视觉大模型 / VLM

Few-Shot Visual Grounding for Natural Human-Robot Interaction

Giorgos Tziafas, Hamidreza Kasaei

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

Comments 6 pages, 4 figures, ICARSC2021 accepted

Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding

Long Chen, Wenbo Ma, Jun Xiao, Hanwang Zhang, Shih-Fu Chang

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

Comments Camera ready version at AAAI 2021, Codes are available at: https://github.com/ChopinSharp/ref-nms

Grounding Language to Autonomously-Acquired Skills via Goal Generation

Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud

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

Comments Published at ICLR 2021

Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding

Dexin Wang, Deyi Xiong

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

Contrastive Learning for Weakly Supervised Phrase Grounding

Tanmay Gupta, Arash Vahdat, Gal Chechik, Xiaodong Yang, Jan Kautz, Derek Hoiem

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

Comments ECCV 2020 (spotlight paper), Project page: http://tanmaygupta.info/info-ground

Options as responses: Grounding behavioural hierarchies in multi-agent RL

Alexander Sasha Vezhnevets, Yuhuai Wu, Remi Leblond, Joel Z. Leibo

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

Comments First two authors contributed equally

Journal ref International Conference on Machine Learning 2020

Unsupervised Online Grounding of Natural Language during Human-Robot Interactions

Oliver Roesler

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

Comments 11 pages, 6 figures, 3 tables; Published in Proceedings of the Second Grand Challenge and Workshop on Multimodal Language (Challenge-HML) in the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)

Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL

Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud

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

MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level

Amar Shrestha, Krittaphat Pugdeethosapol, Haowen Fang, Qinru Qiu

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

Comments Submitted to The 2020 European Conference on Computer Vision (ECCV 2020)

Visual Grounding in Video for Unsupervised Word Translation

Gunnar A. Sigurdsson, Jean-Baptiste Alayrac, Aida Nematzadeh, Lucas Smaira, Mateusz Malinowski, João Carreira, Phil Blunsom, Andrew Zisserman

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

Comments CVPR 2020

Journal ref CVPR 2020

Contextual Grounding of Natural Language Entities in Images

Farley Lai, Ning Xie, Derek Doran, Asim Kadav

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

Comments Accepted to NeurIPS 2019 workshop on Visually Grounded Interaction and Language (ViGIL)

Task-Oriented Language Grounding for Language Input with Multiple Sub-Goals of Non-Linear Order

Vladislav Kurenkov, Bulat Maksudov, Adil Khan

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

Dynamic Attention Networks for Task Oriented Grounding

Soumik Dasgupta, Badri N. Patro, Vinay P. Namboodiri

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

Comments Accepted ICCV 2019 Workshop

Multi-level Multimodal Common Semantic Space for Image-Phrase Grounding

Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, Shih-Fu Chang

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

Comments Accepted in CVPR 2019

Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder

Masataro Asai, Hiroshi Kajino

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

Comments Accepted in 29th International Conference of Automated Planning and Scheduling (ICAPS-2019), Planning and Learning track

Unsupervised Grounding of Plannable First-Order Logic Representation from Images

Masataro Asai

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

Comments Accepted in 29th International Conference of Automated Planning and Scheduling (ICAPS-2019), Planning and Learning track

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu

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

Comments CoRL 2018

Gated-Attention Architectures for Task-Oriented Language Grounding

Devendra Singh Chaplot, Kanthashree Mysore Sathyendra, Rama Kumar Pasumarthi, Dheeraj Rajagopal, Ruslan Salakhutdinov

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

Comments To appear in AAAI-18

Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions

Jakob Suchan, Mehul Bhatt

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

Comments to appear in: ICCV 2017 Workshop - Vision in Practice on Autonomous Robots (ViPAR), International Conference on Computer Vision (ICCV), Venice, Italy

Grounding of Textual Phrases in Images by Reconstruction

Anna Rohrbach, Marcus Rohrbach, Ronghang Hu, Trevor Darrell, Bernt Schiele

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

Comments published at ECCV 2016 (oral); updated to final version

Talking about the Moving Image: A Declarative Model for Image Schema Based Embodied Perception Grounding and Language Generation

Jakob Suchan, Mehul Bhatt, Harshita Jhavar

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

Comments 19 pages. Unpublished report

AffordanceSAM: Segment Anything Once More in Affordance Grounding

可负担性语义分割模型：在可负担性基础上再次分割任何事物

Dengyang Jiang, Zanyi Wang, Hengzhuang Li, Sizhe Dang, Teli Ma, Wei Wei, Guang Dai, Lei Zhang, Harry Yang, Mengmeng Wang

机构 * SGIT AI Lab（SGIT人工智能实验室） ； NWPU（西北工业大学） ； HKUST（香港科技大学） ； XJTU（西安交通大学） ； HUST（华中科技大学） ； ZJUT（浙江工业大学） 纠错

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

AI总结 研究聚焦全监督可负担性基础，提出AffordanceSAM，通过设计适应模块和标注数据集，以三阶段训练方式扩展SAM泛化能力，在AGD20K基准上达最优性能，展现强大泛化能力。

Comments [ACM MM 2026] SAM Meets Affordance Grounding

SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses

SPLIT：英语和乌克兰语LLM回应中的跨语言共情与文化根基

Anna Chorna

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

AI总结 提出SPLIT基准测试，评估LLM在英语和乌克兰语危机情境下的共情准确性、语言自然性和文化根基，发现模型在乌克兰语中表现下降，且人类与AI评估者一致性弱。

Comments 19 pages, 5 figures, 3 tables. Benchmark paper introducing SPLIT for evaluating empathy, linguistic naturalness, and cultural grounding in English and Ukrainian LLM responses

DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework

DEGround：一种有效的基于自身视角的3D视觉定位基线框架

Yani Zhang, Dongming Wu, Hao Shi, Yingfei Liu, Tiancai Wang, Xingping Dong

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院） ； MMLab, The Chinese University of Hong Kong（香港中文大学MMLab） ； Tsinghua University（清华大学） 纠错

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

AI总结 本文提出DEGround框架，通过统一的框架实现检测与定位的物体级共享，引入两个任务特定模块提升细粒度指令定位性能，实验表明在多个基准上表现最佳，尤其在EmbodiedScan数据集上精度提升显著。

Comments 1st place on EmbodiedScan visual grounding

Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning

通过在线强化学习将大语言模型接地于交互环境

Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer

机构 * Inria (Flowers)（Inria（Flowers）） ； University of Bordeaux（波尔多大学） ； Hugging Face ； Univ Angers, LERIA, SFR MATHSTIC（昂热大学，LERIA，SFR MATHSTIC） ； Sorbonne Université（索邦大学） 纠错

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

AI总结 本文提出GLAM方法，通过在线强化学习将大语言模型接地于交互环境，以提升样本效率和泛化能力，并探讨在线学习的影响。

Comments The associated code can be found at https://github.com/flowersteam/Grounding_LLMs_with_online_RL. This is an extended version of the paper published at ICML 2023: https://proceedings.mlr.press/v202/carta23a

Journal ref PMLR 202 (2023):3676-3713

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

Tianxu Wang, Zhuofan Zhang, Ziyu Zhu, Yue Fan, Jing Xiong, Pengxiang Li, Xiaojian Ma, Qing Li

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Tsinghua University（清华大学） ； Peking University（北京大学） ； Beijing Institute of Technology（北京理工大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；分类 cs.CV；multimodal large language model(comments)

Comments Update v3 of the NeurIPS 2025 Datasets and Benchmarks paper (v2), including additional evaluations of state-of-the-art multimodal large language models. Project page: https://anywhere-3d.github.io/

A Roadmap for Embodied and Social Grounding in LLMs

Sara Incao, Carlo Mazzola, Giulia Belgiovine, Alessandra Sciutti

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

Comments Accepted Version of a conference paper presented at Robophilosophy Conference 2024

Journal ref Incao, S., Mazzola, C., Belgiovine, G., Sciutti, A., 2025, A Roadmap for Embodied and Social Grounding in LLMs. In J. Seibt, P. Fazekas, & O. S. Quick (Eds.), Social Robots with AI: Prospects, Risks, and Responsible Methods, IOS Press

Reflex-Based Open-Vocabulary Navigation without Prior Knowledge Using Omnidirectional Camera and Multiple Vision-Language Models

Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa, Naoto Tsukamoto, Kei Okada, Masayuki Inaba

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

Comments Accepted at Advanced Robotics, website - https://haraduka.github.io/omnidirectional-vlm/

Eating Smart: Advancing Health Informatics with the Grounding DINO based Dietary Assistant App

Abdelilah Nossair, Hamza El Housni

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

Comments The work presented in this paper was part of the proceedings for the First International Conference on Artificial Intelligence (ICATA 2024)

Journal ref Eating Smart: Advancing Health Informatics with the Grounding DINO-based Dietary Assistant App, International Journal of Scientific and Innovative Studies, June 2024, Volume 3, Number 3, Pages 26-34, Available online at IJSRIS

Mask Grounding for Referring Image Segmentation

Yong Xien Chng, Henry Zheng, Yizeng Han, Xuchong Qiu, Gao Huang

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

Comments Accepted by CVPR2024; Project page: https://yxchng.github.io/projects/mask-grounding