VLA / 视觉-语言-动作模型

NeuroSpex: Neuro-Guided Speaker Extraction with Cross-Modal Attention

Dashanka De Silva, Siqi Cai, Saurav Pahuja, Tanja Schultz, Haizhou Li

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation

Bunyamin Keles, Murat Gunay, Serdar I. Caglar

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

Comments 14 pages, 2 figures, 9 tables

LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

Yuhang Yang, Wei Zhai, Hongchen Luo, Yang Cao, Zheng-Jun Zha

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments accept by CVPR2024

MixRED: A Mix-lingual Relation Extraction Dataset

Lingxing Kong, Yougang Chu, Zheng Ma, Jianbing Zhang, Liang He, Jiajun Chen

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition

Jiaming Zhou, Junwei Liang, Kun-Yu Lin, Jinrui Yang, Wei-Shi Zheng

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

A ModelOps-based Framework for Intelligent Medical Knowledge Extraction

Hongxin Ding, Peinie Zou, Zhiyuan Wang, Junfeng Zhao, Yasha Wang, Qiang Zhou

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

Evaluation of Speech Representations for MOS prediction

Frederico S. Oliveira, Edresson Casanova, Arnaldo Cândido Júnior, Lucas R. S. Gris, Anderson S. Soares, Arlindo R. Galvão Filho

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

Comments 12 pages, 4 figures, Accepted to the 26th International Conference of Text, Speech and Dialogue (TSD2023)

PLAtE: A Large-scale Dataset for List Page Web Extraction

Aidan San, Yuan Zhuang, Jan Bakus, Colin Lockard, David Ciemiewicz, Sandeep Atluri, Yangfeng Ji, Kevin Small, Heba Elfardy

专题命中 数据集与评测 ：action model(abstract)；分类 cs.LG

Comments Accepted to ACL Industry Track 2023

Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment

Li Ding, Chenliang Xu

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments CVPR 2018

Journal ref Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 6508-6516

Towards Robust Dataset Learning

Yihan Wu, Xinda Li, Florian Kerschbaum, Heng Huang, Hongyang Zhang

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes

Dongxu Zhang, Sunil Mohan, Michaela Torkar, Andrew McCallum

专题命中 数据集与评测 ：action model(abstract)；分类 cs.AI

Comments LREC 2022 (Oral)

NADE: A Benchmark for Robust Adverse Drug Events Extraction in Face of Negations

Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni, Enrico Santus, Giuseppe Serra

专题命中 数据集与评测 ：action model(abstract)；分类 cs.LG

Comments W-NUT Workshop, EMLNP 2021

Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization

Zicheng Pan, Xiaohan Yu, Miaohua Zhang, Yongsheng Gao

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments 8 pages, 4 figures, accepted by DICTA2021

TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables

Harsh Desai, Pratik Kayal, Mayank Singh

专题命中 数据集与评测 ：action model(abstract)；分类 cs.LG

Progressive Transfer Learning

Zhengxu Yu, Dong Shen, Zhongming Jin, Jianqiang Huang, Deng Cai, Xian-Sheng Hua

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments 10 pages, 4 figures, journel verison of our published short paper on IJCAI2019

Automatic Plant Image Identification of Vietnamese species using Deep Learning Models

Nguyen Van Hieu, Ngo Le Huy Hien

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments 7 pages, 8 figures, 2 tables, Published with International Journal of Engineering Trends and Technology (IJETT)

Journal ref International Journal of Engineering Trends and Technology 68.4(2020):25-31. Published by Seventh Sense Research Group

Neural Probabilistic System for Text Recognition

Najoua Rahal, Maroua Tounsi, Adel M. Alimi

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures

Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, Elsa Olivetti

专题命中 数据集与评测 ：action model(abstract)；分类 cs.LG

Comments Accepted as a long paper at the Linguistic Annotation Workshop (LAW) at ACL 2019

The Impact of Annotation Guidelines and Annotated Data on Extracting App Features from App Reviews

Faiz Ali Shah, Kairit Sirts, Dietmar Pfahl

专题命中 数据集与评测 ：action model(abstract)；分类 cs.LG

From Pose to Activity: Surveying Datasets and Introducing CONVERSE

Michael Edwards, Jingjing Deng, Xianghua Xie

专题命中 数据集与评测 ：action model(abstract)；分类 cs.CV

Comments Presentation of pose-based conversational human interaction dataset, review of current appearance and depth based action recognition datasets, public dataset, 38 pages

EURO-5K: When Does Domain Pretraining Matter? Benchmarking Transformers for EU Reporting Obligation Extraction

EURO-5K：领域预训练何时重要？用于欧盟报告义务提取的Transformer基准测试

Marios Koniaris, Vasileios Kotronis, Eugenia Giannini, Panayiotis Tsanakas

机构 * Division of Computer Science, School of Electrical and Computer Engineering（计算机科学系，电气与计算机工程学院） ； National Technical University of Athens（雅典技术大学） ； Department of Humanities Social Sciences and Law, School of Applied Mathematical and Physical Sciences（人文社会科学与法律系，应用数学与物理科学学院） 纠错

专题命中 数据集与评测 ：action model(abstract)

AI总结 本文构建了EURO-5K数据集，通过对比判别式与生成式模型在欧盟报告义务提取上的表现，发现领域预训练在参数高效微调时收益显著，且模型可作为专用提取器。

High-Dimensional Bayesian Calibration of Expensive Nuclear Models with Differentiable Emulation

高维贝叶斯校准昂贵核模型的可微仿真

Jin Lei

专题命中 数据集与评测 ：action model(abstract)

AI总结 提出DREAM可微校准策略，通过离线采样、奇异值分解压缩和在线可微重建，利用自动微分提供精确似然梯度，实现高维核模型的全贝叶斯校准，应用于d+⁵⁸Ni弹性散射的CDCC分析，在单GPU上十分钟内收敛。

HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds

HypoSpace: 欠定性与次线性覆盖边界下集合值假设生成的诊断基准

Tingting Chen, Beibei Lin, Zifeng Yuan, Qiran Zou, Hongyu He, Anirudh Goyal, Yew-Soon Ong, Dianbo Liu

机构 * National University of Singapore（国立新加坡大学） ； College of Computing（计算学院） ； Data Science（数据科学） ； Nanyang Technological University（南洋理工大学） ； Centre for Frontier AI Research (CFAR)（前沿人工智能研究中心 (CFAR)） ； Agency for Science, Technology and Research（科技研究局） ； Meta Superintelligence Labs（Meta超智能实验室） 纠错

专题命中 数据集与评测 ：action model(abstract)

AI总结 提出HypoSpace基准，通过三个结构化领域评估大语言模型在欠定假设空间中的采样能力，发现模型在高有效性下存在覆盖失败，并展示分层解码可部分缓解该问题。

Precision extraction of the deuteron electric polarizability via the Baldin sum rule with full low-energy coverage

通过Baldin求和规则实现双子素电极化率的精确提取：全低能覆盖

Zi-Rui Hao, Gong-Tao Fan, Qian-Kun Sun, Hong-Wei Wang, Hang-Hua Xu, Long-Xiang Liu, Yue Zhang, Jiunn-Wei Chen, Yu-Xuan Yang, Sheng Jin, Kai-Jie Chen, Zhen-Wei Wang, Xiang-Fei Wang, Meng-Ke Xu, Zhi-Cai Li, Pu Jiao, Meng-Die Zhou, Shan Ye, Yu-Long Shen, Yin-Ji Chen, Hao Zhang, Jian-Jun He, Wen-Qing Shen, Yu-Gang Ma

专题命中 数据集与评测 ：action model(abstract)

AI总结 利用SLEGS实验数据和Baldin规则，首次精确提取双子素电极化率，得到αE=0.637±0.004 fm³，解决实验与理论的矛盾，为核相互作用模型提供高精度基准。

A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction

一种多语言数据集和信息提取中相互强化效应的实证验证

Chengguang Gan, Sunbowen Lee, Qingyu Yin, Yunhao Liang, Xinyang He, Hanjun Wei, Younghun Lim, Shijian Wang, Hexiang Huang, Qinghao Zhang, Shiwen Ni, Tatsunori Mori

机构 * Yokohama National University（横滨国立大学） ； Shenzhen University of Advanced Technology（深圳理工大学） ； Zhejiang University（浙江大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Chengdu Institute of Computer Applications, Chinese Academy of Sciences（中国科学院成都计算机应用研究所） ； Southeast University（东南大学） ； University of Tsukuba（筑波大学） ； Pusan National University（釜山大学） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院） 纠错

专题命中 数据集与评测 ：action model(abstract)

AI总结 本文提出多语言MRE混合数据集，通过LLM辅助框架减少标注工作，验证了多语言环境下信息提取中相互强化效应的普遍性。

Comments Accepted by ACL 2026 Findings

Fairness is in the details: Face Dataset Auditing

细节中的公平性：人脸数据集审计

Valentin Lafargue, Emmanuelle Claeys, Jean-Michel Loubes

专题命中 数据集与评测 ：action model(abstract)

AI总结 本文提出了一种基于敏感特征的自动方法，用于审计人脸数据集以确保公平性。

Journal ref Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track and Demo Track. ECML PKDD 2025. Lecture Notes in Computer Science(), vol 16022. Springer, Cham

Can Indirect Prompt Injection Attacks Be Detected and Removed?

Yulin Chen, Haoran Li, Yuan Sui, Yufei He, Yue Liu, Yangqiu Song, Bryan Hooi

专题命中 数据集与评测 ：action model(abstract)

Comments ACL 2025 Main

Quantitative evaluation of methods to analyze motion changes in single-particle experiments

Gorka Muñoz-Gil, Harshith Bachimanchi, Jesús Pineda, Benjamin Midtvedt, Gabriel Fernández-Fernández, Borja Requena, Yusef Ahsini, Solomon Asghar, Jaeyong Bae, Francisco J. Barrantes, Steen W. B. Bender, Clément Cabriel, J. Alberto Conejero, Marc Escoto, Xiaochen Feng, Rasched Haidari, Nikos S. Hatzakis, Zihan Huang, Ignacio Izeddin, Hawoong Jeong, Yuan Jiang, Jacob Kæstel-Hansen, Judith Miné-Hattab, Ran Ni, Junwoo Park, Xiang Qu, Lucas A. Saavedra, Hao Sha, Nataliya Sokolovska, Yongbing Zhang, Giorgio Volpe, Maciej Lewenstein, Ralf Metzler, Diego Krapf, Giovanni Volpe, Carlo Manzo

专题命中 数据集与评测 ：action model(abstract)

Comments 37 pages, 8 figures. This is the author's version of the article published in Nature Communications under CC BY 4.0. The final published version is available at https://doi.org/10.1038/s41467-025-61949-x

Journal ref Nat Commun 16, 6749 (2025)

LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World

Sina J. Semnani, Pingyue Zhang, Wanyue Zhai, Haozhuo Li, Ryan Beauchamp, Trey Billing, Katayoun Kishi, Manling Li, Monica S. Lam

机构 * Stanford University（斯坦福大学） ； Northwestern University（西北大学） ； ACLED 纠错

专题命中 数据集与评测 ：action model(abstract)

Comments Findings of ACL 2025

VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models

Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng, Irwin King

机构 * The Chinese University of Hong Kong（香港中文大学） ； LIGHTSPEED STUDIOS ； National University of Singapore（新加坡国立大学） 纠错

专题命中 数据集与评测 ：action model(abstract)

Comments The Version of Record of this contribution is accepted to ACL 2025 main conference