Overview

Visual grounding studies how systems identify the image regions or objects referred to by language, often producing boxes, points, or masks. Common approaches include aligning text and visual features, selecting among detected objects, using attention or high-resolution crops, and training with localization annotations or reinforcement-learning rewards. The field spans referring-expression benchmarks such as RefCOCO, fine-grained spatial reasoning, medical and remote-sensing images, video, and embodied tasks such as navigation and manipulation. A central challenge is that correct answers do not prove a model used visual evidence: systems still struggle with precise localization, changing scenes, and reliable visual dependence while balancing accuracy, efficiency, and robustness.

Latest papers

CardsList

167 papers21 papers in the last four weeks, down 30% on the four weeks before. 0.1% of all new papers.

  1. MAST: Medoid-Anchored Subspace Steering for Visual Grounding in Multimodal LLMs

    Nov 11, 2026Zhitao Chen, Zhenxin Cai, Jingyuan Li +1Activation SteeringMultimodal Large Language Models

  2. Viscot-steer: Disentangling and Transferring Visual Chain-of-Thought via Activation Steering

    Nov 8, 2026Ningning Wang, Beier Zhu, Xingyu Zhu +2activation steering in vision-language modelsVLM Reasoning

  3. Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-Distillation

    Nov 7, 2026Yujuan Pang, Wenhao Xu, Yinglei TengVisual Evidence Sensitivity in VLMsFine-Grained Visual Perception

  4. AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution

    Nov 3, 2026Suifeng Zhao, Zida Liu, Lei Sun +4Long-Document Visual Question AnsweringVisual Grounding

  5. GAVAGAI: Referential Alignment for Infant-Scale Vision-Language Models via Balanced Optimal Transport

    Oct 30, 2026Rajdeep Pal, Jotiraditya Banerjee, Saptarshi PaniVision-Language AlignmentVisual Grounding

  6. Grounding Image Composition with Label-Conditioned Visual Evidence

    Oct 29, 2026Armin Dadras, Tingyu Lin, Robert Sablatnig +2Visual GroundingImage Segmentation

  7. Surrogate Uncertainty for Black-box Visual Grounding

    Oct 29, 2026Hanbo Zhang, Tianrun Hu, Cedar Site Bai +2Uncertainty QuantificationVisual Grounding

  8. Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

    Oct 29, 2026Guizhen Chen, Weiwen Xu, Wotao Yin +2Multimodal ReasoningVisually Grounded Reasoning

  9. PerceptRL: Making Visual Perception Rewardable in MLLMs from Answers to Interactions

    Oct 27, 2026Tongkun Guan, Zhibo Yang, Mingkun Yang +3Vision-Language ModelsRL for VLMs

  10. AdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding

    Oct 27, 2026Bingchao Wang, Yongcheng Jing, Chengyu Wang +4GUI GroundingVisual Grounding

  11. OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes for Referring Expression Grounding in Aerial Imagery

    Oct 26, 2026Chang Woo Song, Yeong Jun KohVisual GroundingRemote Sensing Visual Grounding

  12. When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders

    Oct 26, 2026Seyedarmin Azizi, Parsa Razmara, Sajjad Ghiasvand +2Demographic Bias in VLMsVLM Safety

  13. What Sketches Tell Us about LVLMs: Conventions, Grounding, and Localisation

    Oct 25, 2026Chaitat Utintu, Ahmed Bourouis, Arkaprabha Basu +1Vision-Language ModelsVLM Interpretability

  14. AgentVQA: A Unified Benchmark for Agentic Visual Understanding

    Oct 22, 2026Advait Gupta, Sachin Konan, Tom Yin +2VLM EvaluationAgent Benchmarks

  15. WeVisOne-VL: Unified Visual Perception from Objects to Pixels

    Oct 22, 2026Tianming Liang, Junyi Pan, Yuxi Li +5Image MattingFine-Grained Visual Perception

  16. A Visual Grounding Benchmark for Retinal OCT with Multimodal Large Language Models

    Oct 22, 2026Ronald Fecso, José Morano, Botond Fazekas +6Medical VLMsMedical Image Grounding

  17. Auditing Where Concept Bottleneck Accuracy Comes From on CUB

    Oct 20, 2026Sascha Saralajew, Eleonora Poeta, Eliana Pastor +1Concept Bottleneck ModelsVisual Grounding

  18. From Seeing to Reporting: A Theory of Reliable Visual Set Generation in Vision-Language Models

    Oct 18, 2026Junzhe Shi, Yuan Gan, Shida JiangCounting in VLMsVision-Language Models

  19. Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding

    Oct 14, 2026Shun Inadumi, Lee Sangmyeong, Koichiro YoshinoVisual GroundingVision-Language Grounding

  20. Thinking with Images without Coordinates

    Oct 9, 2026Meng Cao, Haoze Zhao, Yi Wang +2VLM ReasoningVisually Grounded Reasoning

  21. Jag: Direct Box Prediction for Efficient Visual Grounding

    Oct 9, 2026Xiuyuan Zhu, Ke Lu, Hao Wu +3Visual GroundingVision-Language Grounding

  22. From What to Which: Decoding Modifier Grounding in Frozen MLLMs

    Oct 8, 2026Barbara Toniella Corradini, Caterina Gallegati, Ludovica Genovese +1Multimodal Large Language ModelsVision-Language Grounding

  23. Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery

    Oct 8, 2026Jingbo Yue, Bruce Coburn, Jinge Ma +2Visual Grounding

  24. Mixture of Layers: Dynamic Layer Routing for Visual Reasoning

    Oct 7, 2026Jeonghwan Kim, Sofia Stoica, Jiwan Chung +5VLM ReasoningLarge Vision-Language Models