视觉大模型 / VLM

Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation

Yixin Liu, Alexander R. Fabbri, Pengfei Liu, Yilun Zhao, Linyong Nan, Ruilin Han, Simeng Han, Shafiq Joty, Chien-Sheng Wu, Caiming Xiong, Dragomir Radev

专题命中 视觉定位与Grounding ：grounding(title)

Comments ACL 2023 Camera Ready

Non-Sequential Graph Script Induction via Multimedia Grounding

Yu Zhou, Sha Li, Manling Li, Xudong Lin, Shih-Fu Chang, Mohit Bansal, Heng Ji

专题命中 视觉定位与Grounding ：grounding(title)

chatClimate: Grounding Conversational AI in Climate Science

Saeid Ashraf Vaghefi, Qian Wang, Veruska Muccione, Jingwei Ni, Mathias Kraus, Julia Bingler, Tobias Schimanski, Chiara Colesanti-Senni, Nicolas Webersinke, Christrian Huggel, Markus Leippold

专题命中 视觉定位与Grounding ：grounding(title)

Event Linking: Grounding Event Mentions to Wikipedia

Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth

专题命中 视觉定位与Grounding ：grounding(title)

Comments 9 pages, 9 tables, 1 figure. Main Conference of EACL 2023

Grounding Game Semantics in Categorical Algebra

Jérémie Koenig

专题命中 视觉定位与Grounding ：grounding(title)

Comments In Proceedings ACT 2021, arXiv:2211.01102

Journal ref EPTCS 372, 2022, pp. 368-383

YFACC: A Yorùbá speech-image dataset for cross-lingual keyword localisation through visual grounding

Kayode Olaleye, Dan Oneata, Herman Kamper

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted to IEEE SLT 2022

CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings

Gabriel Skantze, Bram Willemsen

专题命中 视觉定位与Grounding ：grounding(title)

Comments Published in Journal of Artificial Intelligence Research (JAIR)

Journal ref Journal of Artificial Intelligence Research (JAIR), 2022, vol. 74, pp. 1201-1223

Grounding in social media: An approach to building a chit-chat dialogue model

Ritvik Choudhary, Daisuke Kawahara

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted to NAACL 2022 SRW

Grounding Predicates through Actions

Toki Migimatsu, Jeannette Bohg

专题命中 视觉定位与Grounding ：grounding(title)

Towards grounding nuclear physics in QCD

Christian Drischler, Wick Haxton, Kenneth McElvain, Emanuele Mereghetti, Amy Nicholson, Pavlos Vranas, André Walker-Loud

专题命中 视觉定位与Grounding ：grounding(title)

Comments v3: version published in Progress in Particle and Nuclear Physics; v2: updated manuscript based upon community feedback and referee comments. Also, substantially re-written section on two-nucleon lattice QCD controversy. 53.5 pages plus a "few more" references; v1: Contribution to: The tower of effective (field) theories and the emergence of nuclear phenomena; 47 pages plus a "few" references

Attention-Based Keyword Localisation in Speech using Visual Grounding

Kayode Olaleye, Herman Kamper

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted to Interspeech 2021

Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers

Debanjan Chaudhuri, Md Rashad Al Hasan Rony, Jens Lehmann

专题命中 视觉定位与Grounding ：grounding(title)

Comments 16 pages, 3 figures, accepted at ESWC 2021

Robust and Interpretable Grounding of Spatial References with Relation Networks

Tsung-Yen Yang, Andrew S. Lan, Karthik Narasimhan

专题命中 视觉定位与Grounding ：grounding(title)

Comments Findings of Empirical Methods in Natural Language Processing (EMNLP) 2020

Detection and characterisation of two VLM binaries: LP 1033-31 and LP 877-72

Subhajeet Karmakar, A. S. Rajpurohit, F. Allard, D. Homeier

专题命中 视觉定位与Grounding ：VLM(title)

Comments 14 pages, 6 figures, accepted for publication in MNRAS

Discourse Coherence, Reference Grounding and Goal Oriented Dialogue

Baber Khalid, Malihe Alikhani, Michael Fellner, Brian McMahan, Matthew Stone

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted for Publishing at SemDial 2020

NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction

Wenxuan Zhou, Hongtao Lin, Bill Yuchen Lin, Ziqi Wang, Junyi Du, Leonardo Neves, Xiang Ren

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted by WWW2020. Code available at https://github.com/INK-USC/NERO

Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settings

David Schlangen

专题命中 视觉定位与Grounding ：grounding(title)

A Local Resolution of the Problem of Time. XIV. Grounding on Lie's Mathematics

Edward Anderson

专题命中 视觉定位与Grounding ：grounding(title)

Comments 44 pages including 12 figures

Zero-Shot Open Entity Typing as Type-Compatible Grounding

Ben Zhou, Daniel Khashabi, Chen-Tse Tsai, Dan Roth

专题命中 视觉定位与Grounding ：grounding(title)

Comments 16 pages, 5 figures, Accepted at EMNLP 2018

Semantic query-by-example speech search using visual grounding

Herman Kamper, Aristotelis Anastassiou, Karen Livescu

专题命中 视觉定位与Grounding ：grounding(title)

Comments Accepted to ICASSP 2019

Multimodal Grounding for Sequence-to-Sequence Speech Recognition

Ozan Caglayan, Ramon Sanabria, Shruti Palaskar, Loïc Barrault, Florian Metze

专题命中 视觉定位与Grounding ：grounding(title)

Comments ICASSP 2019

Grounding the Semantics of Part-of-Day Nouns Worldwide using Twitter

David Vilares, Carlos Gómez-Rodríguez

专题命中 视觉定位与Grounding ：grounding(title)

Comments In PEOPLES2018 short papers (NAACL workshop), 6 pages, 5 figures, 1 table

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

Michael Spranger, Jakob Suchan, Mehul Bhatt, Manfred Eppe

专题命中 视觉定位与Grounding ：grounding(title)

Comments in: Pham, D.-N. and Park, S.-B., editors, PRICAI 2014: Trends in Artificial Intelligence, volume 8862 of Lecture Notes in Computer Science, pages 958-971. Springer

Theoretical Grounding for Estimation in Conditional Independence Multivariate Finite Mixture Models

Xiaotian Zhu, David R. Hunter

专题命中 视觉定位与Grounding ：grounding(title)

Comments 21 pages, 1 figure

Relational causality and classical probability: Grounding quantum phenomenology in a superclassical theory

Gerhard Groessing, Siegfried Fussy, Johannes Mesa Pascasio, Herbert Schwabl

专题命中 视觉定位与Grounding ：grounding(title)

Comments 22 pages, 5 figures; talk presented at the 2nd international symposium on "Emergent Quantum Mechanics" (Vienna, Austria, 3-6 October, 2013), http://www.emqm13.org/. To be published in J. Phys.: Conf. Ser. (2014)

Journal ref J. Phys.: Conf. Ser. (2014) 504 012006

On the grounding of spin effects in theory of synchrotron radiation

V. A. Bordovitsyn, A. N. Myagkii

专题命中 视觉定位与Grounding ：grounding(title)

Comments 6 pages, LATEX

Journal ref Nucl. Instr. and Meth. A448 (2000) 81-84

Grounding Bohmian Mechanics in Weak Values and Bayesianism

H. M. Wiseman

专题命中 视觉定位与Grounding ：grounding(title)

Comments 11 pages

Journal ref New J. Phys. 9 165 (2007)

Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents

当状态成为攻击面：大语言模型驱动的具身智能体中的状态语义注入

Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu

机构 * Wuhan University（武汉大学） ； University at Buffalo（布法罗大学） 纠错

专题命中 视觉定位与Grounding ：grounding(abstract,abstract_cn)；分类 cs.AI

AI总结 该文聚焦LLM驱动的具身智能体，梳理其技术演进与现有模型，指出其需结合多类信息完成任务落地后执行，为后续状态语义注入攻击研究奠定基础。

Comments submitted to USENIX Security 2027

Neurosymbolic Embodied Agents

神经符号具身智能体

Mohammad Albinhassan, Yuming Feng, Alessandra Russo, Pranava Madhyastha

机构 * Imperial College London（帝国理工学院） ； Johns Hopkins University（约翰斯·霍普金斯大学） ； City, University of London（伦敦城市大学） 纠错

专题命中 视觉定位与Grounding ：vision-language model(abstract)；grounding(abstract)；分类 cs.AI

AI总结 该研究提出一种神经符号具身智能体，将长周期家庭任务分解为视觉探索与符号规划，在VirtualHome、ALFWorld基准测试中表现优异，约束与搜索结合可大幅提升任务解决率，且无需专门训练。

Counterfactual Sensitivity Is Not Repairability: Auditing Replay Probes for Video Evidence

反事实敏感性不等于可修复性：针对视频证据的重播探针审计

Rama AlHamidi, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

专题命中 视觉定位与Grounding ：grounding(abstract,abstract_cn)；分类 cs.CV

AI总结 本研究提出黑盒反事实探针 CARVE，通过对比 SHAM 与 DESTROY 重播下的答案变化，审计视频智能体的证据依赖，在 LVBench 上取得准确率提升，验证了反事实敏感性与可修复性的差异。

Comments 23 pages, 2 figures. Code: https://github.com/KurbanIntelligenceLab/CARVE