Vision-Language Grounding

Follow this topic Ask about this topic

Momentum

44 papers in the last four weeks, up 175% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 288

All topics

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring
Sep 20, 2026Liuyang Song, Yi Zhang, Zhongyi Deng +2Vision-Language Models Vision-Language Grounding
Peking University · Dongguan University of Technology · Sichuan Agricultural University
Pay More Attention To Text In High-Resolution MLLMs
Sep 20, 2026Zhongkuan Mao, Wenzhuo Zhao, Xianjie Liu +7Visual Question Answering Vision-Language Grounding
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University · College of Computer Science, Sichuan University · Peking University +2
DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering
Sep 17, 2026Luca De Grandis, Silvia Cappelletti, William Raccagni +3Visual Question Answering Vision-Language Grounding
University of Modena and Reggio Emilia, Modena, Italy · University of Modena and Reggio Emilia Modena, Italy · University of Pisa, Pisa, Italy +1
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Sep 16, 2026Sara Pieri, Evangelos Kazakos, Shizhe Chen +2Image Captioning Panoptic Segmentation
Inria, École normale supérieure, CNRS, PSL Research University · Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague
RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection
Sep 16, 2026Liyang Fan, Xinping Bi, Yitai Li +3Efficient Multimodal Inference Multimodal Reranking
College of Computer Science and Software Engineering Shenzhen University Shenzhen, China · Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences Shenzhen, China · Shenzhen University of Advanced Technology Shenzhen, China
GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation
Sep 16, 2026Kailing Li, Yu Han, Tianwen Qian +4Vision-Language Navigation Vision-Language Grounding
School of Computer Science and Technology, East China Normal University · NeoteAI · King Abdullah University of Science and Technology
Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models
Sep 15, 2026Ziheng Ren, Qian Gao, Jun Fan +3Hallucination Detection in VLMs Object Hallucination in VLMs
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China · Shandong Engineering Research Center of Big Data Applied Technology, Faculty of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, China · Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan 250014, China +2
sensVLA: Spatially-Grounded Vision-Language-Action Model for Autonomous Wheel Loader
Sep 15, 2026Gopi Krishna Erabati, Bjarne Johannsen, Angus Stewart +1Robotic Control Vision-Language Grounding
sensmore GmbH Berlin, Germany
ProtoLIP: From Sentence-Level to Object-Level Evidence Disentanglement
Sep 14, 2026Yan Zhu, Yongbo Chen, Zhengming Ding +1Vision-Language Models Prototype Learning
Department of Computer Science Tulane University New Orleans, LA, USA
P-POSEMEM: Projective Semantic Memory for Consistent Language Grounding under Pose-Graph Rewrites
Sep 14, 2026Ha Sier, Ali Salmasi, Mengya Xu +5Vision-Language Grounding Graph-Based Agent Memory
Turku Intelligent Embedded and Robotic Systems (TIERS) Lab, University of Turku, Turku, Finland · School of Information Science and Technology, Fudan University, Shanghai, China
AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation
Sep 14, 2026Long Giang Vu, Chengkai Yao, Yuxin Liu +2Vision-Language Navigation Vision-Language Grounding
*These authors contributed equally.
ChitraMiti: Benchmarking Visual Grounding and Modality Reliance in Bengali Geometric Reasoning
Sep 14, 2026Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Sumaiya Tabassum Nimi +1Mathematical Reasoning Benchmarks Multilingual VLM Evaluation
North South University
HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA
Sep 12, 2026Syed Mohaiminul Hoque, Md Sakhawat HossainVLM Evaluation Hallucination Detection in VLMs
Independent Author
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Sep 10, 2026Lisa BylininaWord Embeddings Multimodal Embedding
Institute for Language Sciences Utrecht University
Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World Detection
Sep 9, 2026Ibrohimjon Muminov, Jihie KimOpen-Vocabulary Object Detection Vision-Language Grounding
Dongguk University, Seoul, South Korea · Department of Computer Science and AI, Dongguk University, Seoul, South Korea
FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory
Sep 8, 2026Woosang Jeon, Sanghyeok Choi, Minwoo Kim +2Vision-Language Grounding Information Retrieval
Seoul National University
SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation
Sep 8, 2026Linnan Zhao, Xu Liu, Lingling Li +3Text-Guided Image Segmentation Promptable Image Segmentation
Xidian University Xi’an, China
DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding
Sep 8, 2026Zhuo Cao, Bingqing Zhang, Sen Wang +1Temporal Video Grounding Test-Time Adaptation of VLMs
The University of Queensland, Australia
CLAMP: Constrained Decoding for Vision-Language Embodied Planning
Sep 8, 2026Tianyi Ma, Parisa KordjamshidiConstrained Decoding Vision-Language Grounding
Michigan State University
AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
Sep 8, 2026Shanwei Fan, Bin Zhang, Zhiwei Xu +4Zero-Shot Learning UAV Navigation
National Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, Shandong University, Jinan, Shandong, China
From Coordinates to Candidate Regions: Temporal Change Localization via Region Selection in Remote Sensing Multimodal LLMs
Sep 8, 2026Juwan Chung, Sungjune Park, Yeongyun Kim +1Multimodal Large Language Models Remote Sensing Change Detection
Integrated Vision Language Lab, KAIST, South Korea
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
Sep 8, 2026Bozhou Li, Jiahang Zhang, Yue Ding +11VLM Evaluation Image Captioning
Peking University · Kling Team · Beijing, China +5
DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models
Sep 7, 2026Ami Pandat, Rajasekhar Punna, Gopika Vinod +1Open-Vocabulary Object Detection Vision-Language Grounding
Homi Bhabha National Institute, Mumbai, Maharashtra, India · Bhabha Atomic Research Centre, Mumbai, Maharashtra, India
LOCI: A Locator-Critic with Refinement Loop
Aug 31, 2026Walid Bousselham, Mathilde Caron, Arsha Nagrani +1Visual Question Answering Vision-Language Grounding
Google DeepMind
Cost-efficient Active Learning for Referring Image Segmentation and Grounding
Aug 31, 2026Junbeom Hong, Seonghoon Yu, Hyung Rok Jung +2Active Learning Referring Image Segmentation
1Meissa · 2KAIST · 3GIST +1
Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum
Aug 31, 2026Xingjian Wang, Shijian Wang, Yibo Wang +4Temporal Video Grounding Synthetic Data Generation
1Monash University · 2Southeast University · 3Shanghai University of Electric Power
VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs
Aug 31, 2026Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie +1Hallucination Detection in VLMs VLM Hallucination
School of Computing and Information Systems The University of Melbourne Melbourne, Australia
OPUS: A Simple yet Effective Unified Framework for Open-Vocabulary Detection
Aug 31, 2026Xiaoyan Wei, Zhimin Yao, Ruilin Yang +4Open-Vocabulary Object Detection Vision-Language Grounding
Megvii Technology Inc. · X-Humanoid
Semantic-Spatial Discriminability Enhancement for Generalized Visual Grounding
Aug 31, 2026Kaiyan Lei, Xu-Yao ZhangVision-Language Grounding Visual Grounding
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
ManGo: Manga Active Narrative Grounding Optimization
Aug 30, 2026Hao Qiu, Junyan Wang, Zheyuan Liu +4Visual Question Answering RL for Language Model Reasoning
1Communication University of China · 2Australian Institute for Machine Learning, Adelaide University · University of New South Wales +2

Sep 20, 2026, cs.CVJ/K move · Enter open · S save

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring

Liuyang Song, Yi Zhang, Zhongyi Deng, Daqian Yang+1

Peking University · Dongguan University of Technology · Sichuan Agricultural University

Vision-Language Models Vision-Language Grounding Vision-Language Alignment Compositional Representation Learning

Open paper AskPDF arXiv

Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which region or how those regions are arranged; a model can recognize every word and object yet prefer a compositionally incorrect caption. We argue that a frozen encoder retains this association structure, so the problem is to read it rather than to rebuild it beside the pretrained similarity. We introduce BindCLIP, a pairwise scorer built on one latent object: a balanced token--patch--depth optimal-transport coupling that places both candidate captions and several visual depths in a single plan. Semantic, entity, order, and spatial evidence are read as energies of this state, and exchanging the candidates permutes the plan, making the score exactly antisymmetric. A geometric refinement inside the coupling contracts moves that the candidates and the visual depths do not support. No task label, parser, relation inventory, or detector is used. One checkpoint and one inference path improve the official What'sUp, ARO, and SugarCrepe benchmarks over frozen global CLIP, with the strongest transfer on the relation splits. Controls rule out patch access and caption-length shortcuts, and an inference-time lesion localizes spatial arrangement to the coupling.

Momentum

Related topics

Latest papers 288