跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 06:11 — 2026-11-22 06:11(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

论文修订列表

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 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v3arXiv:2603.13780

Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR

Kai Tan, Lin Zhang, Ruiteng Zhang, Johan Rohdin, Leibny Paola García-Perera, Zexin Cai, Sanjeev Khudanpur, Matthew Wiesner 等 9 位作者

原文摘要

Spoofing-robust automatic speaker verification (SASV) aims to integrate automatic speaker verification (ASV) and countermeasure (CM). A popular solution is fusion of independent ASV and CM scores. To better modeling SASV, some frameworks integrate ASV and CM within a single network. However, these solutions are typically bi-encoder based, offer limited interpretability, and cannot be readily adapted to new evaluation parameters without retraining. Based on this, we propose a unified end-to-end framework via a three-class formulation that enables log-likelihood ratio (LLR) inference from class logits for a more interpretable decision pipeline. Experiments show comparable performance to existing methods on ASVSpoof5 and better results on SpoofCeleb. The visualization and analysis also prove that the three-class reformulation provides more interpretability.

eess.AS · cs.SD

版本更新 · v2arXiv:2610.28465

MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy

Raúl Castilla-Arquillo, Miguel Olivares-Mendez

原文摘要

Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations produce long, high-contrast shadows that challenge stereo vision, terrain segmentation, and localization. Developing perception and navigation algorithms for these conditions requires large amounts of sensor data with accurate ground truth, which field campaigns and analog facilities can only provide at high cost and with limited variety. This paper presents MARE (Modular Autonomy and Rendering Environment), an open-source simulation suite for lunar rover perception and autonomy built on Unreal Engine 5 and ROS 2. MARE consists of three integrated components. Terrain Studio generates cratered and rocky lunar Digital Elevation Maps (DEMs) to build simulation scenes. A dedicated Unreal Engine project hosts two physics-based rovers with plugins for stereo, lidar, event, and Single-Photon Avalanche Diode (SPAD) cameras, streaming time-stamped sensor data and pixel-accurate ground truth. Lastly, a Guidance, Navigation, and Control (GNC) stack provides web-based mission control. Validation shows a mean Intersection over Union (IoU) of 0.79 between predicted and rendered shadows at low sun elevations, and stereo depth analysis verifies decreased pixel coverage in shadowed regions relative to sunlit terrain.

cs.RO

版本更新 · v2arXiv:2610.35128

STeP-TS: Shared Temporal Filters with Pruning for Time Series

Hanne Raum, Jasper Hoffmann, Joschka Boedecker

原文摘要

Multivariate time series forecasting requires capturing temporal dependencies across multiple scales while accounting for both shared and variable-specific dynamics. Compact forecasting models have emerged as an attractive alternative to increasingly large architectures, but preserving strong predictive performance within tight computational and memory budgets remains challenging. We propose a compact one-layer convolutional framework that learns a shared bank of multi-scale temporal filters of each variable. Lightweight variable-specific scalar weights determine the contribution of each temporal component, enabling the model to capture shared temporal structure while adapting to variable-specific dynamics. The learned weights and filter-output energy further provide a natural signal for structured pruning of convolutional filters, reducing computational complexity with minimal degradation in forecasting performance. We additionally introduce an amplitude-adaptive normalization mechanism that preserves variable-dependent temporal amplitudes. Experiments on multiple datasets demonstrate forecasting performance competitive with state-of-the-art methods while requiring substantially fewer parameters and inference FLOPs and achieving low per-sample latency.

cs.LG

版本更新 · v5arXiv:2602.00122

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

Hongzhu Yi, Yujia Yang, Yuanxiang Wang, Tong Li, Zhenyu Guan, Tianyu Zong, Jiahuan Chen, Chenxi Bao 等 21 位作者

原文摘要

Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. We introduce VDE Bench, an evaluation resource for studying instruction-guided editing of Chinese and English document images. VDE Bench contains 3,506 instruction-guided image editing samples, including 1,578 text-region edits and 1,928 table-region edits. The benchmark pairs editing instructions and reference images with annotated editing regions and structured OCR outputs. Its evaluation protocol combines region-level and full-page measurements to assess textual correctness, structural fidelity, and visual content preservation. By focusing on the interaction between local edits and their surrounding document context, VDE Bench complements existing visual text editing benchmarks and provides a resource for diagnosing document-specific editing failures.

cs.CV · cs.AI · cs.MM

版本更新 · v3arXiv:2605.13470

Twincher: Towards Robust and Precise Physical AI via Bijective Representation Learning

Arkady Gonoskov

原文摘要

Perception and planning in physical systems often require inverting a continuous forward map $p \mapsto y = f(p)$, e.g., a renderer or a simulator, that can be queried but not inverted in closed form. Learned inverses are limited by their approximation error, whereas iterative solvers in observation space can stall at spurious stationary points. We instead learn a representation $r(y)$, insensitive to perturbations of $y$ normal to the data manifold, in which $p \mapsto r(f(p))$ is a well-conditioned bijection. In these coordinates, the least-squares inverse problem has no spurious interior stationary points, so that Gauss-Newton iteration with the exact forward model converges to the accuracy the data permit; the learned model need only be qualitatively correct. We introduce Twincher, an exactly invertible architecture of localized area-preserving rotations, trained with Jacobian-level objectives and a domain-growing curriculum. On synthetic maps with tunable nonconvexity, the worst-case residual reaches machine precision within five iterations once the query budget suffices, whereas an MLP-based baseline improves only gradually. In 6D localization of industrial objects in real depth images of the MVTec ITODD benchmark, given instance masks, twinchers trained only on CAD renderings make the iteration converge from a fixed initial guess within a few steps, without feature matching, pose regression, or pose hypotheses; in observation space, the same iteration fails for up to half of the views. All validation poses pass the strictest BOP thresholds and fit the sensor data about as closely as the ground-truth poses; 80\% of all 239 instances (67\% with visible masks only) are solved in agreement with the sensor data, and the number of training iterations grew only 1.5-fold from two to four pose parameters. Code is open source.

cs.LG

版本更新 · v2arXiv:2505.13004

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Yuhao Qing, Boyu Zhu, Mingzhe Du, Zhijiang Guo, Terry Yue Zhuo, Qianru Zhang, Jie M. Zhang, Heming Cui 等 12 位作者

原文摘要

Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To address this gap, we introduce EffiBench-X, the first multi-language benchmark designed to measure the efficiency of LLM-generated code. EffiBench-X supports Python, C++, Java, JavaScript, Ruby, and Golang. It comprises competitive programming tasks with human-expert solutions as efficiency baselines. Evaluating state-of-the-art LLMs on EffiBench-X reveals that while models generate functionally correct code, they consistently underperform human experts in efficiency. Even the most efficient LLM-generated solutions (Qwen3-32B) achieve only around \textbf{62\%} of human efficiency on average, with significant language-specific variations. LLMs show better efficiency in Python, Ruby, and JavaScript than in Java, C++, and Golang. For instance, DeepSeek-R1's Python code is significantly more efficient than its Java code. These results highlight the critical need for research into LLM optimization techniques to improve code efficiency across diverse languages. The dataset and evaluation infrastructure are submitted and available at https://github.com/EffiBench/EffiBench-X.git and https://huggingface.co/datasets/EffiBench/effibench-x.

cs.CL

版本更新 · v2arXiv:2606.05758

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

Zhuoming Liu, Jinhong Lin, Kwan Man Cheng, Lin Zhang, Shayok Bagchi, Yin Li

原文摘要

Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretraining and strong zero-shot generalization across diverse tasks, they are poorly suited for problems that require precise continuous outputs, such as localizing temporal boundaries of events or generating robotic control actions. To address this challenge, we propose DRIFT, a general framework for adapting pretrained VLMs to continuous decoding tasks. DRIFT combines a base predictor, which provides a coarse estimate of the target output, with a generative refinement module based on flow matching that iteratively improves the prediction. This residual formulation transforms the generative modeling problem from learning a global output distribution to modeling a localized residual distribution around a strong prior, substantially simplifying optimization. We evaluate DRIFT on both perception and planning tasks, including visual grounding and robotic control. Across multiple tasks and architectures spanning MLLMs, VLAs, and WAMs, DRIFT consistently outperforms a strong set of regression- and generative-based solutions.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2610.24045

What Remains Without Leaking Test Labels? Exposing Evaluation Flaws in Graph-Level Anomaly Detection

Yujie Lu, Da Yan

原文摘要

Graph-level anomaly detection (GLAD) identifies unusual graphs in applications such as molecular screening, often using only normal graphs for training. Yet the evaluations of some detectors select models with test labels, and high benchmark scores alone do not show whether detectors recognize structural changes. We audit released code and compare the area under the receiver operating characteristic curve (AUROC) for model states (checkpoints) chosen with and without test labels from the same training run. We separately compare test-tuned hyperparameters with repository defaults and test sensitivity to structural changes while controlling graph size. We evaluate 21 detectors on the UB-GOLD benchmark and on synthetic and molecular graphs with controlled structural changes. About half of the checkpoint-selection gain is linked to choosing a checkpoint and reporting its performance on the same labeled test set. The mean gap persists across training seeds and when normal and anomalous graphs come from different datasets. Most detectors miss many tested structural changes that simple counts detect. With tuned hyperparameters, the two leaders remain the top two by AUROC under every checkpoint rule. Across nine main datasets, test-label checkpoint selection raises the mean AUROC of UB-GOLD's 12 detectors by 5.12 points relative to the final checkpoint.

cs.LG · cs.SI

版本更新 · v2arXiv:2610.02466

SD-DPC: Sparse Dictionary Differentiable Predictive Control

Ali Reza Daneshvar Garmroodi, Jan Drgoňa

原文摘要

We present sparse dictionary differentiable predictive control (SD-DPC), a framework for learning sparse, interpretable feedback policies for nonlinear systems from data. A prediction model is first identified by rollout-based sparse identification of nonlinear dynamics (SINDy), building on gradient-based and multistep formulations. The policy is then parameterized as a sparse combination of dictionary functions and trained by differentiating a constrained finite-horizon predictive-control objective through this model, so that its terms are selected by closed-loop performance rather than by imitating a previously trained controller. The result is an explicit feedback law with only a handful of terms. Across three benchmark control problems, SD-DPC satisfies the constraints in almost all test scenarios, outperforms a policy distilled onto the same terms by up to an order of magnitude, and requires orders of magnitude less memory and online computation than an optimization benchmark, while admitting explicit sensitivity bounds.

eess.SY · cs.LG · math.OC

版本更新 · v9arXiv:2507.04346

Action-Increment-Constrained Policy Optimization for Smooth Online Adaptive Critic Flight Control with Actuator Rate Constraints and Low Computational Complexity (extended version with Ultimate Uniform Boundedness analysis)

Yifei Li, Erik-Jan van Kampen

原文摘要

Approximate Dynamic Programming (ADP) enables online control-law adaptation through adaptive critic methods. A safety challenge in applying ADP to angle-of-attack (AoA) tracking control is that an overly sensitive neural network (NN) controller may generate oscillatory or saturated control actions under nonlinear dynamics, potentially compromising flight stability and increasing actuator stress. To address this challenge, this paper proposes two innovations: (1) the actuator rate constraints are enforced within a an Action-Increment-Constrained Policy Optimization (AI-CPO) framework inspired by safe reinforcement learning (RL), in which a primal-dual approach adaptively adjusts the penalty weight to address actuator rate constraints. This optimization is solved online using adaptive Temporally Smoothed Incremental Model-Based Heuristic Dynamic Programming (TS-IHDP) for smooth and computationally efficient online adaptive control; and (2) a low-pass filter integrated into the cascaded NN architecture to attenuate high-frequency pitch-rate commands while preserving the Markov property during online learning by exploiting the hierarchical actor structure. Compared with the IHDP baseline, simulations using a longitudinal air vehicle dynamics model demonstrate that TS-IHDP improves control smoothness and tracking performance, reduces system oscillations, and enhances the trained policy's robustness to model uncertainties.

eess.SY · cs.AI

版本更新 · v2arXiv:2604.14809

Expert-Guided Class-Conditional Goodness-of-Fit Scores for Interpretable Classification with Informative Missingness

Shahar Cohen, David M. Steinberg, Yael Radzyner, Yochai Ben Horin

原文摘要

We study a classification problem with three key challenges: pervasive informative missingness, the integration of partial prior expert knowledge into the learning process, and the need for interpretable decision rules. We propose a framework that encodes prior knowledge through an expert-guided class-conditional model for one or more classes, and use this model to construct a small set of interpretable goodness-of-fit features. The features quantify how well the observed data agree with the expert model, isolating the contributions of different aspects of the data, including both observed and missing components. These features are combined with a few transparent auxiliary summaries in a simple discriminative classifier, resulting in a decision rule that is easy to inspect and justify. We develop and apply the framework in the context of seismic monitoring used to assess compliance with the Comprehensive Nuclear-Test-Ban Treaty. We show that the method has strong potential as a transparent screening tool, reducing workload for expert analysts. A simulation designed to isolate the contribution of the proposed framework shows that this interpretable expert-guided method can even outperform strong standard machine-learning classifiers, particularly when training samples are small.

stat.ML · cs.LG · stat.AP

版本更新 · v2arXiv:2610.24764

BanglaBBQ: A Bias Benchmark for Question Answering in the Bangladeshi Context

Sumit Anthony Gomes, Yasin Rahman, Taeeba Tasnia, Faiza Nooren Suhita

原文摘要

This paper presents BanglaBBQ, a question-answering bias benchmark designed to capture stereotypes grounded in the Bangladeshi context, in both Bangla and English. Following KoBBQ and PakBBQ, BanglaBBQ adapts the original Bias Benchmark for Question Answering (BBQ) by classifying its templates into three groups: directly translated (DT), modified to align target groups or contexts with Bangladesh (TM), and removed when deemed unsuitable for the Bangladeshi context (SR). This process retains 140 templates across six categories, comprising 76 DT and 64 TM templates. Five newly authored (NA) categories, based on stereotypes common in Bangladeshi society, are then added: marital status, age and political perception, regional origin, educational background, and mental-health status. Native Bangladeshi annotators judged all 466 newly authored templates, and 372 were retained because a strict majority of English annotators identified the intended target and rated the attitude as common enough. Each newly authored template is linked to a documented source and a verbatim quote from it. Each evaluated template also has a counter-stereotypical version of its disambiguated context. The dataset was evaluated using two open-weight models (Qwen3-4B and Qwen3-8B) and two closed models (GPT-4.1-mini and Gemini 2.5 Flash). All four lean towards the stereotyped person when the context is ambiguous, in both languages, and the effect of language differs by model, so English results do not predict behaviour in Bangla. On the adapted BBQ templates, both Qwen3 models are also less accurate when the context contradicts a stereotype than when it confirms it. On the newly authored templates, the closed models follow counter-stereotypical evidence almost perfectly, and all four models are more biased on the templates that annotators validated than on those they rejected.

cs.CL

版本更新 · v3arXiv:2503.04956

Foreclassing: From Forecasts to Decisions

Daniel Andrew Coulson, Martin T. Wells

原文摘要

Time series forecasts are widely used to inform decisions under uncertainty. In many applications, these decisions involve classifying a time series based on outcomes that have yet to be observed. In this paper, we introduce Foreclassing, a new machine learning problem in which the class label of a time series is defined as a function of its future observations. We provide a mathematical formulation of Foreclassing and establish several theoretical results characterizing the problem. These results describe how additional future information affects Bayes classification risk, provide bounds on the classification error of learned Foreclassing models, and demonstrate how future observations used during training can yield finite-sample improvements over conventional classifiers. To provide a benchmark for future research, we propose ForeClassNet, a family of neural network models that jointly perform forecasting and classification while accounting for uncertainty in future outcomes. We investigate a variety of model architectures and evaluate their performance against conventional time series classifiers and forecasting-then-classify approaches. Experiments on datasets spanning weather, energy, and finance demonstrate the potential of Foreclassing to improve classification performance, probabilistic prediction, and downstream decision-making. Together, these theoretical and empirical contributions establish a foundation for future research on Foreclassing.

stat.ML · cs.LG

版本更新 · v2arXiv:2605.30058

HEART-Bench: Do LLMs Make Persona-Consistent Decisions?

Weihan Peng, Chenxu Zhang, Qianao Wang, Yuling Shi, Heng Lian, Qihong Mao, Jiahao Pang, Chunliang Feng 等 10 位作者

原文摘要

LLM agents in interactive entertainment and social applications, including companions, role-play characters, and persona clones, need decisions grounded in personality and past experiences. We introduce HEART-Bench to evaluate memory-grounded persona-consistent response selection. The benchmark combines 11 Big Five-anchored synthetic characters, each with 1,000 autobiographical memories, and 64 DIAMONDS-guided decision scenarios into 673 multiple-choice questions. Domain experts independently compare candidate responses, with a senior expert resolving disagreements and revising responses when needed; other characters' adjudicated responses to the same scenario serve as distractors. In the main evaluation, models receive character IDs and occupations, scenarios, and options, with retrieved memories added in memory-augmented settings. Detailed personality-and-value profiles are withheld. We evaluate 16 LLMs under No-Retrieval, Naive-RAG, Mem0, and PersonaDB. Accuracy without memories stays near the 25% chance level, and the best memory-augmented configuration reaches 64.9%. On a matched 150-item subset, human annotators reach 80.8%, compared with 64.0% for the best model. Memory-content ablations show the importance of retrieving experiences that match both the target character and the decision context.

cs.CL

版本更新 · v3arXiv:2604.18215

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Yanjun Guo, Zhengqiang Zhang, Pengfei Wang, Xinyue Liang, Zhiyuan Ma, Lei Zhang

原文摘要

Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent content during scene revisits and diminished generative capacity when exploring novel regions, even when trained on extensive annotated data. To address these limitations, we propose a decoupled framework that separates memory conditioning from generation. Our approach significantly reduces training costs while simultaneously enhancing spatial consistency and preserving the generative capacity for novel scene exploration. Specifically, we employ a lightweight, independent memory branch to learn precise spatial consistency from historical observations. We first introduce a hybrid memory representation to capture complementary temporal and spatial cues from generated frames, then leverage a per-frame cross-attention mechanism to ensure each frame is conditioned exclusively on the most spatially relevant historical information, which is injected into the generative model to ensure spatial consistency. When generating new scenes, a camera-aware gating mechanism is proposed to mediate the interaction between memory and generation modules, enabling memory conditioning only when meaningful historical references exist. Compared with the existing method, our method is highly data-efficient, yet the experiments demonstrate that our approach achieves state-of-the-art performance in terms of both visual quality and spatial consistency. Project page can be found at https://iguoyanjun.github.io/memorize-when-needed-project-page/.

cs.CV

版本更新 · v2arXiv:2605.09552

Phases of Muon: When Muon Eclipses SignSGD

Elliot Paquette, Noah Marshall, Lucas Benigni, Guangyuan Wang, Atish Agarwala, Courtney Paquette

原文摘要

Muon and related spectral optimizers have recently demonstrated strong empirical performance as scalable stochastic methods, often outperforming Adam. Yet their behavior remains poorly understood. We analyze stochastic Muon, which orthogonalizes an exponential moving average of minibatch gradients, on a high-dimensional matrix-valued least squares problem, and we compare it with stochastic SignSGD, a simple baseline comparable to Adam. We derive explicit deterministic dynamics that provide a tractable framework for studying learning behavior. We show that Muon has non-linear sensitivity to the effective batch $B_{\rm eff}=B(1+β)/(1-β)$. With exact whitening and small $B_{\rm eff}$ Muon fails to resolve smaller eigenmodes, slowing down convergence. Momentum and finite Newton--Shulz iterations can act as a ridge which lessen this effect. This behavior is in contrast with SignSGD which has no transition, leading to different optimal learning rates, but with matching convergence rate up to a constant factor in the isotropic setting. For anisotropic data, large batch setting Muon performs a square-root preconditioning with respect to the data covariance spectrum while SignSGD provides no preconditioning for generic covariances. We analyze time to target loss in a power law covariance model and derive a phase diagram in the data exponent $α$ and target exponent $ζ$. Muon is favored for steep covariance spectra with rich targets ($α>2$, $ζ<α+1$), SignSGD is favored for flat spectra ($α<1$), and in other regions the winner depends on how the target loss scales with dimension. Our results shed light on why replacing Adam with Muon is not trivial even from a pure optimization perspective.

math.OC · cs.LG · stat.ML

版本更新 · v3arXiv:2507.16648

An Unconditional Lower Bound for the Active-Set Method in Almost-Linear Programming

Eleon Bach, Yann Disser, Sophie Huiberts, Nils Mosis

原文摘要

We prove that, for every fixed $ε\in(0,1]$, the active-set method requires exponentially many iterations in the worst case to maximize a convex objective of the form $(x_1)^{1+ε}+\vec c^{\top}\vec x$ subject to linear constraints, regardless of the pivot rule used. Our lower bound therefore holds for objectives arbitrarily close to the linear case $ε=0$, where the active-set method coincides with the simplex method and a lower bound for all pivot rules would constitute a major breakthrough. The special case $ε=1$ yields a lower bound in convex quadratic maximization. This improves on the best previously known lower bound [IPCO 2025] requiring polynomial objectives of degree $ω(\log d)$ in dimension $d$ and firmly resolves the open question of whether a constant degree suffices. Our result is based on a novel extended formulation, recursively constructed using deformed products. Its key feature is that it projects onto a polygonal approximation of a parabola while preserving all of its exponentially many vertices. We define a convex objective with a single non-linear variable that forces the active-set method to follow the parabolic boundary of this projection, without allowing any shortcuts along chords corresponding to edges of its full-dimensional preimage.

cs.DM · cs.CC · cs.DS · math.CO

版本更新 · v2arXiv:2502.04309

Targeted Learning for Inference on Data Fairness

Joseph H. Rudoler, Alexander Asemota, Giles Hooker

原文摘要

As algorithmic decision making has become increasingly ubiquitous even in high-stakes settings, significant effort has been invested in defining, detecting, and eliminating unfair model-driven outcomes. Prior work has largely focused on estimating the fairness properties of a given predictive model, and quantifying uncertainty based on variability in a fixed model's performance across evaluation datasets. Alternatively, we can also ask about uncertainty that the model inherits from its training data; here we evaluate data fairness - fairness in the data generating process used for training. We perform inference on data fairness using targeted learning, a flexible framework for nonparametric inference, and derive estimators for demographic parity, equal opportunity, and conditional mutual information. Simulations show that our data fairness estimators improve confidence-interval coverage and reduce false detections of population unfairness relative to fixed-model inference. We also demonstrate their application to real data.

cs.LG · stat.ML

版本更新 · v2arXiv:2605.18007

Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling

Anas Belfathi, Nicolas Hernandez, Laura Monceaux, Warren Bonnard, Richard Dufour

原文摘要

Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on hard examples, where prediction confidence is low. Existing approaches typically handle uncertainty implicitly and treat labels as discrete identifiers, overlooking the semantic information encoded in label names. We introduce RISE, an inference-time semantic reranking framework that leverages label semantics to refine predictions on hard instances. RISE automatically identifies low-confidence predictions and reranks model outputs using contrastively learned label representations, without retraining or modifying the underlying model. Experiments on eight domain-specific RRL datasets with seven LMs, including encoder-based and causal architectures, show an average gain of +9.15 macro-F1 points on hard examples. For explainability, we further propose manual hardness annotations to study difficulty from both model and human perspectives, revealing a moderate agreement with Cohen's kappa = 0.40.

cs.CL

版本更新 · v2arXiv:2610.33460

Semantic-First: Temporal Scheduling in Flow Matching for Reliable Emotional Image Generation

Zhenxuan Wang

原文摘要

Affect-controlled image generation should change how a scene feels while preserving what the prompt specifies. We study the temporal allocation of stochastic exploration and policy optimization in flow-matching models as a means of controlling this balance. During RL training, our semantic-first schedule uses deterministic ordinary differential equation (ODE) sampling during the high-noise phase and confines stochastic differential equation (SDE) exploration and group relative policy optimization (GRPO) to a late window. Controlled experiments separate exploration location, optimization location, and terminal-step sampling, showing distinct semantic benefits from late exploration and late updates. On FLUX.1-dev, semantic-first improves prompt faithfulness, independently evaluated affect accuracy, and human-rated semantic preservation and overall preference. The expanded semantic audit records 2.7% subject drift, while GRPO training time decreases by 41.1% relative to original full-path Flow-GRPO. Window-width experiments characterize the affect-semantic and computational trade-offs, and replication on SD3.5-Medium reproduces the scheduling advantage. These results establish denoising time as a practical control dimension for reliable emotional image generation.

cs.CV

版本更新 · v2arXiv:2607.10697

A Better Analysis For PPSZ For 3-SAT

Tao Jiang, Shaowei Cai

原文摘要

The PPSZ algorithm of Paturi, Pudlák, Saks, and Zane solves 3-SAT by processing the variables in a uniformly random order, setting a variable whenever a bounded number of clauses implies its value, and guessing it otherwise. Its running time is determined by how many variables are forced in this process, and the exact exponent is a central question in the study of exponential-time satisfiability algorithms. Scheder showed that the classical analysis of PPSZ is not tight for 3-SAT. We ask how much further a sharper analysis of the unmodified algorithm can go. Our analysis uses auxiliary distributions on variable orderings that correlate the positions of variables sharing critical clauses. Such correlations make forcing more likely for some variables, can make it less likely for others, and incur an entropy cost. We choose the correlated pairs at random on short components, so that every pair is selected with the same probability, and we express the forcing loss as a sum of weights attached to these pairs in advance. Gains and losses then scale by the same factor and can be compared directly. Combining the resulting estimate with the complementary estimate of Scheder through an explicit linear-programming certificate gives a uniform improvement for every uniquely satisfiable formula. We prove that the original PPSZ algorithm, with a sufficiently large but fixed implication strength, solves Unique-3-SAT in randomized time $O^*(1.306969598^n)$. Through the lifting framework of Scheder and Steinberger, it solves general 3-SAT in randomized time $O^*(1.307031578^n)$. Both bounds improve the guarantees obtained from the analysis of Scheder for the same algorithm. These improvements follow entirely from the analysis, while PPSZ continues to use a uniformly random variable order and unbiased guesses. It shows that the known guarantees for PPSZ can be strengthened by analysis alone.

cs.DS

版本更新 · v2arXiv:2608.02343

Hard Constraints, Smooth Gradients: Learning Feasible Inventory Policies via Differentiable Projection

Patrick Helm, Jan-Niklas Doerr, Joren Gijsbrechts, Stefan Minner

原文摘要

Many operational problems are constrained sequential decision processes with combinatorial action spaces and interdependent constraints. Mixed-integer linear programs (MILPs) handle such constraints flexibly but scale poorly in stochastic environments. Deep reinforcement learning (DRL) promises scalable decision rules, but existing methods either penalize constraints rather than enforce them, or rely on feasibility mechanisms that break down once constraints interact. We bridge this gap by embedding a differentiable optimization module inside the policy: a neural network proposes continuous action targets, a quadratic program projects them onto the relaxed feasible set, and a dual-informed integer mapping restores integrality while preserving feasibility. Given a differentiable simulator, the policy trains end-to-end from sampled trajectories using pathwise gradients, while handling hard constraints with similar flexibility to MILPs. We show that our approach has bounded error relative to an exact integer projection and ensures the entire feasible action space is reachable. We apply the method to multi-echelon production-inventory planning under shared resource and material constraints. Our policy attains an average optimality gap of 1% on 3-item instances and consistently outperforms a rolling-horizon multi-stage stochastic program by at least 5.6% in 10-item networks. Compared to state-of-the-art echelon base-stock policies, savings reach 15.3% on 40-item instances. On an industry-scale case study with nonstationary demand from ASML, we reduce average cost by up to 1.8% relative to the best-known benchmark policy. The savings are largest where planning is hardest: in tightly capacitated systems with high demand variability. More broadly, we show that DRL can improve upon state-of-the-art baselines in sequential decision problems with hard constraints, which are widespread in practice.

cs.AI · cs.LG

版本更新 · v3arXiv:2412.07672

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization

Xiaoqun Liu, Weiming Qi, Qiben Yan

原文摘要

Large language models (LLMs) remain vulnerable to jailbreak attacks in which adversarial prompts induce harmful outputs. Existing defenses often require access to the model internals or additional training, limiting their applicability for service providers deployed through black-box APIs. In this paper, we propose DYNASHIELD, a moving target defense framework that improves robustness by customizing decoding hyperparameters and system prompts at inference time. DYNASHIELD includes two key steps: (1) it identifies decoding configurations that reduce attack success probability, and (2) it probabilistically samples from a weighted configuration pool to introduce controlled variability in model behavior. We evaluate DYNASHIELD across 7 open-source LLMs under 4 state-of-the-art jailbreak attacks, using adversarial prompts from AdvBench. Results show substantial reductions in attack success rate compared with 7 baseline defenses, while maintaining response quality and incurring minimal inference overhead. Because DYNASHIELD operates solely through exposed runtime controls, it requires no retraining or model-internal access. These results suggest that safety-aware dynamic decoding is a promising and practically lightweight defense mechanism for black-box LLM deployments.

cs.CR · cs.CL

版本更新 · v3arXiv:2508.20729

Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision

Ao Cheng, Lei Zhang, Guowei He

原文摘要

Large language models (LLMs) have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this work, we construct a novel agent framework for solving representative problems in scientific computing. The proposed agent incorporates a "rewriting-resolution-review-revision" logical chain via three reasoning LLMs (the Consultant, Reviewer, and Programmer) in a collaborative and interactive manner. The Consultant module enables knowledge transfer to link problems to professional domain insights, thereby rewriting problem descriptions through text augmentation. The Programmer module generates and executes well-structured code to solve problems. The Reviewer module enables self-debugging and self-refinement through interactive feedback with code runtime outputs. Through the end-to-end review mechanism, the Programmer's executable code undergoes iterative revision. We comprehensively evaluate the framework on typical partial differential equations (PDEs), engineering-oriented flow past a cylinder, ill-conditioned linear systems, and data-driven physical analysis problems. Compared with a single-model approach, this collaborative framework significantly improves the bug-free code generation rate and reduces non-physical solutions, establishing a reliable framework for autonomous code generation from natural language descriptions. The review mechanism improved the average execution success (bug-free code and non-NaN solutions) rate of DeepSeek R1 from 59% to 82%, while ChatGPT 4.1-mini improved from 66% to 87% and Gemini-2.5 improved from 60% to 84%. Automatic code generation and review provide a promising workflow for scientific computing; analysis of solver-development trajectories further reveals recurring implementation difficulties in boundary treatment, array indexing, and the preservation of numerical constraints.

cs.AI

版本更新 · v2arXiv:2606.14627

Algebraic Operations on Tensor Trains

Petr Tichavsky

原文摘要

The tensor train (TT) model is widely used to approximate high-dimensional tensors, enabling efficient handling of data that may exceed available memory. TT helps address the curse of dimensionality in applications such as system identification and dynamic programming. In some applications, TT is known as a ``matrix product state" (MPS). The last product is also known under the acronym MPO--MPS. The proposed algorithms achieve an improved trade-off between computational efficiency and accuracy compared to state-of-the-art methods.

cs.CE

版本更新 · v2arXiv:2609.38208

CraftSPH: A composable framework for differentiable smoothed particle hydrodynamics implemented in PyTorch

Gen Matono, Shujiro Fujioka, Mayuko Nishio

原文摘要

Smoothed particle hydrodynamics (SPH) is well suited to large-deformation fluid problems, and the growing use of automatic differentiation in engineering applications has motivated interest in differentiable SPH solvers. In this study, a composable differentiable SPH framework, CraftSPH, has been developed. In CraftSPH, major computational operations are implemented as independent modules that users can combine to construct solvers for different purposes. This design supports high-accuracy discretization and both explicit and implicit computation within a common framework, while allowing individual components to be maintained and extended. Selected numerical operations also support automatic differentiation (AD) for physical-parameter estimation and potential coupling with deep learning models. These capabilities were demonstrated through forward and inverse analyses. Forward analyses using an implicit SPH scheme with high-accuracy discretization showed good agreement with analytical and reference solutions for Poiseuille flow and a rising bubble, while capturing the key experimental trends in two- and three-dimensional dam-break problems. In inverse analyses, explicit and implicit SPH schemes were used to estimate kinematic viscosity in Taylor-Green vortex flow and Reynolds number in lid-driven cavity flow. The results also showed that the choice of operations included in the computational graph affects the computed gradients. Together, these findings demonstrate that CraftSPH enables users to assemble problem-specific solvers for forward and inverse analyses within a common framework.

cs.LG · math.NA

版本更新 · v2arXiv:2608.08984

SoftMCC: An MCC-Brier Calibration Bridge for Threshold-Free Model Selection under Class Imbalance

Özkan Canay

原文摘要

Model selection for imbalanced binary classification often uses the Matthews correlation coefficient (MCC), but its thresholding step makes validation rankings depend on the chosen cutoff. SoftMCC is a post-training MCC validation framework built on established probability-valued confusion counts, coupling an MCC-specific calibrated identity with a tie-aware, shared-pool selection protocol. Its core score is a covariance-normalized probability-label association, reduces exactly to MCC for hard predictions, and is Pearson-bounded. Under perfect population calibration it equals the Brier skill score with identical candidate ordering, which is the calibrated case of Murphy's partition of the Brier score. Outside that regime the gap does not identify calibration error. Across 18 settings with 12 duplicate-safe grouped repeats, SoftMCC attains the best stability mean rank (2.31) and highest mean tie-corrected Kendall's W (0.659), with a significant Friedman test (p=0.004). Nemenyi analysis separates it from area under the precision-recall curve (AUPRC) and MCC@0.5, and 14-source-family sensitivity retains both separations. For selected-model utility, none of six prespecified paired comparisons is significant before or after Holm correction (smallest raw p=0.093), and the dataset-level test is not significant (p=0.746). Label permutation lowers mean W to 0.092. Temperature scaling shifts SoftMCC rankings (mean Spearman 0.851) whereas rank-based and threshold-optimized metrics remain invariant. SoftMCC is a calibration-sensitive MCC-family selector with bounded stability evidence and inconclusive utility differences.

cs.LG

版本更新 · v2arXiv:2601.13401

SQuID: A Benchmark for Quantitative Spatial Reasoning on Satellite Imagery

Peter A. Massih, Eric Cosatto, Martin Renqiang Min

原文摘要

Vision-Language Models (VLMs) describe satellite images fluently but struggle with the quantitative spatial reasoning that remote sensing (RS) analysts perform routinely, such as counting buildings, measuring forest area in hectares and computing distances in meters. We introduce SQuID (Satellite Quantitative Intelligence Dataset), a benchmark of 2,000 questions over 587 images from four sources at 0.3 to 1.0 m ground sampling distance, covering 24 question types in three difficulty tiers. Answers are computed from curated segmentation masks or, for 50 questions, from human consensus, and numeric answers are scored against tolerance ranges informed by human annotations. SQuID also releases the reference masks behind its answers, so that modular systems can be evaluated using reference rather than predicted masks, and 75,687 training question-answer pairs on disjoint images (SQuID-Train). Among 15 evaluated systems, the best zero-shot end-to-end VLM reaches 28.1%, and RS-specialized VLMs score lower. As a baseline, we propose QASR (Quantitative Agentic Spatial Reasoning), in which an LLM writes a program that segments the image and measures the masks with geometric operators. QASR reaches 42.0%. On the 1,950 mask-derived questions, running its programs on the reference masks instead of predicted masks raises accuracy from 42.2% to 82.6%, so segmentation is its main source of error. Fine-tuning Qwen2.5-VL-7B on SQuID-Train raises its accuracy from 16.1% to 40.7%, close to QASR. Multi-condition questions (Tier 3) remain the hardest in every setting, at 62.0% for QASR with reference masks and 13.2% after fine-tuning. These results leave clear room for end-to-end models that learn metric spatial reasoning, and SQuID provides the data to train and evaluate them.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.06126

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

Zheng Lian, Fan Zhang, Lan Chen, Yazhou Zhang, Rui Liu, Jinyang Wu, Haoyu Chen, Xiaobai Li 等 11 位作者

原文摘要

Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by predefined label spaces, thereby enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative models to capture the full spectrum of emotions and employs emotion wheels (EWs) for metric calculation. Previous approaches primarily rely on token-level loss during training. However, this objective is misaligned with the metrics used in OV-MER, and these metrics cannot be directly optimized via gradient backpropagation. To address this limitation, we turn our attention to reinforcement learning, as this strategy can optimize non-differentiable objectives. We term this framework AffectGPT-RL. Furthermore, we conduct extensive experiments to elucidate the role of reinforcement learning in this task, revealing the necessity of the reasoning process, the impact of different rewards, and the generalizability to other emotion tasks such as sentiment analysis and basic emotion recognition. Experimental results demonstrate that AffectGPT-RL yields significant performance improvements on OV-MER. Beyond this task, we also achieve remarkable performance gains on basic emotion recognition, attaining state-of-the-art results on MER-UniBench. To the best of our knowledge, this is the pioneering work exploring the role of reinforcement learning in OV-MER, providing valuable guidance for subsequent researchers. Our code is provided at: https://github.com/zeroQiaoba/AffectGPT/tree/master/AffectGPT-RL.

cs.HC

版本更新 · v5arXiv:2603.18740

When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection

Georgios Alexopoulos, Nikolaos Alexopoulos, Diomidis Spinellis, Dimitris Mitropoulos

原文摘要

Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive assistants to autonomous agents in CI/CD pipelines. In this paper, we study how LLM-based vulnerability detection in ACR is affected by the framing effect: the tendency to let the presentation of information override its semantic content in forming judgments. We examine whether adversaries can exploit this through contextual-bias injection (crafting PR metadata to bias ACR security judgments) as a supply-chain attack vector against real-world ACR pipelines. To this end, we first conduct a large-scale exploratory study across 6 LLMs under five framing conditions, establishing the framing effect as a systematic and widespread phenomenon in LLM-based vulnerability detection. We then design a realistic and controlled experimental environment, evaluating 33 CVEs across 20 real-world projects and two popular ACR pipelines (Claude Code and CodeRabbit), to assess the susceptibility of real-world ACR pipelines to vulnerability re-introduction attacks. We employ two attack strategies: a template-based attack inspired by prior related work, and a novel LLM-assisted refinement attack. We find that template-based attacks are ineffective and may even backfire, as direct biasing attempts raise suspicions. Our refinement attack, on the other hand, is successful in 32/33 (97%) cases, exploiting a fundamental asymmetry: attackers can iteratively refine attacks against a local clone of the review pipeline, while defenders have only one chance to detect them. Overall, our findings highlight the dangers of over-relying on ACR and stress the importance of human oversight and contributor trust in the development process.

cs.SE · cs.AI · cs.CR