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

+0新增论文
+0其中 AI 相关
+0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:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 10:39 — 2026-11-16 10:39(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:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 23,348 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:2610.36952

Does More Thinking Pay Off? Reasoning Cost and Correctness of LLMs in Code Generation and Bug Fixing

Andie Huang, Ying Pang, Qian Zhang, Yihang Cheng, Lin Ma

原文摘要

Many LLMs now emit an explicit reasoning trace before they write code, but benchmark results for code generation and bug fixing usually report correctness alone. It is therefore unclear how much the extra reasoning contributes relative to the tokens it consumes. We examine this question with 866 Python tasks drawn from HumanEval Pro, MBPP Pro, and BugsInPy under five model settings. We look at the accuracy gain and token overhead of reasoning, the behaviors that appear inside reasoning traces, and whether a shortened trace still leads to a correct solution. Turning reasoning on in Qwen3-32B over five runs improves mean pass@1 on HumanEval Pro from 71.1% to 76.5% and mean tests pass on BugsInPy from 3.5% to 7.9%. On MBPP Pro the improvement from 68.1% to 69.5% is not statistically significant, even though the model uses a median of over 2,000 thinking tokens per task. Across models, a longer median trace does not reliably mean higher accuracy. A qualitative analysis shows that traces mostly choose and check an implementation in code generation, while in bug fixing they mostly locate the fault and plan the repair. We then truncate stored traces offline and ask Qwen3-32B with reasoning off to produce a solution from what remains. Retaining the first half of a trace yields no statistically significant drop in correctness. Stopping when the trace becomes repetitive seldom triggers, and stopping once solution code first appears benefits some models but harms others. Neither rule beats plain fixed truncation. These results suggest that more reasoning is not always better and that studies should report reasoning cost alongside correctness.

cs.SE

新论文 · v1arXiv:2610.36951

Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection

Augustin Daridon, Sofiane Sifaoui, Ayman Assi, Mohamad Karam, Wafa Skalli, Elsa Angelini, Loic Le Folgoc

原文摘要

Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning. We reframe anatomical landmark detection as a pixel-level contrastive representation learning problem, matching dense pixel embeddings with landmark prototypes. Surprisingly, even with a generic U-Net backbone, this formulation results in more discriminative heatmaps compared to the traditional heatmap regression paradigm, leading to improved discrimination between vertebral corners on distinct vertebra. Furthermore, we combine the resulting heatmaps with learnable shape priors over the global configuration of spinal landmarks to resolve ambiguities in landmark locations, yielding a simple and practical approach to spinal landmark detection. Our approach is competitive, in terms of landmark accuracy and clinical parameter estimation, with the state-of-the-art on the public AASCE dataset and on two private spinal X-ray datasets. Our code and pre-trained weights are available at https://github.com/BioMedTP/Pix2Point.

cs.CV · cs.AI

新论文 · v1arXiv:2610.36950

DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models

Egor Maximov, Aleksei Merkelov, Vasiliy Alekseev, Ivan Krivorotov, Valentin Beliaev, Nikita Arsenin, Dmitry Bocharov, Aleksei Goncharov

原文摘要

Hybrid language models keep a key-value (KV) cache only in their few full-attention layers, but this cache is still the part of a prompt's state that grows with the prompt and that must be stored or moved to reuse it. We present DCKV, a differentiable codec for the KV cache and the first KV-cache codec that is trained end to end. Its transform, its quantizer and its entropy models, which are conditioned on the prompt tokens and on already decoded neighbouring positions, are optimized together against the frozen language model, both for the code length that the entropy models assign and for the change of the model's output. On Qwen3.5-2B, DCKV stores a compressed token in more than 55 times fewer bytes than bf16 at a loss of at most 1.8 points on three long-context benchmarks, and in more than 100 times fewer bytes at a loss of at most 3.6 points.

cs.LG · cs.AI

新论文 · v1arXiv:2610.36948

Self-Keyed In-Parameter Memorization for External Memory-Free Dialogue Recall in Frozen Language Models

XinYu Piao, Myunghoon Ryu, Joongheon Kim, Jong-Kook Kim

原文摘要

A large language model maintains conversational content in an external storage that is outside the model and grows as the dialogue continues. This work assumes an environment where a language model has no external memory and no prior knowledge of the future question or its answer. The motivation is to research whether a dialogue can be stored in the model parameters and later answer a question about it. This work proposes self-keyed in-parameter memorization (SKIM), a closed-form method in which the model generates its own questions about each dialogue turn and writes those questions into its parameters as the keys that later retrieve the turn's content. Generating many varied questions for each turn allows a later user question to match one even when phrased differently, and its answer is recalled from the parameters alone. Evaluated on five language models, SKIM recalls most stored dialogue turns from later user questions, and it answers from the model parameters without any external storage.

cs.CL · cs.AI

版本更新 · v2arXiv:2510.27369

From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cycle

Tosin Adewumi, Martin Karlsson, Marcus Liwicki, Mikael Sjödahl, Lama Alkhaled, Rihab Gargouri, Nudrat Habib

原文摘要

This work presents a systematic review of the application of natural language processing (NLP) along the entire battery life cycle, instead of the review of one stage or method, and introduces a novel conceptual technical language processing (TLP) framework for the European Union (EU)'s proposed digital battery passport (DBP) and other general battery predictions, as the main objective. It follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method and employs three reputable databases or search engines, including Google Scholar, Institute of Electrical and Electronics Engineers Xplore (IEEE Xplore), and Scopus, searched in October, 2025. The search criteria are 'text', 'language processing', and 'battery' while the exclusion criteria are non-relevant papers and those published before 2017, which was applied to all databases, except IEEE Xplore because it turned up fewer results. Consequently, it assesses 274 scientific papers before the critical review of the final 66 relevant papers. We publicly provide artifacts of the review for validation and possible reproducibility. The findings show that new NLP tasks are emerging in the battery domain, which facilitate materials discovery and other stages of the life cycle. Notwithstanding, challenges remain, such as the lack of standard benchmarks. The proposed TLP framework, which incorporates agentic AI and optimized prompts, may be apt for tackling some of the challenges.

cs.CL

新论文 · v1arXiv:2610.36947

Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance

S M Abdulla Al Mamun, Akif Islam, Mohd. Ruhul Ameen

原文摘要

Can additional specialist language-model contexts improve software assurance when deterministic tool evidence is already available? We study this question through five experiments spanning authored Java warning controls, OWASP Benchmark assessment, Defects4J test generation, SV-COMP assertion verdicts, and deliberately misleading evidence packages. The evaluated systems use Qwen2.5-Coder-7B-Instruct, with a 1.5B sensitivity analysis, and complete 13,638 model requests. On eight related development warnings, increasing the context count from 1 to 50 increases token use 49-fold without improving unsafe clearance. On 160 OWASP cases, model configurations trade clearance against unresolved outcomes; the ten-context arm assesses only 96 cases. On 32 SV-COMP tasks, raw verifier feedback raises mean correct model verdicts from 12.7 to 22.0, but also raises incorrect verdicts from one to seven; a JBMC-plus-JVM validation baseline returns 26 correct verdicts and six unresolved outcomes. On two sets of 120 evidence packages, models reject 70-100% of applicable counterexamples, while construction-specific scope checks classify every package correctly. No target defect is discovered in three Defects4J bugs, one unsupported by the test adapter. These descriptive results support deterministic evidence admission for the tested settings, while exposing limits of verdict aggregation, feedback interpretation, and the available evaluation coverage.

cs.SE · cs.AI

版本更新 · v2arXiv:2604.09512

Integrated electro-optic attention nonlinearities for transformers

Luis Mickeler, Kai Lion, Alfonso Nardi, Jost Kellner, Pierre Didier, Bhavin J. Shastri, Niao He, Rachel Grange

原文摘要

Transformers achieve state-of-the-art performance in language processing and computer vision. Their computation increasingly depends on hardware that can keep pace not only with large matrix multiplications, but also with nonlinear operations like Softmax within the core attention mechanism. On digital accelerators, Softmax accounts for only a small fraction of total operations, yet it can disproportionately impact overall inference latency. Here, we use thin-film lithium niobate Mach-Zehnder modulators (MZM) as analog computing elements for low-latency Transformer attention. Our high-speed nonlinearities based on the intrinsic sinusoidal MZM response achieve performance close to digital baselines in Vision Transformers and GPT-2, even under 4-bit input and output quantization. We experimentally characterize the electro-optic response at symbol rates up to 10 GBaud and assess model robustness under corresponding noise conditions. Accounting for the full signal chain, our analysis indicates more than an order of magnitude lower latency relative to previous custom electronic and photonic Softmax implementations. These results establish analog electro-optic devices as nonlinear function units well suited for integration into emerging co-packaged electronic-photonic hardware, offering a path toward high-speed Transformer inference.

cs.LG

版本更新 · v2arXiv:2604.16015

Discovering quantum phenomena with Interpretable Machine Learning

Paulin de Schoulepnikoff, Hendrik Poulsen Nautrup, Hans J. Briegel, Gorka Muñoz-Gil

原文摘要

Interpretable machine learning techniques are becoming essential tools for extracting physical insights from complex quantum data. We build on recent advances in variational autoencoders to demonstrate that such models can learn physically meaningful and interpretable representations from a broad class of unlabeled quantum datasets. From raw measurement data alone, the learned representation reveals rich information about the underlying structure of quantum phase diagrams. We further augment the learning pipeline with symbolic methods, enabling the discovery of compact analytical descriptors that serve as order parameters for the distinct regimes emerging in the learned representations. We demonstrate the framework on experimental Rydberg-atom snapshots, classical shadows of the cluster Ising model, and hybrid discrete-continuous fermionic data, revealing previously unreported phenomena such as a corner-ordering pattern in the Rydberg arrays. These results establish a general framework, which constitutes an important step toward the autonomous discovery of physical descriptors from diverse quantum datasets. All methods are available through qdisc, an open-source Python library designed to make these tools accessible to the broader community.

quant-ph · cs.LG

新论文 · v1arXiv:2610.36946

Too many clients spoil the logs: distributed parsing, aggregation techniques and metrics

André García Gómez, Viktor Beck, Max Landauer, Markus Wurzenberger, Florian Skopik, Andreas Rauber, Edgar Weipp

原文摘要

Log messages are employed to identify anomalies in IoT systems and have been widely used across many applications. To enable collaboration among infrastructures belonging to different organizations, federated log anomaly detection has been thoroughly investigated for this purpose, often assuming the availability of ground truth log templates. However, this is typically not the case, as it is still necessary to depend on log parsers to extract log templates at inference time, while the design and deployment of such parsers in distributed environments remains largely an open problem. To this end, we report on an empirical investigation of distributed parsing and its key challenges, providing insights and lessons learned towards closing the gap between research and application. To further refine and contextualize the resulting benchmarks, we examine and introduce new metrics that provide a more comprehensive view for evaluating distributed parsers and how they behave in distributed environments. We propose a set of lessons learned and recommendations to support the design, deployment, and evaluation of distributed parsers. In particular, we evaluate the performance of five distinct parsing algorithms in combination with aggregation techniques that allow a unified agreement of event-template mappings across all participating clients, a prerequisite for federated log anomaly detection. In total, 6,720 distinct distributed configurations were tested for this purpose.

cs.CR

新论文 · v1arXiv:2610.36945

Total Deformation-based MPM for Perfectly Elastic Solid Simulation with Strong Deformations

Timna Böttcher, Rick Ridder, Jan Bender

原文摘要

We present a new MPM-based solver for perfectly elastic solids, which can recover from strong deformations and naturally allows contact handling. Typical MPM solvers suffer from numerical fracture, where objects break apart even when no plasticity is included in the elasticity model. Previous approaches for perfectly elastic solids solve this by computing forces on a fixed grid in the reference configuration. However, this makes them incompatible with standard collision handling methods. We instead propose a method for deformable solid simulation without numerical fracture, that still computes elastic forces on the current grid. Our method can easily include grid-based collision handling, as commonly used in MPM frameworks. Additionally, we compute the deformation directly from the particle positions and a fixed reference grid, without any updates based on velocity gradients. This facilitates the inclusion of particle-level collision handling and zero-energy mode suppression, which counteracts artifacts from non-linear deformations. As a result, we can efficiently simulate complex scenarios of elastic objects undergoing large deformations, including contact.

cs.GR

版本更新 · v3arXiv:2512.17263

AnyCXR: Human Anatomy Segmentation of Chest X-ray at Any Acquisition Position using Multi-stage Domain Randomized Synthetic Data with Imperfect Annotations and Conditional Joint Annotation Regularization Learning

Zifei Dong, Wenjie Wu, Jinkui Hao, Tianqi Chen, Ziqiao Weng, Bo Zhou

原文摘要

Robust anatomical segmentation of chest X-rays (CXRs) remains challenging due to the scarcity of comprehensive annotations and the substantial variability of real-world acquisition conditions. We propose AnyCXR, a unified framework that enables generalizable multi-organ segmentation across arbitrary CXR projection angles using only synthetic supervision. The method combines a Multi-stage Domain Randomization (MSDR) engine, which generates over 100,000 anatomically faithful and highly diverse synthetic radiographs from 3D CT volumes, with a Conditional Joint Annotation Regularization (CAR) learning strategy that leverages partial and imperfect labels by enforcing anatomical consistency in a latent space. Trained entirely on synthetic data, AnyCXR achieves strong zero-shot generalization on multiple real-world datasets, providing accurate delineation of 54 anatomical structures in PA, lateral, and oblique views. The resulting segmentation maps support downstream clinical tasks, including automated cardiothoracic ratio estimation, spine curvature assessment, and disease classification, where the incorporation of anatomical priors improves diagnostic performance. These results demonstrate that AnyCXR establishes a scalable and reliable foundation for anatomy-aware CXR analysis and offers a practical pathway toward reducing annotation burdens while improving robustness across diverse imaging conditions.

cs.CV

新论文 · v1arXiv:2610.36941

Algorithmic Monoculture in Machine Learning-based Site-Specific Fertilizer Recommendation

Abdelghani Belgaid

原文摘要

Machine learning recommendations are often evaluated one model at a time, despite deployment across interconnected decision makers. For continuous NPK fertilizer prescriptions, correlated errors can aggregate across farms and generate systemic costs. A model of shared and farm-specific recommendation errors links expected social loss to model adoption shares; the Herfindahl-Hirschman Index characterizes concentration effects when common model errors are independent and predictive risks are equal. A covariance-generalized formulation captures the dependence between model families. A two-model threshold characterizes when privately optimal monoculture is socially dominated, and a convex portfolio rule limits average private predictive regret. Nine model families across five Moroccan cereal systems provide a benchmark-based calibration. Under illustrative parameters and a 10% regret cap, accuracy-constrained diversification lowers modeled social loss in all five systems by 10.89-41.53% (mean 19.41%). Uniform allocation reduces modeled loss in this setting, but breaches the regret cap in every crop. Correlation sensitivity shows that highly dependent model errors attenuate the benefits of diversification. These counterfactual outcomes are not estimates of agronomic or monetary welfare; the framework identifies adoption architecture and error dependence as ecosystem-level evaluation variables.

cs.LG · cs.CY · econ.TH

新论文 · v1arXiv:2610.36940

TDLM: Adaptive Temporal Integration for Diffusion Language Models

Bohang Sun, Max Zhu, Francesco Caso, Christopher Irwin, Jialin Yu, Pietro Liò

原文摘要

Masked diffusion language models repeatedly compute representations for unresolved tokens, but conventional denoisers do not explicitly retain these representations for reuse across steps. We introduce Temporal Self-Conditioning Diffusion Language Model (TDLM), which lets each unresolved position attend to its own history of hidden representations within a frozen denoiser. This gives later predictions access to computation already performed. Training uses self-generated trajectories and a simple cross-entropy objective for tokens revealed between consecutively sampled decoding steps, while causal temporal attention permits parallel evaluation during training. On LLaDA, the temporal modules add only approximately 0.84% trainable parameters. Across LLaDA and Dream, the main comparison shows up to 7.15$\times$ faster generation than the corresponding original diffusion language model, with competitive answer quality on the evaluated tasks. These results motivate temporal memory as a practical way to make more effective use of repeated denoising computation.

cs.LG

版本更新 · v4arXiv:2602.05843

OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions

Fangzhi Xu, Hang Yan, Qiushi Sun, Jinyang Wu, Zixian Huang, Muye Huang, Jingyang Gong, Zichen Ding 等 17 位作者

原文摘要

The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primarily adopt a deductive paradigm, where agents execute tasks based on explicitly provided rules and static goals, often within limited planning horizons. Crucially, this neglects the inductive necessity for agents to discover latent transition laws from experience autonomously, which is the cornerstone for enabling agentic foresight and sustaining strategic coherence. To bridge this gap, we introduce OdysseyArena, which re-centers agent evaluation on long-horizon, active, and inductive interactions. We formalize and instantiate four primitives, translating abstract transition dynamics into concrete interactive environments. Building upon this, we establish OdysseyArena-Lite for standardized benchmarking, providing a set of 120 tasks to measure an agent's inductive efficiency and long-horizon discovery. Pushing further, we introduce OdysseyArena-Challenge to stress-test agent stability across extreme interaction horizons (e.g., > 200 steps). Extensive experiments on 15+ leading LLMs reveal that even frontier models exhibit a deficiency in inductive scenarios, identifying a critical bottleneck in the pursuit of autonomous discovery in complex environments. Project homepage: https://os-copilot.github.io/OdysseyArena-Home/

cs.CL

版本更新 · v3arXiv:2601.18923

DeFM: Learning Foundation Representations from Depth for Robotics

Manthan Patel, Jonas Frey, Mayank Mittal, Fan Yang, Alexander Hansson, Amir Bar, Cesar Cadena, Marco Hutter

原文摘要

Depth sensors are widely deployed across robotic platforms, and advances in fast, high-fidelity depth simulation have enabled robotic policies trained on depth observations to achieve robust sim-to-real transfer for a wide range of tasks. Despite this, representation learning for depth modality remains underexplored compared to RGB, where large-scale foundation models now define the state of the art. To address this gap, we present DeFM, a self-supervised foundation model trained entirely on depth images for robotic applications. Using a DINO-style self-distillation objective on a curated dataset of 60M depth images, DeFM learns geometric and semantic representations that generalize to diverse environments, tasks, and sensors. To retain metric awareness across multiple scales, we introduce a novel input normalization strategy. We further distill DeFM into compact models suitable for resource-constrained robotic systems. When evaluated on depth-based classification, segmentation, navigation, locomotion, and manipulation benchmarks, DeFM achieves state-of-the-art performance and demonstrates strong generalization from simulation to real-world environments. We release all our pretrained models, which can be adopted off-the-shelf for depth-based robotic learning without task-specific fine-tuning. Webpage: https://de-fm.github.io/

cs.RO · cs.CV

新论文 · v1arXiv:2610.36935

Gaussian Process Bandits for Constraint Black Box Lever Optimization

Bram van den Akker, Hidde Fokkema, Anastasiia Kornilova

原文摘要

Optimizing discrete allocation weights across competing segments of a shared budget is a fundamental challenge in resource-constrained, sequential decision-making environments. In practice, this optimization is often hindered by delayed, noisy, and aggregate feedback, alongside strict operational constraints on how frequently weights can be adjusted. Because of the resulting combinatorial action space and extreme data sparsity, classical multi-armed bandit algorithms that evaluate arms independently are rendered highly inefficient. To overcome these limitations, we propose a segmentation-agnostic approach utilizing Gaussian Process Upper Confidence Bound (GP-UCB) algorithms. By placing a Gaussian Process prior on the reward function, our method effectively shares information across neighboring configurations, drastically reducing the necessary exploration horizon. In this paper, we bridge the gap between theoretical bandit research and production-scale deployment. We first introduce a high-fidelity synthetic simulator to evaluate various kernel configurations under stationary, drifting, and reactive environments, identifying a composite Matérn + Linear kernel as the most robust choice for overcoming local noise and global shifts. Finally, we validate our findings through a large-scale Randomized Controlled Trial (RCT) in a live production environment. Our empirical results demonstrate that the GP-UCB approach delivers a statistically significant efficiency lift compared to a standard $\varepsilon$-greedy baseline, offering a highly practical solution for real-world black-box lever optimization.

cs.LG

版本更新 · v3arXiv:2508.11158

Role-Augmented Intent-Driven Generative Search Engine Optimization

Xiaolu Chen, Jie Bao, Haojie Wu, Zhen Chen, Liwei Pan, Yong Liao

原文摘要

Generative search engines (GSEs), which combine large language models (LLMs) with retrieval-augmented generation (RAG), are reshaping how users access Web information and making source visibility and influence in generated responses new optimization objectives. Existing generative search engine optimization (G-SEO) methods seek to improve content visibility, but many rely on direct access to target queries or GSE feedback elicited by those queries. However, Web content is typically optimized and published before future user queries are known, making G-SEO without access to target queries or their associated feedback an important yet underexplored problem. To address this, we propose RAID, a Role-Augmented Intent-Driven G-SEO method that operates without access to target queries or query-dependent GSE feedback. RAID infers a primary retrieval intent from source content, refines it through 4W multi-role deep reflection on prospective searchers' information needs, and uses both the primary and refined intents to jointly plan and rewrite source content. We further extend GEO-BENCH with diverse topic-related query variants, using both the original queries and their variants exclusively for evaluation to assess generalization to queries unseen during optimization. Across 100 samples and 500 evaluation queries, RAID achieves Relative Improvement Scores (RIS) of 3.00\% for Objective Overall and 1.32\% for Subjective Average, exceeding the best corresponding results among the nine predefined GEO rewriting strategies by 1.31 and 0.74 percentage points, respectively. With an optimization considered effective when $\mathrm{RIS}>0$, its effective optimization rates for Objective Overall and Subjective Average average 58.0\%, exceeding the highest corresponding average among the predefined strategies by 4.5 percentage points.

cs.IR · cs.AI

版本更新 · v2arXiv:2608.24175

Amortized Set Prediction for Inverse IFS Reconstruction from Density Maps

Yutaka Yamaguti

原文摘要

Iterated Function Systems (IFS) generate self-similar fractals from a few contractive affine maps. The forward map from parameters to images is inexpensive and well understood, whereas the inverse problem is difficult and is typically solved by per-image optimization. We replace this loop with a single forward pass of a learned estimator that predicts the affine-map set directly from a visit-frequency density map, thereby amortizing the inverse problem. The design follows two constraints. First, density maps do not uniquely identify IFS parameters, so we evaluate by reconstruction rather than parameter recovery and handle unordered map sets by Hungarian matching. Training nevertheless matches the ground-truth parameters: reconstruction-only training gives a better one-shot output, but refinement from its predictions converges to poorer minima, whereas refinement from parameter-matched predictions keeps improving. Second, the fully known forward model lets us generate exact synthetic training pairs and supports image-only test-time refinement. On in-distribution tests, amortized initialization plus a few refinement steps gives a better quality-speed trade-off than equal-budget random-start optimization, and over 1000 steps it reaches high-quality reconstructions more often. It is robust to the sampling settings of the observation, and on an external benchmark outside its training prior it matches the mean accuracy of a recent hour-long optimizer within a minute. On real images (MNIST and Fashion-MNIST), it improves density metrics on average over a published per-image optimizer while being roughly 2 to 500 times faster per image.

cs.CV

新论文 · v1arXiv:2610.36933

Provenance Signatures for Low Rank Adaptations of Image Diffusion Models

Tobias Cheung, Mohan Dantam, Marc Juarez, Rik Sarkar

原文摘要

Diffusion models have revolutionized the generation of realistic artificial images. Efficient techniques such as Low Rank Adaptation (LoRA) can modify these models for particular use cases, making them more diverse and widely usable. At the same time, open base models may be adapted to deliver biased, harmful or illegal images in an online service. In this paper, we develop a protocol to detect when a service may be using an adaptation of an otherwise standard model. We describe the precise setup and threat model for this provenance question and define two different problems arising due the presence of multiple model families and multiple adaptations. In contrast to previous works that have considered model identification within lists of known candidate models, we consider the realistic open world scenario where the set of possible adaptations and alternative models are unknown. Using a hypothesis testing approach, our protocols can distinguish between the base model, a LoRA adaptation and other completely different families of models. For this test, we develop a black box signature of the models based only on intrinsic dimension of sets of images generated by the models.

cs.LG

新论文 · v1arXiv:2610.36931

From Walks to Skeletons: A Reusable Transport Architecture for Interactive Monte Carlo PDE Solvers

Yunfeng Liao, Yucheng Wu, Xiucheng Li

原文摘要

Walk-on-Spheres (WoS) enables mesh-free solutions of elliptic PDEs, but conventional methods repeatedly discard sampled trajectories, limiting their efficiency in interactive applications. We introduce reusable transport skeletons, a persistent representation that organizes stochastic walks into a shared computational graph. Our framework enables efficient reuse across spatial queries and boundary conditions, while supporting progressive refinement, structure-preserving compression, and local adaptation to dynamic geometry. It further enables interactive editing of transport between selected regions. Experiments demonstrate substantial computational savings while preserving solution accuracy. By transforming transient stochastic trajectories into reusable transport structures, our method provides a flexible foundation for interactive Monte Carlo PDE solving.

cs.GR · math.NA

版本更新 · v2arXiv:2610.13020

Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL

Zhicheng Cai, Hanlin Wu, Weinan Dai, Yuyan Zhou, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou

原文摘要

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. Yet long-horizon autoregressive rollouts introduce a fundamental limitation: local policy mismatch can compound into severe state distribution shift over trajectories. Existing LLM RL methods, such as GRPO and GSPO, control policy mismatch at the token or sequence level, but overlook this trajectory-induced shift, causing training instability and eventual collapse as the horizon grows. To close the state distribution gap, we propose Trajectory-Aware Policy Optimization (TAPO), a principled framework that theoretically derives the state-distribution correction from the off-policy policy gradient and incorporates it into the RL objective. TAPO further employs a geometric-mean estimator for variance reduction, together with a length-aware dynamic clipping that prevents overly deviated updates across the trajectory. Extensive experiments demonstrate that TAPO significantly surpasses existing LLM RL algorithms across eight competition-level benchmarks, achieving up to 48% and 12% improvement over GRPO on mathematical reasoning and algorithmic coding, with substantially enhanced training stability.

cs.LG

版本更新 · v2arXiv:2603.15401

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu

原文摘要

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear, and no standard procedure tests an individual skill before installation. We present swe-skills-bench, a skill-centric, requirement-driven benchmark that measures how much individual agent skills improve performance on real-world software engineering (SWE) tasks. We start from 98 public SWE skills, each paired with a real GitHub repository pinned at a fixed commit. For each skill, we derive repository-specific requirements, create executable verifiers, and build a reproducible environment. Under each of four agent-model configurations, we run every task once without the skill and once with it, yielding 3,920 paired evaluations. For each requirement, we compute a paired delta, i.e., the change in outcome when the skill is added. We then aggregate these deltas across a skill's ten requirements into a per-skill utility profile, and use a statistical test to classify each skill as Golden (significantly helpful), Ineffective (no significant effect), or Harmful (significantly detrimental). Our results show that skills provide limited benefits: 92 of 98 skills have no statistically significant effect, and adding skills raises the average pass ratio only from 76.6% to 76.9%. The few helpful skills supply procedures that the agent would otherwise omit (gains of up to $+17.7$ points). In contrast, harmful skills anchor the agent on their own templates and override the task's explicit instructions (losses of up to -17.0 points). Our code is available at https://github.com/ControllableModel/SWE-Skills-Bench.

cs.SE · cs.AI

新论文 · v1arXiv:2610.36929

DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding

Saifullah Saifullah, David Dembinsky, Stefan Agne, Andreas Dengel, Sheraz Ahmed

原文摘要

Multimodal transformer models have driven unprecedented performance breakthroughs in modern document understanding. However, the inherent black-box nature of these models remains a major obstacle to their safe deployment in high-stakes sectors. Despite significant progress in explainability for vision and language tasks, explainable AI (XAI) research tailored to multimodal document understanding has received little attention. To address this gap, we present \ourframework{}, the first comprehensive explainability framework that adapts existing XAI methods and evaluation metrics to the multimodal (text, layout, and image) document understanding context, while introducing efficient multi-target adaptations of both methods and metrics for domain-specific tasks such as semantic entity recognition. Using \ourframework{}, we systematically evaluate 13 XAI methods across 3 document understanding tasks, 8 datasets, 4 models, and 17 evaluation metrics, and find that only a few methods perform consistently across all evaluation criteria, with Occlusion emerging as the most faithful and interpretable method overall. Through a dedicated meta-evaluation, we observe moderate to strong agreement among several faithfulness and complexity metrics while identifying certain ones that produce unreliable results. Finally, through multiple dataset-wide diagnostic analyses, we uncover key insights into model behavior, including the contribution of individual modalities across tasks and labels, spatial attribution patterns around target entities, and potential dataset biases. Overall, this work serves as both a benchmark and a practical guide for future XAI research in multimodal document understanding. To support reproducibility, we publicly release our code at https://github.com/saifullah3396/docxeval/.

cs.CL · cs.CV

新论文 · v1arXiv:2610.36926

Developing a Dynamic Multi-factor Authentication System for Securing Smart Organizations

Mohsen Saffar, Hamid Reza Naji

原文摘要

As smart organizations increasingly rely on technologies like AI, big data, and IoT, securing these systems is crucial. This research introduces a dynamic multi-factor authentication (MFA) system within the Zero Trust Architecture (ZTA) framework, which enforces continuous verification. The system randomly selects biometric authentication factors, such as fingerprint, iris, and face recognition using a Markov chain model to ensure adaptability and reduce predictability in security measures. Using CASIA biometric datasets and AES-128 encryption, the system securely manages user data and authentication. Performance analysis shows that the dynamic selection process balances security and efficiency, making it suitable for smart organizations, particularly in e-government contexts. This MFA system strengthens cybersecurity by providing a flexible, real-time defense against evolving threats.

cs.CR

新论文 · v1arXiv:2610.36925

Vision-Language Agents Can Learn in Their Own Latent Worlds

Haoxi Li, Sikai Bai, Jianfei Ma, Qinglin Hou, Xiaocheng Lu, Tao Han, Jie Zhang, Song Guo

原文摘要

Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) already internalize rich world knowledge, yet this knowledge is rarely leveraged to drive policy improvement through online interaction. Realizing this potential efficiently remains challenging, as policy updates shift the agent's interaction distribution, requiring the world model to adapt accordingly, while continually updating large pretrained models is computationally expensive. To address this challenge, we introduce Dwell, a model-based reinforcement learning (RL) framework that reframes a VLM as a recurrent latent transition operator, endowing it with the ability to predict, adjust, and act in latent space. Leveraging the VLM's own representations and its dual role as both world model and policy, the agent continually learns from real interactions to anticipate and evaluate action outcomes, and from latent imagination to improve its behavior. Across five interactive visual environments, Dwell achieves the strongest overall performance among trainable methods while substantially reducing the compute required for imagination, showing that effective world models for VLM agents need not reconstruct the future; they need to predict futures that are useful for action. Our code is publicly available at https://github.com/Tom111-lhx/Dwell

cs.AI

版本更新 · v2arXiv:2610.26062

Procedural Exposure Bias in Skill-Augmented Language Model Agents

Qing Yang, Yuqi Xiong, Pengcheng Huang, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yu Gu, Ge Yu

原文摘要

External skills provide language-model agents with reusable procedural knowledge, yet how models use such knowledge after it is supplied remains poorly understood. We identify Procedural Exposure Bias (PEB), the tendency of language models to increasingly favor an action as its associated procedural pattern is repeatedly exposed in a skill, even when the interaction state and action relevance remain unchanged. We find that PEB strongly depends on how procedural knowledge is represented: presenting the same content visually substantially attenuates exposure-induced shifts in action preference relative to textual presentation. Further analysis shows that this attenuation primarily arises from visual encoding rather than structured layout. Although repeated procedural signals remain recoverable from Visual representations, they exert a weaker influence on downstream action prediction, distinguishing signal accessibility from its use as action evidence. This effect also extends to executable action selection, where increasing exposure more strongly favors the corresponding action under Text than Visual. Layer-wise analyses show that exposure-dependent action evidence becomes more pronounced toward the model output, with stronger evidence under Text, while activation interventions reveal architecture-specific roles of internal components in transmitting or counteracting the preference shift. Complete-agent evaluations across ALFWorld, ScienceWorld, and WebShop further show that Visual skills achieve higher macro-average task success than Text skills for all four evaluated models. These findings establish skill representation as an important factor governing how procedural knowledge is translated into agent decisions. All code is available at https://github.com/NEUIR/Vis-Skill.

cs.CV

版本更新 · v2arXiv:2610.34378

Logarithmic asymptotics for polynomial threshold functions

Martin Anthony

原文摘要

We count Boolean functions represented as the sign of a real polynomial of bounded degree on the $n$-dimensional cube. We prove that the logarithm of their number is asymptotic to that of the classical hyperplane-arrangement upper bound, uniformly over all degrees, with relative error $O((\log n)^2/n)$. We also obtain sharper additive and relative error estimates in particular degree ranges, including an additive error $O(n^2)$ between the logarithms throughout a small linear degree range and improved bounds just below the central degree. The proof combines probabilistic estimates for Reed--Muller codes with a deletion argument for sets of evaluation vectors, an entropy count, and a sharp-threshold estimate for expected rank deficiency.

cs.DM · cs.IT · math.CO

版本更新 · v2arXiv:2610.26397

Bridged Self-Distillation for On-Policy Learning

Runsheng Chen, Yihong Liu, Raoyuan Zhao, Michael A. Hedderich, Hinrich Schütze, Matthias Grabmair

原文摘要

On-policy distillation can transfer the reasoning capabilities of a strong teacher to a smaller student. However, distillation from a stronger teacher model faces two mismatches: its solutions may be difficult for a smaller student to imitate, and its token-level probabilities may be incompatible with, or even unavailable to, the student. Existing methods handle these settings through different forms of supervision. To this end, we propose Bridged Self-Distillation (BSD), a unified framework for distilling from any teacher that provides reasoning traces. The model to be distilled from, termed the external teacher, first provides a reasoning trace as privileged context, which can be generated in an offline fashion. The student generates rollouts without this context, while a copy of the student conditioned on it, serving as the self-teacher, scores the same rollouts in the student's own token space. BSD uses the resulting token-level guidance to adjust updates on unsuccessful rollouts, with a verifier providing the outcome signal. As the external teacher is queried only to produce text, the same training procedure applies to all teacher scenarios: shared-tokenizer, cross-tokenizer, and closed API teachers. Across these scenarios, BSD improves over the base model and outperforms baselines tailored to each scenario, offering a novel and unified pathway for distillation. Code is available: https://github.com/TUMLegalTech/Bridged-Self-Distillation

cs.CL

新论文 · v1arXiv:2610.36918

TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces

Mingyu Zhang, Zixu Li, Zhiheng Fu, Zhiwei Chen, Jinhe Bi, Yupeng Hu

原文摘要

Large language model (LLM) agents rely on memory systems to leverage long-term interactions, yet existing systems typically retrieve memories based on their relevance to the current query and use them as contextual evidence. However, relevance alone does not characterize how a memory contributes to task solving: the same memory may serve different roles across tasks, such as directly supporting the answer or linking to complementary memories with weaker semantic relevance but necessary information. We therefore reframe agent memory systems as Task-Oriented Role-Adaptive Workspaces, where memories are selected and organized by their task-oriented roles and relations. Based on this view, we propose TrawMem, which organizes interaction histories into local threads and constructs task-oriented workspaces by assigning roles and jointly selecting complementary memories. Experiments on LoCoMo and MemGallery with four open- and closed-source backbones show consistent improvements over representative memory systems, with macro-F1 gains of 2.23-3.14 points. On LoCoMo, TrawMem improves the LLM-Judge score over SimpleMem by 4.07 and 4.31 percentage points on Qwen3.5-9B and DeepSeek-V4-Flash, respectively, while requiring approximately 12.8% and 5.1% fewer context tokens, respectively.

cs.CL

版本更新 · v2arXiv:2510.14233

RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models

Fanchao Meng, Jiaping Gui, Yunbo Li, Yue Wu

原文摘要

Modern Network Intrusion Detection Systems (NIDS) generate vast volumes of low-level alerts that remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing automation, namely rule-based systems and machine learning classifiers, has critical limitations: rule-based approaches fail to adapt to novel attack variations, while machine learning methods lack contextual awareness and treat tactic-technique (TT) mapping as syntactic matching rather than reasoning. Although Large Language Models (LLMs) show promise in cybersecurity, preliminary experiments reveal that existing LLM-based methods frequently hallucinate technique-tactic pairs or produce decontextualized mappings due to single-step classification. We introduce RHINO, a framework that decomposes LLM-based attack analysis into three structured phases: (1) behavioral abstraction, translating raw logs into contextualized narratives; (2) partitioned inference over the ATT&CK tactic space, generating candidate techniques by evaluating behavioral evidence against MITRE ATT&CK knowledge; and (3) knowledge-grounded refinement, cross-referencing predictions with official MITRE definitions to reduce hallucinations. We evaluate RHINO on three benchmarks (DAPT2020, CICIDS2017, IoT23) across four backbone models (ChatGPT-4o, Gemini 2.5 Flash, Claude Sonnet 4, and DeepSeek V3). Under a scenario-documented single-label formulation covering 11 distinct techniques, RHINO achieves an average top-1 accuracy of 87.34% under micro-averaging and 63.77% under macro-averaging, surpassing the strongest baseline by 16.78 and 13.60 points respectively. These results show that structured LLM reasoning can effectively translate low-level network observations into high-level adversarial behaviors.

cs.CR