pseudopolynomial algorithm as well as a fully polynomial algorithm that attains the optimum travel time for budget $B$ while spending at most $B + \varepsilon\cdot\max\{B,u_0\}$. On general networks the problem becomes strongly NP-hard. Moreover, unless $\text{P} = \text{NP}$, for every fixed $\varepsilon \in (0,1)$, no polynomial-time algorithm can achieve the optimal steady-state travel time while exceeding the budget by at most a factor of $n^{1-\varepsilon}$. Lastly, we give structural properties about steady-state travel time under varying arc capacities. We identify capacity thresholds determined by subsets of $s$-$t$-cuts and show that the travel time is constant in the interior of the cells resulting from the corresponding hyperplane arrangement.

cs.DS

新论文 · v1arXiv:2611.12485

Resetting-based designated information distribution

Xiaojuan Ma, Yan Wang, Indranil Gupta

原文摘要

For a network of $n$ nodes under random gossip dynamics, we show that by introducing the additional resetting mechanism (with rate $β$) to a designated subset of $r$ nodes, the expected sum of all node values is asymptotically equal to $\tfrac{n}{r}$ times the sum of the initial values of the $r$ designated nodes, in the small-$β$ and long-time limit. We also analyze the convergence speed to this asymptotic state and provide an approximate high-probability confidence interval for the expected sum at finite time $t$ and finite $β$. Operationally, we propose a protocol that distributes the initial node values over the designated subset evenly (up to a prescribed precision), by appropriately turning on and off the resetting dynamics. Our work not only offers insights into classical problems such as distributed computing and network control, but also serves as a potential foundation for designing quantum algorithms that prepare desired states in quantum networks using only local operations.

cs.DC · cond-mat.stat-mech · cs.SI

版本更新 · v3arXiv:2602.22600

Transformers converge to invariant algorithmic cores

Joshua S. Schiffman

原文摘要

Training selects for behavior, not circuitry: many weight configurations can implement the same function. Studying any single trained neural network thus risks describing accidents of one training run rather than the computation itself. This work shifts focus from what transformers happen to do to what they must do by extracting algorithmic cores, compact subspaces that are necessary and sufficient for a task and that recur across independently trained models. Here, Algorithmic Core Extraction (ACE) is introduced to isolate these subspaces, causally validate them, and recover the algorithms they implement, from synthetic tasks to large pretrained models. Markov-chain transformers embed 3D cores in nearly orthogonal subspaces yet recover identical transition spectra. Modular-addition transformers form compact cyclic cores at grokking that later inflate under continued regularization, redundantly distributing the same computation across many functionally equivalent modes. This functional redundancy accelerates the transition from memorization to generalization, yielding an inverse scaling law for grokking time. In six language models spanning two orders of magnitude in scale (GPT-2 Small/Medium/Large, LLaMA-3.1, Gemma-2, and Qwen2.5), subject-verb agreement is governed by a single, steerable axis that aligns across architectures. Flipping this axis inverts grammatical number throughout open-ended generation. For indirect object identification, a multi-step task, the same six models route computation through compact multi-dimensional cores at two sites, linked by a linear operator that transfers across model families. Together these results suggest that beneath the apparent complexity of trained transformers lies a simpler, shared computational structure, and that targeting invariants rather than parameterizations may offer a more tractable path to mechanistic understanding and control.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14568

Deep learning-guided discovery reveals the diversity and mutational potential of environmental beta-lactamases

Liangjun Ge, Qiandi Gao, Haiming Xu, Zhiwei Qin, Heqian Zhang

原文摘要

Beta-lactamases are a major mechanism of bacterial resistance to beta-lactam antibiotics; however, their functional diversity and mutational potential in environmental microbial communities remain partially understood. This study aimed to characterize environmental beta-lactamase diversity and investigate how sequence variation influences antibiotic resistance. By integrating protein language model (PLMs) with ensemble learning, we identified more than 46,000 putative beta-lactamases across all four Ambler classes from environmental metagenomes, widely distributed across diverse habitats, with distinct habitat-associated class compositions. The candidates sharing approximately 30% sequence identity with known beta-lactamases conferred resistance to multiple beta-lactam antibiotics when expressed in Escherichia coli. Combining inverse folding model with PLMs further identified mutations that altered resistance profiles, including substitutions that increased resistance to carbapenems. Predicted high-fitness sites exhibited greater natural sequence variability overall, with higher variability in wastewater-derived than ocean-derived enzymes. These findings reveal undercharacterized beta-lactamase diversity and substantial mutational flexibility in environmental microbiomes, providing a basis for investigating their potential contribution to the diversification of antibiotic resistance.

q-bio.GN · cs.AI

新论文 · v1arXiv:2611.12480

Reference-Dependent Utility Optimization for Goal-Oriented Communication Systems

Symeon Vaidanis, Photios A. Stavrou, Marios Kountouris

原文摘要

Traditional communication resource allocation optimizes operational metrics such as rate, latency, energy efficiency, and reliability. Motivated by goal-oriented semantic communication, we develop a generalized allocation framework that transforms operational rewards through reference-dependent user utilities and evaluates them via expected utility, cumulative prospect theory (CPT), or related decision criteria. The formulation separates operational rewards, user-side valuations, and system-level decision criteria under uncertainty. We characterize utilities incorporating QoS/service reference levels, deficit sensitivity, post-reference saturation, and loss aversion. Weighted sum-reward maximization, proportional fairness, $α$-fairness, and stochastic expected utility maximization emerge as exact special cases, while soft QoS-aware allocation follows from a deficit-penalty generalization. For deterministic orthogonal systems, we derive utility-weighted marginal-reward KKT conditions characterizing global optimality under concave composite objectives. For nonorthogonal and stochastic systems, we develop successive convex approximation (SCA) algorithms and establish stationary-point guarantees under explicit smooth and composite nonsmooth assumptions, including a CPT branch-stationarity result under eventual nondegenerate ordering identification. For globally solved penalized problems, we derive an $O(1/λ)$ bound on excess aggregate soft-QoS deficit, and on the deficit itself whenever a QoS-feasible allocation exists. Additionally, we establish an $O(1/ε^2)$ outer iteration bound for the smooth fixed-step SCA best-response residual. Numerical examples demonstrate how reference points, marginal utility slopes, channel quality, and resource budgets influence active users and allocation policies.

cs.IT · cs.NI · eess.SP

版本更新 · v4arXiv:2502.03503

Why Transformers Struggle with Distribution-Independent In-Context Learning

Omar Naim, Jerome Bolte, Nicholas Asher

原文摘要

With in-context learning (ICL), transformer models adapt to new tasks from illustrative examples at inference time without updating their parameters. A common interpretation is that transformers implement implicit learning algorithms in their forward pass. We test this interpretation and ICL capability under distribution shift in noiseless polynomial regression, where the context uniquely determines the target function. Models that are near-perfect in distribution exhibit sharp performance degradation under shifts in the input or target-function distribution. This behavior persists across polynomial degrees and multiple training interventions, and in higher-dimensional nonlinear regression. We identify two architectural mechanisms that explain this breakdown: output saturation at finite boundary values linked to final normalization, and attention concentration on a small subset of the context, which can limit context-dependent adaptation required for ICL. Controlled experiments, architectural ablations, targeted interventions, and theoretical analysis provide strong evidence for both mechanisms and their consequence: strong in-distribution ICL does not imply distribution-independent ICL, which calls for caution when using ICL instead of explicit retraining or adaptation under distribution shift.

stat.ML · cs.AI · cs.LG

版本更新 · v2arXiv:2511.18163

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Pasquale De Marinis, Uzay Kaymak, Rogier Brussee, Gennaro Vessio, Giovanna Castellano

原文摘要

Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. Explainable AI has matured on standard computer vision tasks, but not on FSS, where an explanation would tell a practitioner which support pixels the prediction rested on and which examples to provide next. We argue that matching-based FSS models are interpretable by design: their query-support similarity scores, once normalized and processed, attribute the prediction to individual support pixels. Our approach, Affinity Explainer (AffEx), makes this intrinsic interpretability explicit by extracting attribution maps directly from matching scores at multiple feature levels, without requiring gradients or external perturbations. We extend the standard causal metrics for evaluating explanations to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Experiments on two FSS benchmarks, covering seven architectures that range from classical matching-based models to recent pipelines built on vision foundation models (DINOv2/v3, SAM, SAM2) and a prototype-based head, show that AffEx outperforms adapted standard attribution methods at nearly every evaluation point, and that the gain comes from the matching mechanism itself. On pipelines whose segmentation stage transforms the matching output, the same evaluation doubles as a diagnostic of where the decision is made, and on the prototype-based head AffEx subsumes the prototype-style read-out as a special case. Qualitatively, the attribution maps expose how each architecture resolves the support set, and we show how they guide model diagnosis. Code is available at https://github.com/pasqualedem/AffinityExplainer.

cs.CV

新论文 · v1arXiv:2611.12478

AuDiR: Diagnosing Audio Reasoning with Rule and Percept Interventions

Chengwei Wei, Yi Ma, Nancy F. Chen

原文摘要

Answer accuracy alone does not distinguish failures in acoustic perception, rule knowledge, and rule application. AuDiR (Audio Diagnostic Reasoning) examines these distinctions through controlled input interventions. Each item contains an audio clip, a multiple-choice question, a task-general rule, and a textual description of the acoustic observations needed to answer. Three conditions progressively supply the rule and observations; a fourth removes the audio while retaining the question and rule. The first correct diagnostic condition assigns an operational response label, without identifying a unique internal cause. The current benchmark contains 201 items in 18 families drawn from 9 sources, with answer references documented separately from percept extraction. In a preliminary evaluation of Gemini-3.8-flash, accuracy is 29.3% without supplied information, 31.3% with the rule, and 98.5% with the observations also supplied. No-audio accuracy is 23.9%, with a confidence interval containing the 25.0% chance rate. A family-level knowledge probe associates incomplete rule recall with larger gains from rule provision. These results show the benefit of supplying acoustic observations as text, while incomplete validation, possible recognition shortcuts, and non-monotonic responses limit stronger failure-attribution claims.

cs.AI

版本更新 · v2arXiv:2608.30300

Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?

Zijian Luo, Runzhi He, Pengfei Gao, Yu Kang, Zeqi Lin, Minghua Ma, Qingwei Lin, Saravan Rajmohan 等 9 位作者

原文摘要

Modern software systems rely heavily on third-party dependencies, but upgrading those dependencies remains a costly maintenance activity. Dependency upgrades do not always preserve the function signatures, type systems, APIs, or runtime semantics assumed by existing code. Consequently, developers often need to perform source code adaptations to accommodate dependency-induced changes. However, such code-level changes are often not explicitly communicated to project maintainers, posing a significant challenge to software reliability. Meanwhile, coding agents have emerged as a new form of software development tool and are increasingly adopted by developers due to their automation capabilities. In this paper, we introduce DEPBENCH, a benchmark consisting of 203 real-world dependency-upgrade tasks across five package ecosystems spanning five language communities, each involving hidden code-level changes that require source code adaptation. We evaluate mainstream coding agents on DEPBENCH. The best completed configuration solves only 104/203 tasks (51.2%), with substantial variation across agent harnesses, models, and ecosystems, highlighting an important gap between current agent capabilities and real-world software maintenance needs.

cs.SE

新论文 · v1arXiv:2611.12477

Perturb, Aggregate then Reconstruct: Consensus Aggregation and Fourier-Attended Multi-Decoders for Reconstruction-based Multi-View Anomaly Detection

Yongho Son, Junyeong Yun, Je Hyeong Hong

原文摘要

Multi-view anomaly detection is crucial for industrial inspection to identify defects hidden from single viewpoints. Yet, despite their strong success in single-view applications, reconstruction-based methods remain largely underexplored in multi-view settings. A key challenge in extending these methods lies in generating view-consistent pseudo-anomalies. To address this, we propose PAR, a reconstruction-based framework for enhanced multi-view anomaly detection. First, we introduce a feature perturbation strategy coupled with a consensus aggregation module that integrates these perturbed features across viewpoints to mitigate view-inconsistent anomalies and construct highly aligned pseudo-anomaly representations. Second, we employ a view-specialized multi-decoder architecture; by assigning a dedicated decoder to each view, we increase the model's representational complexity, enabling the generation of highly feasible, localized anomaly maps rather than less precise, view-agnostic reconstructions. Last, we incorporate Fourier attention into the decoders to emphasize global frequency-domain structures over local token evidence, effectively preventing identity mapping. Extensive experiments on the Real-IAD dataset demonstrate that PAR consistently outperforms state-of-the-art methods in sample-level, image-level, and pixel-level anomaly detection. Our code is available at https://github.com/SpatialAILab/PAR_mvad.

cs.CV

新论文 · v1arXiv:2611.12475

Learning to Select Sparse Linear Solvers with Convolutional Neural Networks

Artemis Pados, Alan Edelman, Emmanuel Lujan, Daniel Pickard, Felipe Tome, Christopher Rackauckas

原文摘要

We investigate convolutional-neural-network (CNN) based automatic solver selection for sparse linear systems, a problem of practical importance where solver performance varies dramatically with matrix sparsity structure. A CNN is trained to regress log timing ratios between candidate solvers using spy plot images of matrix nonzero structure as input, achieving strong prediction accuracy on both held-out SuiteSparse matrices and real-world matrices from high-performance simulation codes.

cs.LG