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

+672新增论文
+517其中 AI 相关
+80已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 11:09 — 2026-11-17 11:09(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

24,106 已收录论文20,158 AI 相关7,049 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 24,106 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.05776

Closed-Loop Adaptive Sampling on a Generative Ocean Model

Shayesteh Hafezi, Alan Papalia

原文摘要

Adaptive sampling can substantially improve the value of sparse ocean observations by directing mobile robots toward measurements that are most informative for an evolving environment. Recent learned generative ocean models can produce high-resolution forecasts and ensembles at substantially lower computational cost than traditional numerical models, creating an opportunity to use rich predictive forecasts directly in closed-loop robotic sampling. However, these models do not natively provide the explicit uncertainty representations assumed by classical informative-planning methods, and their forecasts often evolve in learned latent spaces rather than directly in physical ocean variables. We develop a multi-robot closed-loop adaptive sampling framework that uses a single learned generative model for forecasting, uncertainty estimation, planning, and measurement assimilation. The model forecasts an ensemble in latent space, decodes it to physical ocean states, and uses ensemble statistics to construct A- or D-optimal sampling objectives. We select sampling locations subject to robot reachability under predicted currents. The collected measurements are assimilated back into the latent state using observation-conditioned diffusion sampling. Across 120 test scenarios A- and D-optimal sampling generally outperforms static, random, and systematic-coverage baselines while adding little planning overhead. Our experiments uncover several scenarios in which model uncertainty diverges from forecast error, motivating future work in uncertainty quantification.

cs.RO

新论文 · v1arXiv:2611.05774

Optimizing Recourse Under Predictive Multiplicity

Shahin Jabbari

原文摘要

Algorithmic recourse identifies modifications that can change an unfavorable model prediction into a favorable one. Under predictive multiplicity, similarly performing models can disagree on individual predictions, so recourse valid for one model may fail for another. We formulate robust recourse under predictive multiplicity as a budget-constrained minimization of the worst-case validity loss across a competing set of models, which can include models with different architectures or from different hypothesis classes. We propose an oracle-efficient algorithm called ORPM and prove sufficient conditions for its convergence. We evaluate ORPM on one synthetic and five real datasets, and competing sets consist of linear, neural, mixed, and decision-tree models. Our experiments show decreasing optimization-gap bounds and high validity in many tested settings, with favorable performance against baselines designed for specific model classes or architectures. We also quantify how requiring a common action across competing models changes recourse success at a given budget and examine disparities in this success across demographic groups.

cs.LG

版本更新 · v3arXiv:2610.22454

Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss

Zhiyuan Wang, Han Wang, Shuo Zhang

原文摘要

Running prompt tokens through fewer routed experts during prefill makes mixture-of-experts (MoE) serving cheaper, but what it damages has not been measured. We locate the damage with token-, layer- and attention-path interventions in four MoE families on short-answer question answering. At half the experts the F1 loss is mostly answer form: the model still finds the answer but no longer answers briefly. The loss is made at a few tokens: the two chat-template tokens before the answer in Qwen3-30B-A3B, and the first 8-32 tokens, where the instruction sits, in DeepSeek-V2-Lite. Keeping them at full experts removes most of the F1 loss and about half and a fifth of the increase in answer NLL. Reduction changes the first-token sink statistics by less than 4%, and restoring super experts or massive activations recovers at most a quarter of the loss. We then test placement on real prompts with about 4% of tokens at full experts. Putting them on the task interface keeps F1 within one point of the unmodified model, while the same budget scattered in the documents is about 3 points worse in both prespecified primary tests of this comparison. Time to first token falls about 14% on 11K-token prompts.

cs.CL · cs.LG

新论文 · v1arXiv:2611.05772

Hotplug Coded Caching: Embedding the YMA and Interference Elimination Schemes via Reed--Muller Codes

Daniela Tuninetti

原文摘要

In the hotplug coded caching model, $K$ users fill their caches of size $M$ as a function of $N$ files, but only an unknown subset of $A<K$ users is active in the delivery phase. We recently showed that (i) under uncoded placement, offline users cause a strict load penalty at intermediate memory sizes, so that coded placement is needed; and (ii) for $AM\leq N$, every classical scheme with row-wise placement, including the scheme of Gomez-Vilardebo (GV), can be embedded in a Reed-Solomon code, which removes the penalty. In this note, we show that every point of the scheme of Yu, Maddah-Ali and Avestimehr (YMA) for a classical system with $A$ users is achievable in the hotplug model for every $K\geq A$. Each user is associated with a hyperplane and each file with a homogeneous polynomial; each user caches the restriction of the polynomial to its hyperplane, and the subfiles seen by the active users are the values of the polynomial at the points where their hyperplanes meet. This is a projective Reed-Muller code, which reduces to the Reed-Solomon code when each subfile is cached by one user. We then show, by an existence argument, that every classical scheme whose cache is a linear compression of the Maddah-Ali-Niesen cache and whose correctness holds for generic coefficients can also be embedded over a sufficiently large field; this includes the interference elimination (IE) schemes of Tian and Chen. These embeddings complement the Reed-Solomon one, which allows any row-wise placement and any delivery. Together with past work, our results show that every point attained by a GV, YMA or IE scheme ($N\leq A$ for IE), and every corner point of the linear tradeoff for $A=N=3$, is achievable in the hotplug model with a load that does not depend on $K$. Whether the optimal hotplug tradeoff depends only on $A$ remains open, but these results support a positive answer.

cs.IT · eess.SP

新论文 · v1arXiv:2611.05771

How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation

Harshit Gupta, Shunichi Ishihara

原文摘要

This study investigates the authorship impersonation capacity of six widely used large language models (LLMs): Gemini 3 Pro, Claude Opus, GPT 5.2, GPT 5.2 Pro, DeepSeek 3.2, and Grok 4.1 Fast. The evaluation was conducted using short product review texts selected to ensure high within author consistency in individual writing style. Two types of in context prompt were designed: a simple prompt with minimal instruction and a complex prompt incorporating explicit stylometric guidance for mimicry. Authorship mimicry was evaluated using a cosine distance based distance to training metric, supplemented by visual analyses of embedding distributions. The results indicate that authorship impersonation remained challenging for most LLMs, with Gemini 3 Pro showing the strongest apparent mimicry performance. However, subsequent overlap analysis revealed that Gemini 3 Pro extensively copied and reused sentences and phrases from the training texts, at levels far exceeding those observed among human authors. Follow up factor analyses showed that training set consistency was the most robust predictor of mimicry success across models, whereas author distinctiveness did not generalise as a reliable predictor. Global embedding visualisations further revealed a consistent macro level pattern: for most models, generated texts occupied regions of the embedding space that were largely separated from the corresponding human training clusters. This indicates limited convergence towards target author style and suggests the presence of model specific lexical and phraseological preferences. The findings highlight the importance of distinguishing genuine stylistic imitation from direct textual reuse and have implications for the forensic analysis of textual evidence involving potential LLM enabled impersonation.

cs.CL · cs.AI

版本更新 · v2arXiv:2512.09360

A Granular Framework for Construction Material Price Forecasting: Econometric and Machine-Learning Approaches

Boge Lyu, Qianye Yin, Iris Denise Tommelein, Hanyang Liu, Karnamohit Ranka, Karthik Yeluripati, Junzhe Shi

原文摘要

The persistent volatility of construction material prices poses significant risks to cost estimation, budgeting, and project delivery, underscoring the urgent need for granular and scalable forecasting methods. This study develops a forecasting framework that leverages the Construction Specifications Institute (CSI) MasterFormat as the target data structure, enabling predictions at the six-digit Section level and supporting detailed cost projections across a wide spectrum of building materials. To enhance predictive accuracy, the framework integrates explanatory variables such as raw material prices, commodity indexes, and macroeconomic indicators. Five time-series models, long short-term memory (LSTM), autoregressive integrated moving average (ARIMA), vector error correction model (VECM), vanilla Transformer, and Chronos-Bolt, were evaluated under both baseline configurations (using CSI data only) and extended versions with explanatory variables. Results demonstrate that incorporating explanatory variables significantly improves predictive performance across all models. Among the tested approaches, the LSTM model consistently achieved the highest accuracy, with root mean squared error (RMSE) values as low as 4.19 and mean absolute percentage error (MAPE) values of 1.60 based on Division 06 as a representative demonstration, representing improvements of up to 59% over the traditional statistical time-series model, ARIMA. Validation across multiple CSI Divisions within the residential-material confirmed the framework's scalability, while Division 06 (Wood, Plastics, and Composites) is presented in detail as a demonstration case. This research offers a robust methodology that enables owners and contractors to improve budgeting practices and achieve more reliable cost estimation at the definitive level.

cs.LG · econ.EM

新论文 · v1arXiv:2611.05769

Noncrossing is All You Need: Beyond Identical Delay Functions in Online Matching with Delays on General Metrics

Yossi Azar, Junhao Gan, Shahar Lewkowicz, Xiao Sun, Seeun William Umboh

原文摘要

Online optimization with delays has emerged as a powerful paradigm with numerous applica- tions, including matching, caching, server management, network design, and set cover. In most of these problems, competitive algorithms are known for arbitrary monotone delay functions, even when different requests are associated with different delay functions. The notable exception is online matching with delays, where all previously known algorithms achieving constant or polylogarithmic competitive ratios require the delay functions to be identical, either linear or concave, and known in advance. We study the online minimum-cost perfect matching with delays problem on general metrics. We introduce the broad class of noncrossing delay functions, which strictly generalizes the classic setting of identical concave delay functions while naturally modeling scenarios in which different requests may experience different delay costs. We present the first deterministic $O(1)$-competitive algorithm for the single-location online matching problem with noncrossing delay functions in the non-clairvoyant setting as well as a randomized $O(lognlogΔ+log^2Δ)$-competitive algorithm of an arbitrary metric space where $n$ is the number of points of the metric space and $Δ$ is its aspect ratio. Our result allows each request to have an arbitrary noncrossing delay function, thereby simultaneously removing the assumptions of identical delay functions, concavity, and clairvoyance that were required by all previous constant or polylogarithmic-competitive algorithms.

cs.DS

新论文 · v1arXiv:2611.05766

ME^2FDiff: Multiscale Expert Enhancing Feature Diffusion in Residual Network for Brain Tumor Segmentation

Afrida Rahman, Bijoy Kundu

原文摘要

Automated segmentation of post-treatment glioma from MRI is essential for accurate diagnosis and treatment planning, yet remains difficult. Surgery and chemoradiotherapy cause structural changes in brain like resection cavities, edema, and fibrosis, that alter imaging appearance and mimic tumor recurrence. Contemporary segmentation architectures attain high accuracy with two limitations. First, the bottleneck originates from the deepest encoder stage, so one representation must serve sub-regions that differ widely in size and appearance. Second, they produce the segmentation in a single forward pass with no mechanism for refinement. We propose ME^2FDiff, a single-model architecture, addressing both. An attention-conditioned spectral diffusion block refines the bottleneck. It uses the image-conditioned latent diffusion process with two processes: a spatial pre-attention gate and a spectral fusion block whose timestep-adaptive bandpass filter selects the informative frequency band at each noise level. A multiscale expert-enhanced feature block fuses the intermediate encoder scales into the bottleneck through expert-selected shared tokens, guaranteeing balanced utilization without an auxiliary loss. On the BraTS 2024 post-treatment glioma dataset, ME^2FDiff achieves the best results on every tumor sub-region among all single-model baselines (91.23% Dice, 84.52% IOU, 2.13 mm HD95 on whole-tumor) and surpasses a three-expert ensemble on both overlap metrics at roughly one-third of its inference cost. Against recent state-of-the-art methods retrained under identical conditions, it maintains the strongest performance with the fewest parameters of any competing model. These findings demonstrate that a single, compact network can absorb the specialization, usually sought through ensembling or larger architectures.

cs.CV

版本更新 · v2arXiv:2608.15968

Vision-Guided Reorientation and Color Sorting of Writing Utensils Using a Low-Cost 4-DoF Arm

Anirudh Rangarajan, Bibit Bianchini

原文摘要

Low-cost four-degree-of-freedom (DoF) arms are among the most accessible robotic platforms. But they are one joint short for picking up in situations where objects are at arbitrary orientations, a task that appears to require five degrees of freedom: the planar position (x and y), the height (z), a wrist rotation to align the gripper with the object, and gripper actuation, of which a four-DoF arm lacks the wrist rotation. This work uses perception and motion planning so that such an arm, a roughly $200 Waveshare RoArm-M2-S under a fixed overhead camera, can detect and color-sort writing utensils without that joint. A YOLO11n-OBB (You Only Look Once, oriented bounding box) detector locates each writing utensil; camera intrinsics and an ArUco reference pose convert its pixel coordinates to robot coordinates; and a color classifier labels it. The detected orientation angle determines the motion strategy: utensils close to the arm's fixed approach direction are picked up directly, and those at steeper angles are reoriented via corrective sweeps until they are graspable, after which they are picked up and sorted into the assigned color bin. In 196 single-utensil trials, the 98 that started beyond 45 degrees from that direction all became graspable within four sweeps (130 total). Overall, 176 (89.8%) ended in the correct bin; 19 of 20 failures were slipped or missed grasps, one a mislabeled color. For the seven utensils tested in this setup, corrective sweeps brought every steeply misaligned utensil into a graspable orientation on an arm with no wrist joint.

cs.RO

版本更新 · v2arXiv:2610.04624

Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems

Yida Pan, Muhammad H. Ashiq, Chanyong Jung, Yixuan Jia, Jonah M. Miller, Qing Qu, Ismail Alkhouri

原文摘要

Recovering Partial Differential Equation (PDE) coefficient fields from extremely sparse observations is a severely ill-posed inverse problem for which generative machine learning methods (e.g., diffusion models) have become a leading way to encode the prior. Recent state-of-the-art diffusion solvers lift these priors to function spaces, finding a physics-consistent reconstruction in the output space of the diffusion denoiser. We prove that, in a discontinuous PDE setting, output space methods can result in failure to appropriately minimize the unobserved error with the correct coefficient field. Consequently, we propose Function Space Backward-Consistent Sampling (FunBCS), an input space optimization approach for solving PDE problems which aims to find the best input such that the denoiser reconstruction is physics-consistent. We then prove that FunBCS appropriately minimizes the unobserved error, unlike output space optimization methods. Per our theoretical analysis, we also provide insights on how to dynamically allocate the number of input space optimization steps used throughout the sampling process. Our evaluations, across four PDE inverse problems (including the discontinuous Darcy flow), demonstrate that FunBCS reduces the reconstruction error by $27$-$64\%$ while running $1.4$-$2.1\times$ faster when compared to the current state-of-the-art.

cs.LG

新论文 · v1arXiv:2611.05762

Classifying K-Geodetic Graphs Via Combinatorial Designs and Distance-regularity

Carlos E. Frasser

原文摘要

The classification of K-geodetic graphs is a fundamental problem in graph theory concerning the number of shortest paths connecting pairs of vertices. A graph is called K-geodetic if every pair of distinct vertices is joined by at most K geodesics, where a geodesic is a shortest path between two vertices. The cases K=1,2,3 correspond, respectively, to geodetic, bigeodetic, and trigeodetic graphs. Despite substantial progress in the study of their structural properties, a comprehensive classification of these graph families remains elusive. This paper develops a research framework for investigating the classification problems by combining metric graph theory, distance-regular graphs, algebraic graph theory, and combinatorial design theory. Particular attention is given to distance-regular graphs, for which the number of geodesics between vertices at a fixed distance is determined by the intersection numbers of the graph. This property converts the K-geodetic condition into a finite collection of arithmetic inequalities. We establish the resulting necessary conditions for K=1,2,3, discuss representative examples, and distinguish these conditions from the stronger requirements needed to prove the existence and classification of graphs with a given intersection array. The paper also investigates the potential role of balanced incomplete block designs (BIBDs) in constructing and organizing families of K-geodetic graphs. Finally, it proposes a computational research methodology based on constraint satisfaction, graph-isomorphism testing, exhaustive enumeration, and machine-assisted conjecture generation.

cs.DM

新论文 · v1arXiv:2611.05761

BobFlow: Towards Human-Agent Collaborative Data Science Using Dataflows

Jiadong Bai, Yicong Huang, Chen Li

原文摘要

Recent advances in large language models (LLMs) have established human-agent collaboration as a promising paradigm for data science. Effective collaboration requires a shared computational abstraction that enables agents to reason about processing logic while allowing human analysts to understand, guide, and refine the analysis. Although scripts written in Python or SQL provide precise control, their syntax and execution details can be difficult for analysts to understand and modify. In this paper, we argue that dataflows are an effective abstraction for human-agent collaboration in data science. We introduce BobFlow, a system that combines the dataflow abstraction with the ReAct paradigm. It enables agents to iteratively construct and execute dataflows for data science tasks while allowing analysts to inspect the analysis and provide feedback. Our user study shows that BobFlow helps analysts understand, inspect, and verify agent-generated analyses. A thorough experimental evaluation across proprietary and open-weight LLMs shows accuracy score gains of up to 18.6 points at just over 1/3 of a script-based ReAct agent's inference cost.

cs.DB · cs.AI · cs.HC

版本更新 · v3arXiv:2605.18991

Agent Security is a Systems Problem

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Kamalika Chaudhuri, Xiaohan Fu, Khawaja Shams 等 14 位作者

原文摘要

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the community) are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. Based on our experience as cybersecurity researchers in operating systems, networks, formal methods, and adversarial machine learning, we articulate a set of core principles, grounded in decades of systems security research, that provide a foundation for designing agentic systems with predictable guarantees. As evidence, we analyze eleven representative real-world attacks on agents and discuss how systems principles, if realized, could have prevented these attacks. We also identify the research challenges that stand in the way of implementing these principles in agents.

cs.CR · cs.AI

版本更新 · v2arXiv:2510.01183

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory

Jiahao Wang, Luoxin Ye, TaiMing Lu, Junfei Xiao, Jiahan Zhang, Yuxiang Guo, Xijun Liu, Rama Chellappa 等 11 位作者

原文摘要

Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving 3D memory to enable spatially consistent long-horizon exploration. Given a single panoramic image as input, EvoWorld first generates future video frames by leveraging a video generator with fine-grained view control, then evolves the scene's 3D reconstruction using a feedforward plug-and-play transformer, and finally synthesizes futures by conditioning on geometric reprojections from this evolving explicit 3D memory. Unlike prior state-of-the-arts that synthesize videos only, our key insight lies in exploiting this evolving 3D reconstruction as explicit spatial guidance for the video generation process, projecting the reconstructed geometry onto target viewpoints to provide rich spatial cues that significantly enhance both visual realism and geometric consistency. To evaluate long-range exploration capabilities, we introduce the first comprehensive benchmark spanning synthetic outdoor environments, Habitat indoor scenes, and challenging real-world scenarios, with particular emphasis on loop-closure detection and spatial coherence over extended trajectories. Extensive experiments demonstrate that our evolving 3D memory substantially improves visual fidelity and maintains spatial scene coherence compared to existing approaches, representing a significant advance toward long-horizon spatially consistent world modeling.

cs.CV

首次观测 · 记录 #1软件学报:jos:7712软件学报

语义迁移:面向云端大语言模型交互的数据隐私保护方法

语义迁移: 面向云端大语言模型交互的数据隐私保护方法

陈董, 欧阳朋朋, 杨彤, 刘起东, 李亚飞, 谢立伟, 丁少杰, 徐明亮

AI 速读 基于摘要

提出STPP方法,通过语义加密把隐私关键信息迁移到相似逻辑的新场景、再语义解密还原反馈,在保护云端大语言模型交互隐私的同时维持数据效用。

cs.* · cs.CL

软件学报 · 2026 · 正式发表

查看原文摘要

具有强大理解、生成能力的云端大语言模型(cloud large language model, CLLM)已经成为人们日常工作中不可缺少的工具. 然而, CLLM的运行方式意味着用户需要上传原始数据, 这将使得用户的数据隐私安全难以得到有效保障. 现有数据加密方法往往通过添加噪声来改变原始数据形式, 这极易导致数据效用下降, 并影响任务效果. 不同于对原始数据的全盘保护, 将用户数据分为可被识别并用于对齐归属个体的隐私关键信息, 以及不涉及归属问题的普通信息, 并提出保护隐私关键信息, 传递普通信息, 从而在保护数据隐私安全的同时, 维持数据效用. 具体而言, 提出基于语义迁移的用户隐私保护(semantic transfer for privacy protection, STPP)方法. STPP首先基于LLM广泛的先验知识构建语义映射库与语义映射模型, 并通过语义加密将原始信息迁移到具有相似逻辑的新场景. 在获得CLLM反馈后, STPP又通过语义解密将反馈信息还原回原始场景, 从而保护用户数据隐私安全的同时, 降低所提方法对用户使用CLLM体验的影响.

首次观测 · 记录 #1软件学报:jos:7736软件学报

代码差异表示在代码提交信息生成中的有效性实证研究

代码差异表示在代码提交信息生成中的有效性实证研究

李旻灿, 王国庆, 赵逸凡, 郝丹

AI 速读 基于摘要

该研究实证比较三种不同上下文范围的代码差异表示对六种提交信息生成方法效果的影响。

cs.*

软件学报 · 2026 · 正式发表

查看原文摘要

提交信息生成(commit message generation, CMG)是软件演化与维护领域的重要任务, 其目标是依据给定的代码差异自动生成提交信息. 目前CMG方法普遍基于Git原生差异格式GitDiff构造输入, 该格式通过固定大小的上下文窗口展示变更行附近的代码片段. 然而, 代码差异的表示方式并非唯一, 通过扩大上下文范围可以构造信息更完整的代码差异表示. 具体地, 构建两种不同上下文范围的差异表示形式, 并围绕差异表示形式对CMG质量的影响开展实证研究. 实验使用现有CMG研究常用的MCMD数据集, 选取6种代表性CMG方法, 使用多种度量来分析3种代码差异表示对于CMG方法的效果影响. 实验结果表明, 尽管 GitDiff 在整体平均指标上略占优势, 但其样本胜率(41.5%)并未构成压倒性领先, 表明不同差异表示在不同代码语境下存在明显性能差异. 此外, 差异表示的选择会影响CMG模型性能比较结论, 在25%–50%的样本中, 基于GitDiff得到的模型优劣排序在切换至其他表示后会发生变化, 说明仅依赖单一代码差异表示所得模型性能结论可能存在偏差. 进一步研究发现, 当变更行依赖的关键语义单元超出GitDiff固定上下文窗口的覆盖范围时, 补全这些缺少的关键语义单元可以在一定程度上提升提交信息生成质量. 对此类场景进行系统归纳, 可为实践中代码差异表示的选择提供参考.

首次观测 · 记录 #1软件学报:jos:7737软件学报

开源社区新手到核心贡献者的成长路径分析

开源社区新手到核心贡献者的成长路径分析

黄革宇, 谭鑫, 郑凯, 张莉

AI 速读 基于摘要

基于87个项目、45 342名以GFI为初始任务的新手的纵向实证分析,刻画新手向核心贡献者转变的比例、周期与行为特征。

cs.*

软件学报 · 2026 · 正式发表

查看原文摘要

开源软件社区通常采用“good first issue (GFI)”机制, 为新手提供精心筛选的入门任务, 以促进其参与与融入. 理解尝试解决GFI的新手如何逐步成长为核心贡献者, 对于社区的可持续发展至关重要, 这也是GFI机制的核心目标. 以87个开源软件项目中45 342名以GFI作为初始任务的新手为研究对象, 开展一项纵向实证分析. 研究结果表明, 仅有2.3%的新手最终成功转变为核心贡献者, 其在转变过程中累计代码提交次数的中位数为19次, 转变周期中位数为12个月. 进一步分析表明, 新手在贡献行为上呈现出明显的分层特征: 首先, 大量未成功转变的新手在直接性贡献维度上长期处于不活跃状态, 尤其体现在代码提交和问题报告相关活动上; 其次, 在已表现出一定活跃度的新手中, 成功转变者表现出显著更高的参与水平——其提交次数约为其他新手的15倍, 评论数量约为8倍, 协作者数量为3倍, 整体活跃度比例高出28倍. 此外, 成功转变的新手在贡献行为上呈现出更高的波动性与复杂性, 其参与程度随时间逐步提升, 并在较晚阶段达到活跃峰值, 体现出渐进式学习与逐步融入的过程. 相比之下, 未实现转变的新手则表现为长期不活跃, 或仅在早期出现短暂且难以持续的活跃峰值. 在转变速度方面, 研究发现, 更高的沟通波动性、更长的持续活跃周期以及更具选择性的参与节奏与更快的转变相关; 而较高的问题报告活动或长期低活跃状态则与较慢的转变相关. 在项目层面, 控制变量分析结果表明, 项目受欢迎程度越高, 新手转变速度越快; 而历史提交规模越大, 则转变速度相对较慢. 研究为理解开源社区中新手成长路径提供了系统性的实证证据, 并为设计更有效的新手引导与培养策略提供了可操作的参考依据.

首次观测 · 记录 #1软件学报:jos:7745软件学报

融合双视角不确定性度量与双代理模型池的DNN测试排序

融合双视角不确定性度量与双代理模型池的DNN测试排序

钱忠胜, 范赋宇, 刘金平, 李玉龙, 刘凯强

AI 速读 基于摘要

提出一种结合输入侧双视角不确定性度量与模型侧双代理模型池的DNN测试输入优先级排序方法,以预测误分类概率并降低标注成本。

cs.*

软件学报 · 2026 · 正式发表

查看原文摘要

深度神经网络(deep neural network, DNN)测试需要大量的测试数据来保证其质量, 但大多数测试输入缺乏标注信息, 且对其进行标注会带来高昂的人工代价. 现有研究提出测试输入优先级方法, 筛选高优先级的测试输入进行标注以降低人工标注成本. 然而, 它们均仅从单一不确定性视角或模型静态行为上考虑测试输入. 一方面, 局限于固定的单一不确定性度量, 会片面刻画测试输入的错误失效风险, 从而降低排序的准确性. 另一方面, 对模型内部结构微小扰动的刻画不充分, 难以揭示其对决策边界动态变化的影响, 易忽视模型的深层脆弱性, 从而降低早期故障检测效率. 基于此, 提出一种融合双视角不确定性度量与双代理模型池的DNN测试输入优先级排序新方法. 该方法以预测测试输入误分类概率, 并构建输入侧与模型侧的风险协同排序机制为核心目标. 首先, 在输入侧, 为突破单一不确定性指标与静态评估的局限, 利用测试时增强(test-time augmentation, TTA)实施动态鲁棒性评估, 并设计双视角不确定性指标, 以识别测试输入在不同扰动下的潜在失效风险, 提高排序整体性能; 其次, 在模型侧, 构建结合深度集成与模型变异微调的双代理模型池, 量化多模型间的预测分歧, 并设计模型内部结构的动态扰动机制, 暴露模型的深层脆弱性, 以提升早期故障检测效率. 最后, 将输入侧潜在失效风险特征与模型侧决策边界脆弱性特征统一表示为误分类特征, 据此特征, 利用轻量级元模型预测测试输入的错误概率并进行排序, 以降低人工标注成本. 通过与9个已有方法在5个实验对象上的对比发现, 所提方法是可行高效的, 在APFD与RAUC-100指标上分别平均提升约11.92%、28.85%.

新论文 · v1arXiv:2611.05759

PAYWORTHY: Can LLMs Predict Which Freelance Jobs an AI Agent Will Complete?

Mohammad Reza Rezaei, Dingxian Wang, Brett Levert, Celeste Fejzo, Andrew Rabinovich, Zhao Chen

原文摘要

Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed. We test whether frontier language models can make this call before any attempt. We propose PAYWORTHY which contains 1{,}494 real freelance job postings, sampled from 18.8M postings made between 2020 and 2026 on a freelancing platform. An agent attempts each job from the posting alone in a single run, and an LLM judge acting as the client decides whether to accept the work. We ask 18 models to forecast how likely the agent is to succeed and measure how well each model's forecasts rank the accepted jobs above the rejected ones (AUC, where 0.5 is a random ranking). The answer depends on how the agent is described. Told what the agent cannot do, every model ranks the jobs well (AUC 0.66--0.86). Told instead that it is a generic agent with a browser and code execution, the same models rank the same jobs about as well as a random ordering (0.45--0.56). These results hold under judges from four other model families (Claude, GLM, Kimi and Qwen), and the informed forecasts also rank the verdicts of two human raters. Code is available at https://github.com/upwork/Payworthy

cs.AI · cs.CL

新论文 · v1arXiv:2611.05758

Mechanical Engineering Skills: An Open Library of Agent Skills for Design, Analysis and Manufacturing

Achuth Chandrasekhar, Jesse Barkley, Peter Pak, Rumi Loghmani, Aakash Oza, Amir Barati Farimani

原文摘要

Mechanical engineers use specialized tools for CAD, simulation, manufacturing and research, each with a distinct interface and learning curve. We present Mechanical Engineering Skills, an open library of 33 agent skills that makes these capabilities accessible through a single text or voice conversation. Each skill combines operating instructions, executable tools and verification procedures. A language model interprets the request, selects and coordinates skills, while deterministic tools perform computations and return checked results. Default workflows require no tool-specific interface training, local model execution or model fine-tuning; skills load on demand and install with one command. Nineteen skills adapt published or preprint research from our laboratory, including text-to-CAD, linkage synthesis, CFD setup, stress-field and lattice surrogates, equation discovery, additive-manufacturing planning and in-process monitoring. Fourteen additional skills support core engineering and education. We describe the skill format, design principles and a method for translating research into practical workflows. Five case studies with explicit evidence scopes and independent reruns demonstrate exact analytical agreement for lattice homogenization, rocket apogee predictions within 4% of stored OpenRocket references, an equation fit nine times more accurate than a cubic polynomial at an unseen temperature, and an end-to-end rehearsal of porosity monitoring. Controlled agent comparisons remain future work. The open library is available at https://github.com/BaratiLab/mechanical-engineering-skills.

cs.MA

新论文 · v1arXiv:2611.05756

Flow-Optimal Separators for Minor-Free and Induced-Minor-Free Graphs in Linear Time via Follow the Regularized Leader

Hung Le, Jack Spalding-Jamieson

原文摘要

We give a new algorithm for finding balanced separators in minor-free and induced-minor-free graphs. A key technical idea is a new connection to online learning: we formulate a continuous, non-convex optimization problem and solve it using the Follow the Regularized Leader (FTRL) framework. Our implementation of each FTRL step yields a purely combinatorial algorithm that assigns and adjusts vertex weights over multiple rounds. For graphs with $n$ vertices and $m$ edges, we obtain the following results. (1) For $H$-induced-minor-free graphs, we find a balanced separator of size $O(\log(|V(H)|)\sqrt{|V(H)|+|E(H)|}\sqrt{m})$ in expected linear time for fixed $H$. As a corollary, we find balanced separators of size $O(\sqrt{m})$ in string graphs in expected linear time, without requiring string representations. (2) For $K_h$-minor-free graphs, we find a balanced separator of size $O(h\log h\sqrt{n})$ in expected linear time for fixed $h$. Our algorithm unifies two long lines of work on separators in minor-free graphs, dating back to Alon, Seymour, and Thomas (1990): one optimizing separator size and the other optimizing running time. It also gives a natural interpretation of the vertex weighting scheme in a recent linear-time algorithm by Bonnet, Korhonen, Le, Li, and Masarik (2026). The separator bounds for both graph classes are flow-optimal: techniques based on flow-cut duality, including ours, cannot yield balanced separators of asymptotically smaller size.

cs.DS

新论文 · v1arXiv:2611.05755

Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models

Wuyang Zhang, Xiaolin Xu

原文摘要

Classifier-Free Guidance is a widely used inference-time guidance rule for conditional image generation with diffusion models, which exposes a guidance scale that adjusts conditioning strength after training. This flexibility requires conditional and unconditional model evaluations at every sampling step, so an N-step trajectory takes 2N forward passes. Single-pass alternatives reduce such cost, yet most collapse CFG's two components into one opaque guided prediction, losing the separable base flow and guidance direction that support per-step control and diagnostics, even when the scale remains adjustable. This work introduces CtrlFlow, a single-pass guidance method that preserves CFG's separable base-flow and guidance-direction interface. To preserve both components at one-pass cost, CtrlFlow attaches two lightweight LoRA adapters to a frozen backbone, each adding 2.5% parameters, and predicts the base flow and guidance direction from one pass of the shared frozen backbone. Because the guidance scale multiplies the guidance direction only after the forward pass, one evaluation yields the guided velocity at any scale, so a single trained checkpoint remains adjustable at inference without retraining. Preserving two outputs introduces a training mismatch: inference amplifies guidance-direction errors by the chosen scale, while naive component-wise losses weight both outputs equally. To align training with this composed inference-time error, CtrlFlow uses a unified multi-scale distillation loss. Residual guidance errors can still persist at extreme scales, where even small guidance-direction errors are amplified by the guidance scale. To reduce this inference-time error, CtrlFlow applies scale-adaptive modulation to damp velocity-field errors and time-grid warping to concentrate solver evaluations where the trajectory changes most rapidly.

cs.CV · cs.GR

版本更新 · v2arXiv:2606.04594

Ekka: Automated Diagnosis of Silent Errors in LLM Inference

Yile Gu, Zhen Zhang, Shaowei Zhu, Xinwei Fu, Jun Wu, Yida Wang, Baris Kasikci

原文摘要

LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introduce silent errors where output quality silently degrades without any explicit error signals. Diagnosing silent errors is notoriously difficult due to the substantial semantic gap between the high-level symptoms and the low-level root causes. We observe that diagnosis of silent errors can be effectively framed as a differential debugging problem by leveraging the existence of semantically correct reference implementations. We propose Ekka, an automated diagnosis system that identifies root causes by systematically aligning and comparing intermediate execution states between a target and a reference framework. We constructed a benchmark of real-world silent errors from popular serving frameworks, where Ekka shows 80% pass@1 diagnosis accuracy and 88% pass@5 diagnosis accuracy, outperforming state-of-the-art systems. Ekka also diagnoses 4 new silent errors from serving frameworks, all of which have been confirmed by the developers.

cs.DC · cs.AI · cs.SE

新论文 · v1arXiv:2611.05754

GRASP: Gradient-Guided Sampling for Contact-Rich Physics-Based Motion Retargeting

Yang Liu, Tong Wang, Yiming Bao, Heng Yang

原文摘要

We study physics-based retargeting of human demonstrations for robot learning: finding robot controls that reproduce reference motions under contact dynamics. We propose GRASP (Gradient Recovery from Archived Samples for Proposals), which combines sampling-based exploration with gradient-guided refinement without requiring a differentiable simulator. GRASP-TO extends tempered sequential Monte Carlo by fitting local quadratic cost models to archived rollouts and using their gradients to guide Markov chain Monte Carlo rejuvenation. Metropolis-Hastings correction preserves the target distribution for each fixed proposal kernel, and a population analysis connects the recovered gradients to Gaussian smoothing. GRASP-MPC scales this optimizer to long demonstrations through warm-started receding-horizon planning. Experiments on dexterous hands and humanoids show accurate retargeting with a shared tracking objective and no task-specific contact rewards, including 92.8% success on 1352 bimanual OakInk2 demonstrations. The refined references improve PPO tracking in pen spinning and humanoid-object interaction. We also demonstrate dexterous manipulation and whole-body humanoid motion on real hardware.

cs.RO

新论文 · v1arXiv:2611.05753

Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex

Andrew Miracle, Phyl Georgiou, Christine Okoth, Ese Monday

原文摘要

Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.

cs.AI · cs.IR

版本更新 · v3arXiv:2404.17144

Sensor Response-Time Reduction using Long-Short Term Memory Network Forecasting

Simon J. Ward, Muhamed Baljevic, Sharon M. Weiss

原文摘要

The response time of a biosensor is a crucial metric in safety-critical applications such as medical diagnostics where an earlier diagnosis can markedly improve patient outcomes. However, the speed at which a biosensor reaches a final equilibrium state can be limited by poor mass transport and long molecular diffusion times that increase the time it takes target molecules to reach the active sensing region of a biosensor. While optimization of system and sensor design can promote molecules reaching the sensing element faster, a simpler and complementary approach for response time reduction that is widely applicable across all sensor platforms is to use time-series forecasting to predict the ultimate steady-state sensor response. In this work, we show that ensembles of long short-term memory (LSTM) networks can accurately predict equilibrium biosensor response from a small quantity of initial time-dependent biosensor measurements, allowing for significant reduction in response time by a mean and median factor of improvement of 18.6 and 5.1 respectively. The ensemble of models simultaneously estimates uncertainty, which is vital for ensuring confidence in the predictions and subsequent safety-related decisions that are made. This approach is demonstrated on real-time experimental data collected by exposing porous silicon biosensors to buffered protein solutions using a multi-channel fluidic cell that enables the automated measurement of 100 porous silicon biosensors in parallel. The dramatic improvement in sensor response time achieved using LSTM network ensembles and associated uncertainty quantification opens the door to trustworthy and faster responding biosensors, enabling more rapid medical diagnostics for faster clinical decision making that can lead to improved patient outcomes and healthcare access, as well as quicker identification of toxins in food and the environment.

cs.LG · eess.SP

新论文 · v1arXiv:2611.05751

Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs

Gengyu Rao, Ghadeer Ahmed H Alabandi, Su Ann Chong, Thomas Huber, Kailash Gogineni, Subhajit Dutta Chowdhury, Saleel Kudchadker, Suchita Pati 等 31 位作者

原文摘要

Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus

cs.AR · cs.AI

版本更新 · v3arXiv:2507.22186

Scalable Source Selection for Machine Learning Tasks

Ambarish Singh, Romila Pradhan

原文摘要

Given a query table, existing data lake discovery techniques seek to identify data sources related to the query table through schema similarity and joinability. The discovered sources, however, are not always useful for downstream analyses; while some improve task generalization, some have the potential to inadvertently introduce harmful noise or distribution shifts. We formalize source selection as the problem of finding a subset of the discovered sources that maximizes downstream task utility. We propose Splice, a target- and cost-aware source selection system that adopts the idea of gene splicing to identify sources which provide additional signals that the union of all sources misses. To speed up the process, we develop two surrogate variants, Splice-DP and Splice-Grad, that estimate the marginal contribution of subsets to task utility by leveraging data profiles in a meta-learning approach and gradient alignment, respectively. On classification tasks over two real-world benchmarks derived from SOTA table union search tools, Splice shows 3-5 percentage points improvement in binary F1 scores compared to the case when all discovered tables are considered. On five additional real-world ML tasks spanning classification and regression, Splice improves task utility over the all-sources baseline by 1.8-13.7 points, while Splice-DP and Splice-Grad match this quality with 3-7x fewer model evaluations (up to 77x at scale).

cs.LG · cs.AI · cs.DB

版本更新 · v2arXiv:2606.30356

OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL

Karl El Hajal, Mathew Magimai. -Doss

原文摘要

We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE couples masked latent prediction and waveform reconstruction through a functional separation within a single encoder: reconstruction constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations for robust downstream performance, with waveform view augmentations defining the invariances they learn. To the best of our knowledge, OLIVE is the first speech SSL model that directly reconstructs waveforms, retains its vocoder after pre-training, and remains competitive on discriminative tasks. Adding reconstruction largely preserves the speech recognition performance of masked latent prediction alone, while improving waveform reconstruction and speaker tasks. Adding waveform mixup and gain augmentations provides a controllable way to shift the representations further toward speaker, generation, and reconstruction tasks, while remaining competitive on recognition and semantic tasks.

cs.CL · cs.LG · cs.SD · eess.AS

新论文 · v1arXiv:2611.05750

Follow or Surpass? Collaboration, Sound, and the Recognition of Influence in Lineages of Jazz Trumpet Players

Onur Tuncay Bal, Samuel Coavoux, Nathalia A. Loureiro, Balazs Vedres, Mark Wittek

原文摘要

Cultural fields cohere not only horizontally, through collaboration, but also vertically, through lineages of artistic influence. Considerable attention has been devoted to collaboration networks in various fields of creative production; however, we know less about the structure of artistic influence that is nevertheless key to individual artistic development and the evolution of genres. We examine the structure of such an influence network in a genealogy of 52 prominent jazz trumpet players, combining musicians' discographies, demographic characteristics, geographical locations, and audio analysis of more than 16,000 recordings with exponential random graph models. Direct collaboration, overlap in collaborators, and sonic context similarity, that is, the similarity of the recordings on which players appear, are each associated with an ascribed influence tie, net of the others. Not surprisingly, ascribed ties connect musicians whose recordings share a similar sonic context, but musicians also tend to collaborate with their influences and share collaborators with them. However, players whose recordings share a sonic context and who move in the same circle of collaborators can be thought of as peers or rivals, rather than as influences of each other, because lineage implies a succession predicated on difference as much as on continuity. Taken together, our findings suggest that a field's account of its own evolution is neither a record of who played together nor a map of shared sonic contexts, but a selective ordering that requires both. While our data do not permit a causal account, our aim is to provide a rich and varied methodological strategy and descriptive as well as inferential tools to understand the yet understudied vertical integration of cultural fields through influence ties.

cs.SI · stat.AP