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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 10:19 — 2026-11-18 10:19(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2511.15090

SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

Wenhan Yu, Zhaoxi Zhang, Wang Chen, Guanqiang Qi, Weikang Li, Lei Sha, Deguo Xia, Jizhou Huang

原文摘要

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that support the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we introduce SciEGQA, a scientific document question answering and reasoning dataset with semantic evidence grounding, where supporting evidence is represented as semantically coherent document regions annotated with bounding boxes. SciEGQA consists of two components: a **human-annotated fine-grained benchmark** containing 1,623 high-quality question--answer pairs, and a **large-scale automatically constructed training set** with over 30K QA pairs generated through an automated data construction pipeline. Extensive experiments on a wide range of Vision-Language Models (VLMs) show that existing models still struggle with evidence localization and evidence-based question answering in scientific documents. Training on the proposed dataset significantly improves the scientific reasoning capabilities of VLMs. The project page is available at https://yuwenhan07.github.io/SciEGQA-project/.

cs.DB · cs.AI · cs.CV

新论文 · v1arXiv:2611.13919

EAGLE: Early Identification of Information Propagation Sources through Generalized Bayesian Inference in Large-scale Social Networks

Tao Wen, Yu-wang Chen, Jie Zhao, Changchun Pan, Tahir Abbas Syed, Yong-Yeol Ahn, Kang Hao Cheong

原文摘要

In the era of infodemics, rapidly pinpointing information propagation sources is essential for mitigating negative impacts and enhancing societal resilience. This study presents EAGLE (Early identificAtion of propagation sources through GeneraLized Bayesian infErence), a novel and effective framework for early source identification in large-scale social networks, which integrates evolutionary computation to strategically deploy sparse observers with generalized Bayesian inference to aggregate observational data of varying credibility. Unlike existing approaches, our method relies on limited input from human observers and explicitly incorporates the uncertainty and noise of the data. Comprehensive evaluations across diverse networks and propagation scenarios demonstrate that our approach consistently surpasses state-of-the-art models, without relying on assumptions about propagation characteristics or user attributes. Utilizing real-world datasets with empirical propagation paths from Twitter, our method is among the first capable of identifying potential sources in large-scale networks using limited observers, demonstrating its broad applicability. These findings highlight the effectiveness of generalized Bayesian inference in uncovering propagation dynamics and equip organizations and policymakers with critical tools to proactively address threats to digital trust and security.

cs.SI