视觉大模型 / VLM

Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL

代理Jackal：用于文本到JQL的实时执行与语义价值接地

Vishnu Murali, Anmol Gulati, Elias Lumer, Kevin Frank, Sindy Campagna, Vamse Kumar Subbiah

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出Jackal基准，通过实时执行和语义检索工具提升文本到JQL的准确性，验证了代理方法在解决语义歧义中的有效性。

Spatio-Temporal Grounding of Large Language Models from Perception Streams

从感知流中对大语言模型进行时空 grounding

Jacob Anderson, Bardh Hoxha, Georgios Fainekos, Hideki Okamoto, Danil Prokhorov

机构 * Toyota Motor North America Research & Development（丰田北美研发中心） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出FESTS框架，通过将自然语言查询转化为SpRE，为大语言模型注入可验证的时空监督，提升时空推理能力，使30亿参数模型在27k数据上实现87.5%的帧级F1分数，接近GPT-4.1性能。

Grounding AI-in-Education Development in Teachers' Voices: Findings from a National Survey in Indonesia

将教育中的AI发展扎根于教师的声音：来自印度尼西亚全国调查的结果

Nurul Aisyah, Muhammad Dehan Al Kautsar, Arif Hidayat, Fajri Koto

机构 * Quantic School of Business and Technology（昆蒂克商业与技术学院） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Indonesia University of Education（印度尼西亚教育大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 研究通过全国性调查揭示印尼教师对AI在教育中的应用现状，发现AI在教学、内容开发和教学媒体中日益普及，但应用不均，教师更倾向于利用AI减轻教学准备负担。

VoxAnchor: Grounding Speech Authenticity in Throat Vibration via mmWave Radar

VoxAnchor：通过毫米波雷达接地语音真实性 via 喉部振动

Mingda Han, Huanqi Yang, Chaoqun Li, Wenhao Li, Guoming Zhang, Yanni Yang, Yetong Cao, Weitao Xu, Pengfei Hu

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出VoxAnchor系统，通过毫米波雷达捕捉喉部振动，结合语音声学与雷达信号，实现细粒度语音真实性验证，有效检测编辑、拼接等伪造手段。

Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith

以多哈历史词典为基础 grounding Arabic LLMs：检索增强的古兰经和圣训理解

Somaya Eltanbouly, Samer Rashwani

机构 * College of Islamic Studies, Hamad bin Khalifa University（哈马德·本·哈利法大学伊斯兰学院） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出基于多哈历史词典的检索增强生成框架，提升阿拉伯语LLM对历史宗教文本的理解能力，实验表明在Fanar和ALLaM模型上准确率超过85%。

TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

TxSum: 基于微粒语义锚定的用户导向以太坊交易理解

Zifan Peng, Jingyi Zheng, Yule Liu, Huaiyu Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Wuhan University（武汉大学） ； University of North Texas（北卡罗来纳州立大学） ； Fudan University（复旦大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出TxSum任务，通过构建187个复杂以太坊交易数据集，引入MATEX框架提升交易解释质量，使用户对复杂交易的理解率从52.9%提升至76.5%，恶意交易拒绝率提升至88%。

PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A

PaperTrail: 一种用于在基于大语言模型的学术问答中建立溯源的声明-证据接口

Anna Martin-Boyle, Cara A. C. Leckey, Martha C. Brown, Harmanpreet Kaur

机构 * University of Minnesota（明尼苏达大学） ； NASA Langley Research Center（NASA兰利研究中心） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 PaperTrail通过分解LLM回答和源文档为声明与证据，帮助学术领域更严谨地验证LLM的可信度，并揭示其信任worthiness。

Comments 25 pages, 3 figures. Accepted at the ACM CHI conference on Human Factors in Computing Systems 2026

From Crafting Text to Crafting Thought: Grounding AI Writing Support to Writing Center Pedagogy

从文本创作到思维创作：将AI写作支持 grounded 到写作中心教学法

Yijun Liu, John Gallagher, Sarah Sterman, Tal August

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出Writor工具，旨在通过目标设定、平衡反馈和对话来支持写作，而非直接生成文本，以促进学生批判性思维和保留其声音。

Comments Conditionally accepted to CHI 26

Grounding Natural Language to SQL Translation with Data-Based Self-Explanations

通过数据驱动的自我解释实现自然语言到SQL翻译

Yuankai Fan, Tonghui Ren, Can Huang, Zhenying He, X. Sean Wang

机构 * School of Computer Science, Fudan University（复旦大学计算机科学学院） ； Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究所） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

AI总结 本文提出CycleSQL框架，通过数据驱动的自我解释提升自然语言到SQL翻译的准确性和可解释性。

Comments ICDE2025

Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment

Buwei He, Yang Liu, Zhaowei Zhang, Zixia Jia, Huijia Wu, Zhaofeng He, Zilong Zheng, Yipeng Kang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院） ； Peking University（北京大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

Comments Under review

Evaluating Multimodal Large Language Models on Spoken Sarcasm Understanding

Zhu Li, Xiyuan Gao, Yuqing Zhang, Shekhar Nayak, Matt Coler

机构 * University of Groningen, The Netherlands（Groningen大学，荷兰） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(title)

Holistic Versus Fragmented Multiverses: Empirical Access via Causal and Grounding Signatures

Baptiste Le Bihan

专题命中 视觉定位与Grounding ：grounding(title)

Comments Chapter draft for the Blackwell Companion to the Philosophy and the Multiverse

Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models

Atharva Bhargude, Ishan Gonehal, Dave Yoon, Kaustubh Vinnakota, Chandler Haney, Aaron Sandoval, Kevin Zhu

机构 * Algoverse AI Research（Algoverse AI研究院） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(title)

Comments Published at ACL 2025 SRW, 9 pages, 3 figures

"Can You See Me Think?" Grounding LLM Feedback in Keystrokes and Revision Patterns

Samra Zafar, Shifa Yousaf, Muhammad Shaheer Minhas

专题命中 视觉定位与Grounding ：grounding(title)

Comments 15 pages, 4 figures, 6 tables, Submitted to IJCNLP-AACL 2025

AROMA: Mixed-Initiative AI Assistance for Non-Visual Cooking by Grounding Multi-modal Information Between Reality and Videos

Zheng Ning, Leyang Li, Daniel Killough, JooYoung Seo, Patrick Carrington, Yapeng Tian, Yuhang Zhao, Franklin Mingzhe Li, Toby Jia-Jun Li

专题命中 视觉定位与Grounding ：grounding(title)

Chaining Event Spans for Temporal Relation Grounding

Jongho Kim, Dohyeon Lee, Minsoo Kim, Seung-won Hwang

机构 * Seoul National University（首尔国立大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

Comments In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1689-1700

Rethinking Scientific Summarization Evaluation: Grounding Explainable Metrics on Facet-aware Benchmark

Xiuying Chen, Tairan Wang, Qingqing Zhu, Taicheng Guo, Shen Gao, Zhiyong Lu, Xin Gao, Xiangliang Zhang

机构 * King Abdullah University of Science and Technology（国王阿卜杜勒·阿齐兹科技大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； National Institutes of Health（美国国家卫生研究院） ； University of Notre Dame（诺特难大学） ； Shandong University（山东大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)

Comments 14pages

Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory

Haoran Li, Wei Fan, Yulin Chen, Jiayang Cheng, Tianshu Chu, Xuebing Zhou, Peizhao Hu, Yangqiu Song

专题命中 视觉定位与Grounding ：grounding(title)

Comments To appear at NAACL 25

Proactive Detection and Calibration of Seasonal Advertisements with Multimodal Large Language Models

Hamid Eghbalzadeh, Shuai Shao, Saurabh Verma, Venugopal Mani, Hongnan Wang, Jigar Madia, Vitali Karpinchyk, Andrey Malevich

专题命中 视觉定位与Grounding ：multimodal large language model(title)

Mathfish: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula

Li Lucy, Tal August, Rose E. Wang, Luca Soldaini, Courtney Allison, Kyle Lo

专题命中 视觉定位与Grounding ：grounding(title)

Comments 30 pages, 23 figures

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory

Wei Fan, Haoran Li, Zheye Deng, Weiqi Wang, Yangqiu Song

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted by EMNLP 2024

SQLucid: Grounding Natural Language Database Queries with Interactive Explanations

Yuan Tian, Jonathan K. Kummerfeld, Toby Jia-Jun Li, Tianyi Zhang

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted to UIST'24

LMExplainer: Grounding Knowledge and Explaining Language Models

Zichen Chen, Jianda Chen, Yuanyuan Chen, Han Yu, Ambuj K Singh, Misha Sra

专题命中 视觉定位与Grounding ：grounding(title)

Comments 25 pages, 10 figures, and 8 tables

De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding

Aryaz Eghbali, Michael Pradel

专题命中 视觉定位与Grounding ：grounding(title)

Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection

Shruti Palaskar, Oggi Rudovic, Sameer Dharur, Florian Pesce, Gautam Krishna, Aswin Sivaraman, Jack Berkowitz, Ahmed Hussen Abdelaziz, Saurabh Adya, Ahmed Tewfik

专题命中 视觉定位与Grounding ：multimodal large language model(title)

Comments Accepted at Interspeech 2024

Grounding Toxicity in Real-World Events across Languages

Wondimagegnhue Tsegaye Tufa, Ilia Markov, Piek Vossen

专题命中 视觉定位与Grounding ：grounding(title)

Comments Paper accepted for at The 29th International Conference on Natural Language & Information Systems (NLDB 2024)

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

Sina J. Semnani, Violet Z. Yao, Heidi C. Zhang, Monica S. Lam

专题命中 视觉定位与Grounding ：grounding(title)

Comments Findings of EMNLP 2023

Grounding Spatial Relations in Text-Only Language Models

Gorka Azkune, Ander Salaberria, Eneko Agirre

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted in Neural Networks

Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches

Daniel Fried, Nicholas Tomlin, Jennifer Hu, Roma Patel, Aida Nematzadeh

专题命中 视觉定位与Grounding ：grounding(title)

Comments Findings of EMNLP 2023

GG-LLM: Geometrically Grounding Large Language Models for Zero-shot Human Activity Forecasting in Human-Aware Task Planning

Moritz A. Graule, Volkan Isler

专题命中 视觉定位与Grounding ：grounding(title)