视觉大模型 / VLM

From Grounding to Stabilisation: Adequacy as a Criterion for Scientific Explanation

从基础到稳定化：充足性作为科学解释的标准

Jonathon Sendall

专题命中 视觉定位与Grounding ：grounding(title,abstract)

AI总结 本文提出基于稳定化的科学解释标准，通过可测量不变性测试解决无限倒退问题，统一理论变化、量子测量和数学有效性等核心问题。

Comments 14 pages

The Vector Grounding Problem

向量语义问题

Dimitri Coelho Mollo, Raphaël Millière

机构 * Umeå University（乌梅大学） ； University of Oxford（牛津大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

AI总结 本文探讨了大型语言模型是否能通过指涉 grounding 实现对现实世界的联系，提出了基于因果-信息关系和选择历史的判断标准。

Comments Accepted for publication in Philosophy and the Mind Sciences

Grounding LLM Reasoning with Knowledge Graphs

通过知识图谱 grounding 大语言模型的推理

Alfonso Amayuelas, Joy Sain, Simerjot Kaur, Charese Smiley

机构 * UC Santa Barbara（加州大学圣巴巴拉分校） ； JP Morgan AI Research（摩根大通人工智能研究） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

AI总结 通过知识图谱 grounding 大语言模型的推理，提升推理的准确性和可解释性

Skypilot: Fine-Tuning LLM with Physical Grounding for AAV Coverage Search

Skypilot: 通过物理现实 grounding 提升 LLM 在 AAV 覆盖搜索中的微调

Zhongkai Chen, Yihao Sun, Chao Yan, Han Zhou, Xiaojia Xiang, Jie Jiang

机构 * College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学） ； College of Automation Engineering, Nanjing University of Aeronautics and Astronautics（自动化工程学院，南京航空航天大学） ； China Academy of Launch Vehicle Technology（中国运载火箭技术研究院） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

AI总结 Skypilot通过结合MCTS和物理感知奖励函数，提升LLM在AAV覆盖搜索中的微调效果，实现高效且高质量的决策与路径规划。

Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback

通过闭环状态反馈接地LLMs用于机器人任务规划

Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami

专题命中 视觉定位与Grounding ：grounding(title,abstract)

AI总结 本文提出BrainBody-LLM方法，通过闭环反馈机制提升LLMs在机器人任务规划中的鲁棒性，实现在复杂任务中的显著性能提升。

Comments Preprint version. Accepted full paper available here: https://advanced.onlinelibrary.wiley.com/doi/10.1002/adrr.202500072

More than A Point: Capturing Uncertainty with Adaptive Affordance Heatmaps for Spatial Grounding in Robotic Tasks

Xinyu Shao, Yanzhe Tang, Pengwei Xie, Kaiwen Zhou, Yuzheng Zhuang, Xingyue Quan, Jianye Hao, Long Zeng, Xiu Li

机构 * Shenzhen International Graduate School, Tsinghua University, China（清华大学深圳国际研究生院） ； Noah’s Ark Lab, Huawei, China（华为诺亚实验室） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments More details and videos can be found at https://robo-map.github.io

Case Law Grounding: Using Precedents to Align Decision-Making for Humans and AI

Quan Ze Chen, Amy X. Zhang

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments Accepted at ACM Collective Intelligence 2025

The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders

Adrian Sauter, Willem Zuidema, Marianne de Heer Kloots

机构 * Institute for Logic, Language and Computation（逻辑、语言与计算研究所） ； University of Amsterdam（阿姆斯特丹大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments 5 pages, 3 figures, Submitted to ICASSP 2026

Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs

Nicolas Goulet, Alexandre Blondin Massé, Moussa Abdendi

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Artificial Intelligence and Misinformation in Art: Can Vision Language Models Judge the Hand or the Machine Behind the Canvas?

Tarian Fu, Javier Conde, Gonzalo Martínez, Pedro Reviriego, Elena Merino-Gómez, Fernando Moral

专题命中 视觉定位与Grounding ：vision language model(title,abstract)

Near-real-time ship grounding damage assessment using Bayesian networks

Dimitris G. Georgiadis, Manolis S. Samuelides, Daniel Straub

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments Preprint submitted to Elsevier journal

Journal ref Ocean Engineering 339 (2025) 122132

Data-CASE: Grounding Data Regulations for Compliant Data Processing Systems

Vishal Chakraborty, Stacy Ann-Elvy, Sharad Mehrotra, Faisal Nawab, Mohammad Sadoghi, Shantanu Sharma, Nalini Venkatsubhramanian, Farhan Saeed

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments To appear in EDBT '24

Grounding Degradations in Natural Language for All-In-One Video Restoration

Muhammad Kamran Janjua, Amirhosein Ghasemabadi, Kunlin Zhang, Mohammad Salameh, Chao Gao, Di Niu

机构 * Huawei Technologies, Canada（华为技术有限公司，加拿大） ； ECE Department, University of Alberta, Canada（阿尔伯塔大学电子工程系，加拿大） 纠错

专题命中 视觉定位与Grounding ：grounding(title)；分类 cs.CV、cs.AI、cs.LG

Comments 17 pages

Music Grounding by Short Video

Zijie Xin, Minquan Wang, Jingyu Liu, Ye Ma, Quan Chen, Peng Jiang, Xirong Li

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments Accepted to ICCV2025

Subject grounding to reduce electromagnetic interference for MRI scanners operating in unshielded environments

Beatrice Lena, Bart de Vos, Teresa Guallart-Naval, Javad Parsa, Pablo García Cristóbal, Ruben van den Broek, Chloé Najac, Joseba Alonso, Andrew Webb

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments 12 pages (+ 2 SI), 4 figures (+ 1 SI). Comments welcome

Grounding Intelligence in Movement

Melanie Segado, Felipe Parodi, Jordan K. Matelsky, Michael L. Platt, Eva B. Dyer, Konrad P. Kording

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title)；分类 cs.CV、cs.AI、cs.LG

Comments 9 pages, 2 figures

Design and Validation of an Intention-Aware Probabilistic Framework for Trajectory Prediction: Integrating COLREGS, Grounding Hazards, and Planned Routes

Dhanika Mahipala, Trym Tengesdal, Børge Rokseth, Tor Arne Johansen

机构 * Department of Engineering Cybernetics（工程 cybernetics 系） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments IMPORTANT: This preprint is not the final version. The peer-reviewed and updated version is published in Ocean Engineering journal [https://doi.org/10.1016/j.oceaneng.2025.121564]

Journal ref Ocean Engineering 335, 121564 (2025)

From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding

Chiwei Zhu, Benfeng Xu, Xiaorui Wang, Zhendong Mao

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments To be published at ACL 2025

Growing Through Experience: Scaling Episodic Grounding in Language Models

Chunhui Zhang, Sirui, Wang, Zhongyu Ouyang, Xiangchi Yuan, Soroush Vosoughi

机构 * Department of Computer Science, Dartmouth College（达特茅斯学院计算机科学系） ； School of Computer Science, Georgia Institute of Technology（佐治亚理工学院计算机科学学院） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments Accepted at The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz

机构 * Stanford University（斯坦福大学） ； Microsoft Research（微软研究院） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments ACL 2025, 16 pages, 5 figures

Grounding force-directed network layouts with latent space models

Felix Gaisbauer, Armin Pournaki, Sven Banisch, Eckehard Olbrich

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects

Tobias Preintner, Weixuan Yuan, Qi Huang, Adrian König, Thomas Bäck, Elena Raponi, Niki van Stein

机构 * Institute of Advanced Computer Science, Leiden University（先进计算机科学研究所，莱顿大学） ； BMW Group（宝马集团） 纠错

专题命中 视觉定位与Grounding ：grounding(title)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted at IJCNN 2025

Symbol grounding in computational systems: A paradox of intentions

Vincent C. Müller

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Journal ref (2009) Minds and Machines, 19 (4), 529-41

GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization

Gennady Sidorov, Malik Mohrat, Denis Gridusov, Ruslan Rakhimov, Sergey Kolyubin

专题命中 视觉定位与Grounding ：grounding(title)；分类 cs.CV、cs.AI、cs.LG

Comments Project website at https://gsplatloc.github.io/

Grounding Video Models to Actions through Goal Conditioned Exploration

Yunhao Luo, Yilun Du

专题命中 视觉定位与Grounding ：grounding(title)；分类 cs.CV、cs.AI、cs.LG

Comments ICLR 2025 (Spotlight). Project page: https://video-to-action.github.io/

Deictic Codes, Demonstratives, and Reference: A Step Toward Solving the Grounding Problem

Athanassios Raftopoulos, Vincent C. Müller

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Journal ref (2002) in Wayne D. Gray and Christian D. Schunn (eds.), CogSci 2002, 24th annual meeting of the Cognitive Science Society (Mahwah, NY: Lawrence Erlbaum), 762-67

RoboDexVLM: Visual Language Model-Enabled Task Planning and Motion Control for Dexterous Robot Manipulation

Haichao Liu, Sikai Guo, Pengfei Mai, Jiahang Cao, Haoang Li, Jun Ma

专题命中 视觉定位与Grounding ：visual language model(title)；vision-language model(abstract)

CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding

Xingyu "Bruce" Liu, Ruolin Wang, Dingzeyu Li, Xiang 'Anthony' Chen, Amy Pavel

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models

Minh Duc Bui, Katharina von der Wense, Anne Lauscher

专题命中 视觉定位与Grounding ：vision-language model(title,abstract)

Comments Accepted to NAACL 2025 Main (Camera-Ready Version)

Language Writ Large: LLMs, ChatGPT, Grounding, Meaning and Understanding

Stevan Harnad

专题命中 视觉定位与Grounding ：grounding(title,abstract)

Comments 54 pages, 29 references

Journal ref Frontiers in Artificial Intelligence 7: 1490698 (2025)