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 19:36 — 2026-11-16 19:36(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:2611.13052

Explanation-Aware Fairness Beyond Output Parity: Joint Output-Attribution Regularization for Medical Image Classification

Gökhan Özbulak, Oscar Jimenez-del-Toro, Lilian Berton, André Anjos

原文摘要

Output-level fairness does not constrain whether demographic groups rely on similar predictive contributions in representation space. For a nonlinear encoder with a linear head, we show that outcome-conditioned output score disparity equals the signed sum of feature attribution differences across subgroups by allowing small prediction gaps to arise through cancellation effect. We test whether an attribution disparity penalty complements output-level equalized odds based fairness surrogates. Across 960 DINOv2-LoRA models on HAM10000 and Harvard-GF datasets for gender and race fairness, attribution augmentation increases utility-fairness trade-off performance for hypervolume in six different settings with paired 95% confidence intervals and relative gains of 1.49-10.57%. Under a predefined utility constraint, augmented model families also achieve 9.0-38.7% lower equalized odds difference, lower attribution disparity, and reduced cancellation ratio while preserving predictive utility. These results support attribution fairness as a complementary explanation-aware constraint on output fairness.

cs.LG

版本更新 · v2arXiv:2609.38524

Generative sequence modeling for infinite memory processes via predictive states

Michael Wieck-Sosa, Cosma Rohilla Shalizi

原文摘要

We consider estimating the one-step-ahead conditional distribution of a multivariate stochastic process. Many existing approaches rely on assumptions such as finite-range memory, sparsity, or additivity, which can be poorly suited to processes with long-range nonlinear interactions. However, without such structural assumptions, nonparametric estimation is challenging due to the curse of dimensionality. To address this challenge, we introduce a new estimator based on learning representations of the \emph{predictive states} of a stochastic process. We show that the statistical complexity of the estimation problem is determined by the dimension of this predictive state representation. Furthermore, we show that a $p$-dimensional predictive state space can be represented in a $2p+1$-dimensional feature space. Our results imply that faster convergence rates are achievable when the predictive state space is lower-dimensional, i.e., when the past history can be compressed into a lower-dimensional statistic that is sufficient for predicting the future. We establish theoretical convergence rate guarantees for an instantiation of our method based on deep neural network estimators. We implement our method in PyTorch and evaluate its performance on processes with infinite-range memory.

stat.ML · cs.LG · stat.ME

版本更新 · v2arXiv:2609.32728

Single-Exponential Algorithms for Directed Feedback Vertex Set on Planar Digraphs

Daniel Lokshtanov, Saket Saurabh, Jie Xue

原文摘要

We consider Directed Feedback Vertex Set on planar digraphs, parameterized by the solution size $k$. We give a randomized algorithm with one-sided error running in time $(2+\sqrt5)^k n^{O(1)}= 4.24^k n^{O(1)}$, and a deterministic algorithm running in time $8.04^k n^{O(1)}$. Both algorithms use polynomial space. To the best of our knowledge, these are the first single-exponential fixed-parameter algorithms for Directed Feedback Vertex Set on planar digraphs. This contrasts with general digraphs, where the best known algorithms run in time $2^{O(k\log k)}(n+m)$, and whether a $2^{o(k\log k)}n^{O(1)}$-time algorithm exists remains a major open problem. Our main tool is an exact Euler-type counting identity for plane digraphs. It shows that every small solution must carry a large share of the vertices whose in- and out-arcs alternate in the embedding, while solutions avoiding such vertices can be computed by reducing to Directed Feedback Arc Set, which is known to be solvable in polynomial time on planar digraphs via the Lucchesi-Younger theorem.

cs.DS

版本更新 · v2arXiv:2604.24293

Mitigating Global Feature Collapse in Graph ODEs via Hysteretic Topology Evolution

Qinhan Hou, Jing Tang

原文摘要

Graph neural ordinary differential equations provide continuous-time propagation on graphs, but their long-time behavior is largely determined by the asymptotic structure of the mixing operator. We show that diffusion-style Graph ODEs with positive irreducible mixing face a \emph{monostability trap}, where node features converge to a rank-one consensus subspace. This reveals a structural limitation of positive diffusion-style continuous graph propagation: within this consensus class, exact long-time avoidance requires changing the effective support; otherwise, smooth suppression should be interpreted as finite-horizon or metastable mitigation. We address this by introducing a \emph{hysteretic mechanism} for topology evolution, where candidate edges carry latent bistable potentials in a double-well landscape. A node-feature-conditioned force field evolves these potentials, and a smooth sigmoid gate converts them into differentiable propagation weights. We prove global consensus under the stated mixing assumptions and block-wise consensus under idealised support separation. For consensus-form dynamics, we further establish a finite-horizon perturbation bound under small cross-block leakage, and empirically evaluate the resulting nonlinear HGODE on node- and graph-level benchmarks.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.08438

Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

Fazl Barez, Tung-Yu Wu, Hunar Batra, Gabriele Dominici, Florent Draye, Yanai Elazar, Damiano Fornasiere, Antía García 等 27 位作者

原文摘要

Neural networks are likely to be among the most consequential artefacts in human history. As these systems become more capable and autonomous, their potential to cause societal harm also grows, making AI safety one of the defining challenges of our time. Yet we continue to build increasingly powerful systems without fully understanding how they work, how they will behave in unfamiliar situations, or how to reliably control them. Mechanistic interpretability offers a path towards understanding these systems by studying their internal representations and computations, with the aim of evaluating, predicting, and controlling behaviour. We survey mechanistic interpretability for AI safety in order to answer the question: Does understanding how models work actually make them safer? We place mechanistic interpretability in the broader context of interpretability research and compare its mechanistic evidence with behavioural evaluation. We introduce the foundations of mechanistic interpretability, including features, polysemanticity, transformer computation, and circuits, and survey methods for feature extraction and analysis, circuit discovery and causal verification, explaining intermediate representations in natural language, learning dynamics, and training-data attribution. Beyond surveying existing methods, we propose a unified framework for evaluating mechanistic interpretability claims and characterise six research orientations by their goals, assumptions, and trade-offs. Finally, we examine how mechanistic understanding can support AI safety, including knowledge editing, steering, and monitoring, and assess its limitations, failure modes, open problems, and relationship to behavioural safety measures. We also release a repository of code notebooks with worked examples that reproduce key findings from surveyed methods, allowing readers to build intuition through hands-on experimentation.

cs.CL · cs.AI · cs.LG

版本更新 · v4arXiv:2511.21245

FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision

Chen Ling, Henglin Shi, Hedvig Kjellström

原文摘要

Monocular 3D face reconstruction estimates the parameters of a 3D morphable face model (3DMM) from a single image, providing an explicit geometric representation for facial expression analysis. Owing to the scarcity of paired 2D images and 3D facial meshes, most methods are trained in a self-supervised manner by rendering the predicted face and minimizing image-level reconstruction losses, such as photometric and landmark errors, against the input image. However, these losses enforce visual alignment but do not ensure that the predicted parameters preserve affective information. Recent methods add image-level emotion consistency loss, but it can be satisfied by exaggerating facial deformations. To address these issues, we propose FIELDS (Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision), which learns affect-informative expression representations in the FLAME parameter space. Specifically, FIELDS augments 2D self-supervised reconstruction with scan-derived expression anchoring and a parameter-space emotion loss. During training, scan-fitted targets directly constrain expression-related FLAME parameters to discourage exaggerated deformations, while a jointly trained emotion head uses discrete emotion and continuous valence--arousal annotations to make the predicted parameters informative for affect analysis. Experiments show that FIELDS improves affective utility from the predicted parameters in both within- and cross-dataset settings. Notably, it also achieves lower reconstruction errors overall and across most facial regions than the comparison baselines under both rigid and similarity alignment.

cs.CV

版本更新 · v2arXiv:2610.19940

A Non-Dichotomy for CSPs of Stable $ω$-Categorical Structures

Manuel Bodirsky, David Bradley-Williams, Ehud Hrushovski, Christoph Spiess

原文摘要

We construct countable, stable, $ω$-categorical structures with at most two binary relations whose CSPs exhibit three complexity regimes: NP-complete, decidable but not in NP, and undecidable. The templates arise from a controlled Hrushovski construction of stable $ω$-categorical graphs $M_α$ for suitable irrational parameters $α>1$. Some of these graphs have NP-complete CSPs. Expanding the graphs $M_α$ by the non-edge relation turns age membership into a restriction of the CSP. For every time-constructible bound $t$, there is such an expansion whose CSP is decidable but not in DTIME$(t)$. For an explicit parameter $α$, the restriction to complete instances belongs to $\mathrm{coNP}$ and the full CSP belongs to $Σ_2^{\mathrm P}$. Separating the ages of the $M_α$ using graphs with large girth and prescribed density yields $2^{\aleph_0}$ distinct CSPs of these expansions, all but countably many of which are undecidable.

cs.LO · math.LO

新论文 · v1arXiv:2611.12468

Sets of reach $R$ are $\operatorname{CAT}\left( 1/R^2\right)$

André Lieutier, Mathijs Wintraecken

原文摘要

Positive reach underpins many results in computational geometry and topology. It is used for triangulation criteria, topological inference, and manifold learning. The geometric properties of these sets have therefore been studied intensely. In this paper we focus on the intrinsic metric properties of sets of positive reach. In particular we give an elementary proof of the fact that (closed) sets of reach at least $R$ are $\operatorname{CAT}(1/R^2)$. This fact was established earlier by Alexander and Bishop, using quite significant machinery. The fact that a space is $\operatorname{CAT}(1/R^2)$ offers many advantages, such as the uniqueness and continuity of sufficiently short geodesics, the existence of Fr{é}chet means and by extension the Rips based homotopy reconstruction of Hausmann is available.

cs.CG · math.MG

新论文 · v1arXiv:2611.12466

Prediction with Foundation Models under Deployment Budgets

Zhaohui Xu, Xiaofei Xu, Doudou Zhou

原文摘要

Foundation models can supply predictions for a downstream task that draw on knowledge from extensive pretraining, but they differ in task-specific accuracy and query cost. We develop a framework that improves prediction for the task under a budget on the average query cost per input, using training data to learn which models to query and how to combine their outputs with features available without querying. The first method queries the same models for every input; the second lets them vary across inputs and uses Q-learning to decide which model to query next and when to stop. For the first method, we show that several individually inaccurate outputs can jointly outperform the best single one. It attains the minimax rate when the regression function depends on the outputs only through models within the budget. Otherwise, any method within the budget can be forced to a slower rate, which the first method attains. For the second method, we show when varying the queried models across inputs strictly improves on querying the same models for every input, and bound its prediction risk and average cost in finite samples. In simulations and a multimodal laptop price application, both methods outperform existing methods.

stat.ML · cs.LG

新论文 · v1arXiv:2611.12464

Phrase-Level Speculative Decoding on a Frozen Target

Madhusudhana Naidu

原文摘要

Speculative decoders raise throughput by banking more target tokens per forward pass, and Medusa, EAGLE-3, DFlash and DSpark all do it the same way: more candidates that survive verification. All of them draft in the target's own vocabulary, so one node of the candidate tree is one target token, and the tokenizer makes that unit look like a constant. It is not. BPE's pretokenizer splits on whitespace before merges are learned, so no multi-word string can ever become a single token: in Qwen3-4B, "United States of America" is four tokens and no adjacent pair of them exists as one entry, so a phrase is out of reach of any method drafting in the target's vocabulary. We change the unit. A small MLP head reads the frozen target's hidden state and predicts a one- to three-word phrase as one entry in a separate draft vocabulary; greedy longest-match expansion maps it back into the target's own tokens, and N candidates are verified in one forward pass behind a prefix-tree mask, so the change is orthogonal to tree depth and width. The target and its tokenizer stay frozen and a candidate is accepted only while it matches the target's own argmax, so the served output is identical to greedy decoding up to floating-point tie-breaking. On one A5000 at batch 1, against HuggingFace generate(), a 21.94M head (0.545% of Qwen3-4B) reaches 2.391x on GSM8K, 2.444x on MATH-500 and 1.544x on MT-Bench. Because the head's output layer is one row of 257 parameters per entry, the draft vocabulary size is the parameter budget: an 8,000-entry head is 3.434M parameters, 0.0854% of the target and 64x smaller than EAGLE-3's drafter, and keeps 92.3% of the larger head's GSM8K tokens per pass. With EAGLE-3 run on same prompts and baseline, our 21.94M head is ahead of tree-16 on both maths sets and behind tree-60 on every set.

cs.CL · cs.AI · cs.LG

版本更新 · v3arXiv:2605.11970

NOFE - Neural Operator Function Embedding

Lars Uebbing, Harald L. Joakimsen, Siyan Chen, Georgios Leontidis, Kristoffer K. Wickstrøm, Michael C. Kampffmeyer, Sébastien Lefèvre, Arnt-Børre Salberg 等 9 位作者

原文摘要

Most dimensionality reduction methods treat data as discrete point clouds, ignoring the continuous domain structure inherent to many real-world processes. To bridge this gap, we introduce Neural Operator Function Embedding (NOFE), a domain-aware framework for continuous dimensionality reduction. NOFE learns function-to-function mappings via a Graph Kernel Operator, enabling mesh-free evaluation at arbitrary query locations independent of input discretization. We establish NOFE as approximation of sheaf-to-sheaf mappings, generalizing Sheaf Neural Networks to continuous domains. We evaluate NOFE across different datasets, comparing it against six traditional as well as recently developed methods, including PCA, t-SNE, UMAP. Our results demonstrate that NOFE significantly outperforms baselines in local structure preservation, achieving a local Stress of 0.125 compared to 0.464 for PCA, 0.694 $-$ 2.127 for remaining methods on the ERA5 climate reanalysis dataset. NOFE also exhibits robust sampling independence, reducing the Patch Stitching Error by up to $20.0\times$ relative to UMAP (13.035 vs. 267.586 under regional normalization) and ensuring consistency across disjoint domain patches. While maintaining competitive global structure preservation (Stress-1: 0.379 vs. PCA's 0.268), NOFE resolves fine-grained structures and produces smooth, consistent embeddings that generalize across varying sample densities, addressing key limitations of discrete reduction methods.

cs.LG

版本更新 · v4arXiv:2602.16681

VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

Yingyuan Yang, Tian Lan, Yifei Gao, Yimeng Lu, Xuming An, Wenjun He, Meng Wang, Chenghao Liu 等 9 位作者

原文摘要

Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime .

cs.CV

版本更新 · v2arXiv:2610.07417

Bayesian Optimization on Function Spaces via Sparse RKHS Manifolds

Davide Sartor, Meghan E. Huber, Donghyun Kim, Nathan Wycoff

原文摘要

Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter vector arises from the discretization of an inherently functional relationship. Several recent articles have considered the Functional Bayesian Optimization (FBO) setting, in which the variable to be optimized is not a member of a finite dimensional vector space, but rather an infinite dimensional function space. In this work, we propose $L^0$ Manifold Optimization (L0MO), a simple approach to FBO which searches the subset of a Reproducing Kernel Hilbert Space (RKHS) consisting of functions with a sparse representation in the kernel functions, optimizing both the kernel locations and their coefficients. We discuss in detail the relationship between our method and existing ones, providing a unifying lens through which to view prior works. To assess our method against the state of the art, we conduct an extensive computational study, and along the way develop a novel set of benchmark test functions which port standard finite-dimensional ones to the infinite dimensional domain. Our experiments demonstrate that, on balance, the proposed method achieves superior performance across a wide range of test benchmarks.

stat.ML · cs.LG

新论文 · v1arXiv:2611.12458

Causal discovery from Bayesian symbolic regression

Roger Guimerà, Kai-Hendrik Cohrs, Sergio Pedreira, Marta Sales-Pardo, Gustau Camps-Valls

原文摘要

Causal discovery from observational data is central to scientific reasoning, yet established constraint-based and score-based methods often recover only a Markov equivalence class and provide no signal in bivariate or strongly autocorrelated regimes typical in some areas of science. Here, we recast causal discovery as a Bayesian symbolic regression problem. Given a set of candidate parents for each target variable, the Bayesian symbolic regression samples closed-form expressions from a posterior over symbolic models. The fraction of sampled expressions in which each candidate variable appears defines a posterior inclusion probability that we use as the causal score. This replaces pointwise model selection by an ensemble of plausible mechanisms. We evaluate the method on coupled nonlinear bivariate dynamics, on the CauseMe benchmark suite spanning linear, chaotic, nonlinear, higher-dimensional and high-noise settings, and on a four-variable biogeoscience structural causal model under Gaussian, heavy-tailed and mixed-noise regimes. Our approach is competitive with, and often outperforms, specialized causal discovery algorithms. Additionally, the method returns closed-form mechanisms leading to explicit causality and interpretability.

stat.ML · cs.LG · physics.comp-ph · physics.data-an

版本更新 · v2arXiv:2603.20827

Swim2Real: Vision-Language Models for Simulator Calibration of a Soft Robotic Fish

Kevin Qiu, Kyle Liam Walker, Mike Yan Michelis, Marek Cygan, Josie Hughes

原文摘要

Calibrating a soft aquatic robot simulator requires matching coupled deformation and propulsion from limited pool recordings. Swim2Real uses a vision-language model (VLM) to compare real and simulated swimming videos and propose updates to 16 simulator parameters. A backtracking line search tests each direction and accepts updates that reduce marker error. To test whether the proposals carry useful directions, we compare them with random and signed-permuted directions under the same line search and simulator budget. In an independent, preregistered fifty-seed replication, Swim2Real reduces the mean best-so-far error over 40 simulator evaluations by 63.4 mm against random directions and 53.2 mm against permuted directions. Both paired comparisons pass Holm correction ($p<10^{-5}$), conditional on run completion. A 24-seed experiment with a second VLM supports the same direction effect. Backtracking averages 16.1 VLM proposals per run versus 39 for Vid2Sid, which attains lower error at the same simulator budget. Ten hardware trials demonstrate open-loop execution of simulator-generated motor commands. Project page and videos: https://swim2real.github.io.

cs.RO

版本更新 · v4arXiv:2605.08786

PRIM: Meta-Learned Bayesian Root Cause Analysis

Christopher Lohse, Anish Dhir, Amadou Ba, Bradley Eck, Marco Ruffini, Jonas Wahl

原文摘要

Root Cause Analysis (RCA) aims to identify the main drivers of anomalies in complex multivariate systems. The task is challenging due to the need for structural causal knowledge for some methods, and the computational cost of inference at test time. This paper introduces PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a prior of causal models. By marginalising out structural uncertainty, PRIM detects changes in the data-generating mechanism between normal and anomalous periods, infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time. Following the simulation-based meta-learning paradigm of prior-fitted networks (PFNs), PRIM uses a transformer neural process (TNP) that jointly attends over normal and anomalous samples and the structural dependencies of nodes, enabling fast zero-shot inference in systems with up to 100 variables. Across synthetic benchmarks and two realistic benchmark datasets, PetShop and CausRCA, PRIM is competitive with other graph-free methods.

cs.LG

版本更新 · v2arXiv:2607.08932

Shape-based Figure-Ground Organization in Vision Transformers

Matthias Tangemann, Benjamin Lo, Zygmunt Pizlo, Kaleem Siddiqi, Dirk B. Walther, Sven Dickinson

原文摘要

Rich perceptual structure emerges in modern vision encoders. Several studies have shown that the internal representation in many vision transformers separates foreground objects from the background, however, little is known about the visual cues that have been learned by these models. In this work, we study whether figure-ground organization in a broad range of 25 vision transformers relies on generalizable shape cues, rather than on superficial texture statistics. To do so we train linear probes to classify patches as figure or ground, and evaluate them zero-shot on synthetic stimuli where individual cues are systematically manipulated. For a broad range of vision encoders, we find that probes are robust to the random replacement of textures in the input image, suggesting that the emerging figure-ground organization relies on shape cues. Probes also generalize in a zero-shot fashion to synthetic images where individual shape cues, recognizability and spatial priors are controlled for. Our experiments reveal a strong influence of surroundedness and convexity cues, while results for parallelism and symmetry are more nuanced. More detailed analyses reveal stronger evidence for shape-based cues in larger models, that models trained for object-recognition tend to be less robust to texture changes and that figure-ground information emerges most prominently in middle layers. Taken together, our study demonstrates that emerging figure-ground organization in recent vision encoders relies strongly on generalizable shape cues, advancing our understanding of the internal processing in vision transformers, and opening an exciting avenue for computational research on human visual perception. Code and data is available at https://github.com/mtangemann/mlvbench.

cs.CV

新论文 · v1arXiv:2611.12452

V3DSAM: Semantic-Geometric Loop Verification and Geometry-Anchored Persistent Instance Mapping for Feed-Forward Dense SLAM

Maolin Ye, Dongqing Zhao, Linyang Li, Shuai Xue, Yuan Liu, Yiyuan Wang, Wen Li

原文摘要

To address unreliable cross-view association in long-sequence feed-forward dense SLAM, this letter presents V3DSAM, an open-vocabulary semantic dense SLAM system that establishes physical correspondences at both the scene and object levels. The system combines feed-forward geometric estimates from VGGT-SLAM 2.0 with open-vocabulary semantic observations from SAM3. We introduce semantic-geometric dual-scale loop verification, which identifies false loop closures using pixel-level bidirectional reprojection and object-level 3D spatial correspondences, without accessing backbone-internal features. We further propose geometry-anchored persistent instance mapping, which defines physical instances through class-constrained 3D connectivity in an optimized global coordinate system and assigns global IDs without inter-frame identity propagation. The proposed verifier rejects all four false loop candidates in our TUM RGB-D evaluation, while long-sequence ScanNet experiments show improved instance identity consistency. Thus, V3DSAM reduces dependence on internal backbone features and temporal ID propagation for robust long-term cross-view association.

cs.RO · cs.CV

新论文 · v1arXiv:2611.13049

The Gene Is Not the Gate: Conceptualizing the Semantic Genome of Quantum Software

Jiongchi Yu, Yue Duan, Ziming Zhao, Xiaofei Yue, Zhaoxuan Li

原文摘要

Quantum software spans applications, program representations, compilers, runtimes, and hardware-facing control. Existing abstractions describe these artifacts and layers, but they do not capture the semantic responsibilities that must remain valid as a computation is transformed across the stack. This limits systematic reasoning about cross-layer correctness, evolution, and reuse. We present QGenome, a semantic foundation for quantum software genomics. We define a quantum software gene as a typed, reusable responsibility characterized by an explicit contract, execution context, concrete expressions, and supporting evidence. QGenome organizes genes across five software strata and ten responsibility families grouped into computational semantics, coordination, realization, and assurance. Typed genes compose into pathways and genomes through dependency, refinement, provenance, and phenotype relations, enabling responsibilities to be traced across alternative implementations and execution contexts. We illustrate the taxonomy using representative public artifacts across the quantum software stack and define principles for contextual validity, genome evolution, environmental adaptation, and capability expression. Rather than presenting a complete taxonomy or an automated extraction technique, QGenome establishes a falsifiable framework and a concrete research agenda for gene mining, lineage recovery, cross-layer regression testing and repair, and evidence-grounded quantum software agents.

cs.SE

新论文 · v1arXiv:2611.12446

Pricing Symbolic Rules by What GNNs Leave Unlearned

Satabarto Sarkar, Prithwineel Paul

原文摘要

Symbolic knowledge (motif counts, ring counts, label constraints) is routinely added to graph neural networks (GNNs) and justified by their limited expressivity. We replace this yardstick with an exact one. The largest log-loss reduction a rule $S$ can give a model family is $I(Y;S\midσ)$ given what the family computes; every realised gain splits exactly into this term plus repaid neural debt; and for a trained network with representation $T$ the value is $I(Y;S\mid T)$, the label information training failed to extract. Rule design thus becomes rule discovery: we score candidates on the network's out-of-fold residual against calibrated permutation nulls with family-wise error control. On ZINC, discovery recovers the hidden ring term $\max(0,\ell_{\max}-6)$ of the target in three independent runs ($p_{\mathrm{adj}}=0.001$) and beats expert cycle counts; frozen and applied to five unseen datasets it is never significantly worse than the plain network or the expert rule, and on BBBP it significantly beats both.

cs.NE · cs.AI · cs.LG

新论文 · v1arXiv:2611.12444

Sampling Colorings on $G(n, d/n)$ via Glauber Dynamics

Leon Schiller

原文摘要

We study the mixing time of Glauber dynamics for sampling uniformly from the proper $q$-colorings of sparse Erdős-Rényi random graphs $G(n,d/n)$. Our main result establishes that with probability $1-o(1)$ over the draw of $G$, Glauber dynamics is rapidly mixing for every $q\geq d+d^{1/2+\varepsilon}$, given any fixed $0<\varepsilon\leq1/2$ and any sufficiently large fixed $d$. In particular, the surplus of colors above $d$ is sublinear and close to $\sqrt{d}$. The achieved color range therefore approaches the tree uniqueness threshold and improves over the previously best achievable number of colors $q > 1.763 d$ due to Efthymiou, Hayes, Stefankovic, and Vigoda [SODA 2018]. Moreover, our mixing-time bound is $O(n^{2+o_d(1)})$, and hence almost quadratic as $d\rightarrow\infty$. Our proof is based on establishing a spectral gap for block dynamics resulting from a suitable decomposition of $G(n,d/n)$ into blocks and singleton vertices, ensuring that every high-degree vertex is encapsulated within a block. Our main technical contribution is a novel way of establishing rapid mixing of block dynamics via an integrated Bochner-Bakry-Émery approach, which we expect to have applications beyond sampling colorings. We further devise a new block decomposition of $G(n,d/n)$ that strengthens and simplifies similar constructions used in previous work. Finally, to compare block and Glauber dynamics, we establish a novel recursive separator decomposition of tree-like blocks, together with a coupling argument that avoids the need for nearly uniform color marginals at vertices adjacent to hubs. This comparison argument might be of independent interest.

math.CO · cs.DS · math.PR

新论文 · v1arXiv:2611.12445

LongSCOP: Semantically Consistent Long Video Outpainting

Yu Tang, Zhiyuan You, Zhixiao Wang, Fanghua Yu, Qingyu Zhang, Xiang Yin, Chao Dong, Jinjin Gu

原文摘要

Video out-painting is an important problem, yet existing research focuses primarily on short clips, leaving long video out-painting largely underexplored. Extending video out-painting to long videos poses substantial challenges. A natural solution is iterative out-painting, i.e., generating videos chunk by chunk, but this introduces two major issues: generation instability or even failure caused by inter-chunk inconsistencies and error accumulation, and semantic drift over long temporal horizons. In this paper, we propose LongSCOP, short for Semantically Consistent long Video Out-Painting. First, we introduce a training recipe with three components for smooth and stable long-horizon generation: self-forcing training, latent calibration, and future references. Beyond generation stability, we recognize that the rich temporal context of long videos provides valuable references for maintaining semantic consistency. We therefore develop a VLM-based agent that automatically selects the most informative reference frames from the entire video to maintain consistent subjects, scenes, and backgrounds throughout long-horizon generation. We also construct a high-quality training dataset of 62K video clips. To facilitate research on this underexplored problem, we introduce LVO-Bench, a benchmark curated by human experts to assess long-horizon stability and semantic consistency. Extensive experiments demonstrate that our method outperforms existing approaches in both generation stability and semantic coherence.

cs.CV

新论文 · v1arXiv:2611.12443

MoSTE: Mixture of Spatio-Temporal Experts for Deepfake Detection in Videos

Charbel Yahchouchi, Nabyl Quignon, Noemi Roggero, Laurent Saroul, Antitza Dantcheva

原文摘要

Generalizable deepfake video detection remains challenging because forgery artifacts vary substantially across manipulation types and often combine diverse spatial and temporal inconsistencies. Existing parameter-efficient adaptation methods typically rely on a single shared representation, rendering them prone to manipulation-specific bias and limiting transfer to unseen forgeries. To address this challenge, we propose Mixture Of Spatio-Temporal Experts (MoSTE), an adaptation framework that enables conditional specialization of forensic representations. Instead of forcing one adapter to model all forgery patterns, MoSTE decomposes adaptation into parallel spatial and temporal expert pools and dynamically routes tokens to the most relevant experts through an unsupervised token-level routing mechanism. This allows experts to naturally specialize in complementary forgery cues without requiring explicit manipulation labels or multi-stage training, while effectively transferring representations from CLIP to the video domain. Extensive experiments across cross-dataset and cross-manipulation benchmarks demonstrate that MoSTE sets a new state of the art in average generalization while preserving strong performance across diverse manipulation families. Additional analysis of expert routing and attention behavior reveals the emergence of expert diversity, suggesting that MoSTE learns complementary spatio-temporal forensic features. Code is available at https://github.com/charbelyah/MoSTE

cs.CV

新论文 · v1arXiv:2611.12442

When Handshakes Go Dark: An Adaptive Semantic-Sequential Fusion Framework for Encrypted Traffic Classification

Tong Guan, Yunchun Li, Minyuan Xiao, Mingyuan Xia, Yuchen Zhao, Wei Li

原文摘要

Encrypted traffic classification is essential for network security monitoring and traffic management. Self-supervised pre-training can learn reusable representations from large-scale unlabeled traffic, but TLS 1.3, QUIC, and privacy mechanisms such as Encrypted Client Hello (ECH) increasingly conceal application, handshake, and service-identifying information. Observable upper-layer bytes are therefore dominated by ciphertext, weakening the link between raw-byte patterns and application semantics and limiting model generalization. Moreover, the availability and discriminative value of observable information vary across protocols, protection profiles, and tasks, complicating classification across diverse scenarios. To address these challenges, we propose FLARE, a Field-aware Learning and Adaptive Representation Fusion framework for encrypted traffic classification. FLARE pre-trains a BERT-based packet encoder through Masked Field Prediction, which reconstructs masked tokens from field-structured context. During downstream fine-tuning, the parameters of the pre-trained packet encoder remain frozen, and a packet-level gated module adaptively combines protocol-semantic representations with directional packet-length representations. A flow-level encoder then models inter-packet dependencies for classification. We evaluate FLARE on eight datasets spanning diverse encrypted-traffic tasks, including CipherSpectrum and VisQUIC for strongly encrypted scenarios. FLARE achieves superior performance over baselines across the eight datasets, exceeding the strongest pre-trained baseline by 10.92 percentage points on QUIC website fingerprinting. These results demonstrate the effectiveness of field-aware pre-training and adaptive semantic-sequential fusion under constrained observability.

cs.NI

新论文 · v1arXiv:2611.12440

Exploring public-private data sharing practices through the lens of Open Data Ecosystems: A multiple case study on municipal and regional freight logistics

John Larsson, Johan Linåker, Per Runeson

原文摘要

Background: Freight transport is expected to increase, contributing to air pollution. There is, therefore, a critical need for increased efficiency that can reduce emissions. Data sharing is one approach, where actors within Open Data Ecosystems (ODE) collaborate and share data among stakeholders to plan and operate more efficient and sustainable freight transport. Aim: In this study, we explore how public-private data sharing practices in municipal and regional last-mile freight logistics in Sweden may improve efficiency. Method: Following a prolonged participation process, we conducted a multiple-case study involving three different cases, built upon initial meetings, semi-structured interviews, supported by a thematic analysis, and validated through a follow-up workshop. Results: The findings show that data sharing in public-private freight logistics (ODE-PPF) is shaped by interrelated socio-technical aspects, including platform design, roles of actors, handling of sensitive data, data quality, and procurement processes. We synthesize our findings in an actor model and a conceptual model, highlighting how these aspects contribute to the functioning of ODE-PPF, and derive seven proposition sketches as a foundation for future research. Conclusion: Data sharing is a central mechanism enabling integration and value creation in last-mile logistics. It depends on the interaction between technical and organizational aspects. Public actors can undertake a key role as a neutral keystone actor by orchestrating the ecosystem and facilitating data sharing through governance practices such as procurement.

cs.SE

版本更新 · v2arXiv:2607.22698

FogDrive: A Multi-Modal Synthetic Driving Dataset for Perception under Graded Fog

Vansh Panwar, Naveen Varshney, Prashant W. Patil

原文摘要

Fog degrades autonomous-driving perception across modalities: it lowers image contrast, attenuates and scatters LiDAR returns, and shifts the input distribution of every learned module downstream. Choosing between restoring the degraded input and training on it directly requires the same scenes observed with and without fog at known severities, and enough foggy data to train on. Real-world capture cannot supply this: fog arrives entangled with lighting and traffic, at severities recorded rather than chosen; existing synthetic datasets narrow the sensor suite, the scale, or the severity range. We present FogDrive, a CARLA dataset of ~660 scenes (~133k frames), each released as a clear reference plus three calibrated fog densities, with physics-based fog on camera and LiDAR and 2D/3D annotations consistent across all variants. Every frame carries four cameras (RGB, depth, semantic), LiDAR, semantic LiDAR and radar -- spanning fog's response spectrum from heavily degraded cameras to largely unaffected radar. Experiments trained on FogDrive show that mixing fog densities improves 3D detection at no extra data cost, that PSNR and SSIM poorly predict a dehazer's detection benefit, and that radar improves camera-LiDAR fusion at every density. The dataset and its generation framework will be released.

cs.CV

新论文 · v1arXiv:2611.13048

Reliable Computation of the $L_{\infty}$-Norm of Linear Time-Invariant Systems Depending on One Parameter

Florent Corniquel, Alban Quadrat, Fabrice Rouillier, Grace Younes

原文摘要

The $L_{\infty}$-norm of a linear time-invariant system is a central quantity in robust control, used in robust stability tests, stability margins, and $H_{\infty}$ controller design. Physical models depend on parameters, such as masses, stiffnesses, or gains, so the $L_{\infty}$-norm becomes a function of these parameters. This computation reduces to studying the real critical points of a plane algebraic curve whose coefficients depend on the parameters. Previous approaches based on cylindrical algebraic decomposition describe the $L_{\infty}$-norm on the whole parameter space, but their cost grows very quickly with the number of parameters. In this paper, we propose instead to compute a generic parametrisation of the solutions, valid outside an explicitly characterised set of non-generic parameter values. In the case of one parameter, this parametrisation is obtained by interpolation from a certified solver for the non-parametric case. The resulting algorithm is fully certified, relying on a priori bounds and multimodular computations rather than on Gröbner bases. It is illustrated on examples from the robust control literature.

cs.SC

新论文 · v1arXiv:2611.12437

Occupancy Modelling of Biased Landslide Inventories: When Does Separating Occurrence from Recording Improve on Neutralisation?

Abdirashid Omar, Abdikadir Ugaas

原文摘要

Landslide susceptibility models are trained on inventories that record where landslides were seen, not where they occurred. The established remedy fits bias-describing variables and neutralises them when mapping. We adapt occupancy-detection modelling from ecology, treating several inventories as imperfect observers of one event and separating occurrence from recording, and ask when this improves on neutralisation. We use near-complete inventories of the 2018 Hokkaido Eastern Iburi, 2015 Gorkha and 2010 Haiti earthquakes with simulated reporting bias, and three real Gorkha inventories. Compared with standard practice, the occupancy model reduces road bias in 24 of 25 paired draws and raises AUC by 0.08-0.14 on Gorkha and 0.03 on Haiti, but only 0.01-0.02 on Iburi. Its median predicted-to-true landslide rate is 0.99 (range 0.44-1.89), against 0.24-0.30 for the baselines. Rescaling the baselines with the same anchor area corrects their median but leaves larger errors (range 0.20-4.34). Cell-level probabilities remain too extreme (calibration slope 0.59). Compared with the best neutralised model, AUC is higher on Iburi (by 0.03-0.07) and lower on Gorkha and Haiti (by 0.01-0.05). Transplant experiments tie the Iburi advantage to the structure of its true landslide pattern, not to its terrain or road network. In all eight settings with a low interaction gap, computable from biased records, neutralisation was at least as accurate, including a prespecified test on Haiti; a high gap did not guarantee an advantage. The real Gorkha inventories are slope-biased, not road-biased, and there the model brings no meaningful gain. Report-based catalogues remain the main untested case.

cs.CV

新论文 · v1arXiv:2611.12436

Patching Up Circuit Learning via Parameter Sharing

Charles Bricout, Gennaro Gala, Viacheslav Borovitskiy, Antonio Vergari

原文摘要

Probabilistic circuits (PCs) have emerged as generative models guaranteeing tractable probabilistic inference. However, tractability comes at the price of larger model sizes than in other generative models. As such, to scale PCs to high-dimensional data such as images, previous work has devised several parameter sharing techniques as well as fast evaluation protocols that consider learning PCs on independent image patches. In this work, we revisit this practice to highlight a surprising learnability issue: models that assume independence counterintuitively can yield better likelihoods than models that do not. To break this apparent bottleneck and to scale PCs further, we introduce a recursive parameter sharing construction (RePA) that fosters efficiency without assuming independence. We show empirically that RePA can greatly reduce time and memory consumption while yielding competitive likelihoods. Inspired by these results, we further generalize the approach to data modalities that do not inherently exhibit patch-structure (NoPA), such as tabular data, showing similar efficiency improvements, with marginal changes in likelihoods and sample quality on seven tabular datasets. Code available at https://github.com/april-tools/RePA.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12435

To SIMD or Not to SIMD: Comparing RVV vs. CGRA SoCs for Non-Linear Functions in AI

Sameer Deshmukh, Naoya Mizuki, Takumi Honda

原文摘要

Non-linear functions are an important class of operations in modern large language models. However, chip vendors building for AI have so far relied on traditional vector or scalar processing units for non-linear functions. The performance of these units has not kept pace with matrix multiplication units (MMUs), which can be found in both high-performance and edge-computing devices from almost every vendor. Reconfigurable units such as FPGAs and CGRAs have been proposed in the literature, but have not been systematically compared with traditional units backed by MMUs. In this paper, we build two SoCs: one using an RVV vector processor and the other using a latency-insensitive (\emph{elastic}) CGRA, both coupled with an MMU and driven by a single-core CPU. We then propose mappings for common feed-forward networks on our SoCs and find that the CGRA reaches a maximum speedup in clock cycles of 7.12x over RVV on the activation stage of simple point-wise non-linear functions like SiLU, whereas the RVV reaches a maximum speedup of \textbf{9.8x} over the CGRA on complex non-linear functions such as $\mathrm{softmax}$. Over the enclosing feed-forward block the corresponding maxima are 3.16x and 4.24x.

cs.AR · cs.AI