Elamur Research⌕
☰
home / papers / 2026 / Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition

Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition

Paper · 2026 · Ye Wang, Qianglong Chen, Siyuan Wang et al.

Summary

Multimodal large language models (MLLMs) often lose track of visual evidence while reasoning. The authors identify three distinct grounding failures. Long-Context Grounding Error occurs when the image's influence fades over long outputs. Fine-Grained Grounding Error occurs when low resolution hides details. Regional Grounding Error occurs when diffuse attention misaligns text with image regions. Attention-map analysis supports this split. To address each failure, they define three tools: reuse re-inserts the original image, zoom_in raises resolution, and focus_area crops a bounding-box region. They build TWI-Tools-146K, a dataset of automatically generated multi-step trajectories with interleaved images and text that passes through a two-stage filter. Using only supervised fine-tuning, they train Simple-VGC, a model that decides adaptively which tools to combine. Each tool helps with its matching error type, and combining them gives further gains. The model performs on par with RL-based tool-use systems such as DeepEyes, which suggests that flexible tool composition can make perception-heavy multimodal reasoning more reliable.

Key points

  • Preliminary single-tool study: for each tool, 20K one-step samples were drawn from the COCO subset of LLaVA-CoT-100K and used to fine-tune Qwen2.5-VL. All three tools improved MME reasoning scores, and reuse gave the largest gain.
  • Evaluation covers COCO_VAL, HRBench-4K, HallusionBench, InfoVQA, MME and ScienceQA. Tool use varies by task: cropping is frequent on HRBench-4K, while InfoVQA questions are often answered from the global image or even without any tool. Inference uses about 1.7–2.3 steps on average.
  • In a controlled re-run, DeepEyes often produced malformed bounding boxes, which broke evaluation on MME and HallusionBench. The authors suggest this may come from reward hacking under format-focused RL rewards. Simple-VGC kept its tool calls stable.
  • Remaining failure modes include not using OCR text extracted in intermediate steps and leaning too heavily on visual cues at the expense of prior knowledge.
  • Limitations: training is SFT-only, and math data was deliberately excluded, so performance on mathematical tasks may be weaker.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of Southern CaliforniaLos Angeles · United States162 works · 35,836 citations🎓Fudan UniversityShanghai · China167 works · 20,987 citations🏢Alibaba GroupHangzhou · China168 works · 15,386 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,426 worksVision & language · 657 works

Cite

Cite as Ye Wang, Qianglong Chen, Siyuan Wang, Zejun Li, Shijie Guo, Zhirui Zhang and Zhongyu Wei. 2026. Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.223

@inproceedings{wang2026simple,
  title = {{Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition}},
  author = {Ye Wang, Qianglong Chen, Siyuan Wang, Zejun Li, Shijie Guo, Zhirui Zhang and Zhongyu Wei},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.223},
  url = {https://doi.org/10.18653/v1/2026.acl-long.223}
}

References

83 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, and 1 others. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems, 35:23716– 23736.
  2. Kazi Hasan Ibn Arif, Sajib Acharjee Dip, Khizar Hussain, Lang Zhang, and Chris Thomas. 2025. Paint: Paying attention to informed tokens to mitigate hallucination in large vision-language model. arXiv preprint arXiv:2501.12206. — [arXiv:2501.12206](https://arxiv.org/abs/2501.12206) find
  3. Anas Awadalla, Irena Gao, Josh Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Shiori Sagawa, and 1 others. 2023. Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390.
  4. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609.
  5. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025a. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  6. Tianyi Bai, Zengjie Hu, Fupeng Sun, Jiantao Qiu, Yizhen Jiang, Guangxin He, Bohan Zeng, Conghui He, Binhang Yuan, and Wentao Zhang. 2025b. Multi-step visual reasoning with visual tokens scaling and verification. arXiv preprint arXiv:2506.07235. — [arXiv:2506.07235](https://arxiv.org/abs/2506.07235) find
  7. Walid Bousselham, Felix Petersen, Vittorio Ferrari, and Hilde Kuehne. 2024. Grounding everything: Emerging localization properties in vision-language transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3828–3837. find
  8. Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing multimodal llm’s referential dialogue magic. arXiv preprint arXiv:2306.15195.
  9. Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, and 1 others. 2024a. Are we on the right way for evaluating large vision-language models? Advances in Neural Information Processing Systems, 37:27056–27087.
  10. Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollár, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325.
  11. Zhangquan Chen, Ruihui Zhao, Chuwei Luo, Mingze Sun, Xinlei Yu, Yangyang Kang, and Ruqi Huang. 2025. Sifthinker: Spatially-aware image focus for visual reasoning. arXiv preprint arXiv:2508.06259. — [arXiv:2508.06259](https://arxiv.org/abs/2508.06259) find
  12. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, and 1 others. 2024b. Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271.
  13. An-Chieh Cheng, Hongxu Yin, Yang Fu, Qiushan Guo, Ruihan Yang, Jan Kautz, Xiaolong Wang, and Sifei Liu. 2024. Spatialrgpt: Grounded spatial reasoning in vision-language models. Advances in Neural Information Processing Systems, 37:135062–135093. find
  14. Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V Le, Sergey Levine, and Yi Ma. 2025. Sft memorizes, rl generalizes: A comparative study of foundation model post-training. arXiv preprint arXiv:2501.17161.
  15. Jiwan Chung, Junhyeok Kim, Siyeol Kim, Jaeyoung Lee, Min Soo Kim, and Youngjae Yu. 2025. Don’t look only once: Towards multimodal interactive reasoning with selective visual revisitation. arXiv preprint arXiv:2505.18842. — [arXiv:2505.18842](https://arxiv.org/abs/2505.18842) find
  16. Wenliang Dai, Junnan Li, Dongxu Li, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2023. Instructblip: Towards general-purpose vision-language models with instruction tuning. Advances in neural information processing systems, 36:49250–49267.
  17. Chao Dong, Chen Change Loy, and Xiaoou Tang. 2016. Accelerating the super-resolution convolutional neural network. In European conference on computer vision, pages 391–407. Springer. find
  18. Parsa Esmaeilkhani and Longin Jan Latecki. 2025. Direct visual grounding by directing attention of visual tokens. arXiv preprint arXiv:2511.12738. — [arXiv:2511.12738](https://arxiv.org/abs/2511.12738) find
  19. Xiaoran Fan, Tao Ji, Changhao Jiang, Shuo Li, Senjie Jin, Sirui Song, Junke Wang, Boyang Hong, Lu Chen, Guodong Zheng, and 1 others. 2024. Mousi: Poly-visual-expert vision-language models. arXiv preprint arXiv:2401.17221. — [arXiv:2401.17221](https://arxiv.org/abs/2401.17221) find
  20. Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, and Rongrong Ji. 2024. Mme: A comprehensive evaluation benchmark for multimodal large language models. Preprint, arXiv:2306.13394.
  21. Chunjiang Ge, Sijie Cheng, Ziming Wang, Jiale Yuan, Yuan Gao, Jun Song, Shiji Song, Gao Huang, and Bo Zheng. 2024. Convllava: Hierarchical backbones as visual encoder for large multimodal models. arXiv preprint arXiv:2405.15738. — [arXiv:2405.15738](https://arxiv.org/abs/2405.15738) find
  22. Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, and 1 others. 2024. Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In Proceedings of…
  23. Hulingxiao He, Geng Li, Zijun Geng, Jinglin Xu, and Yuxin Peng. 2025. Analyzing and boosting the power of fine-grained visual recognition for multi-modal large language models. arXiv preprint arXiv:2501.15140. — [arXiv:2501.15140](https://arxiv.org/abs/2501.15140) find
  24. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025. Vision-r1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749. find
  25. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  26. Chaoya Jiang, Yongrui Heng, Wei Ye, Han Yang, Haiyang Xu, Ming Yan, Ji Zhang, Fei Huang, and Shikun Zhang. 2025. Vlm-r 3 : Region recognition, reasoning, and refinement for enhanced multimodal chain-of-thought. arXiv preprint arXiv:2505.16192. — [arXiv:2505.16192](https://arxiv.org/abs/2505.16192) find
  27. Mingi Jung, Saehyung Lee, Eunji Kim, and Sungroh Yoon. 2025. Visual attention never fades: Selective progressive attention recalibration for detailed image captioning in multimodal large language models. arXiv preprint arXiv:2502.01419. — [arXiv:2502.01419](https://arxiv.org/abs/2502.01419) find
  28. Seil Kang, Jinyeong Kim, Junhyeok Kim, and Seong Jae Hwang. 2025. Your large vision-language model only needs a few attention heads for visual grounding. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 9339–9350. find
  29. Sunil Kumar, Bowen Zhao, Leo Dirac, and Paulina Var-shavskaya. 2025. Reinforcing vlms to use tools for detailed visual reasoning under resource constraints. Preprint, arXiv:2506.14821. — [arXiv:2506.14821](https://arxiv.org/abs/2506.14821) find
  30. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and 1 others. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326.
  31. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning, pages 19730–19742. PMLR.
  32. Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. 2024b. Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models. arXiv preprint arXiv:2403.00231.
  33. Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023b. Evaluating object hallucination in large vision-language models. Preprint, arXiv:2305.10355.
  34. Zhang Li, Biao Yang, Qiang Liu, Zhiyin Ma, Shuo Zhang, Jingxu Yang, Yabo Sun, Yuliang Liu, and Xiang Bai. 2024c. Monkey: Image resolution and text label are important things for large multi-modal models. In proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2676… find
  35. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024a. Improved baselines with visual instruction tuning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 26296–26306.
  36. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, 36:34892– 34916.
  37. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, 36.
  38. Shi Liu, Kecheng Zheng, and Wei Chen. 2024c. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. In European Conference on Computer Vision, pages 125–140. Springer. find
  39. Yexin Liu, Zhengyang Liang, Yueze Wang, Xianfeng Wu, Feilong Tang, Muyang He, Jian Li, Zheng Liu, Harry Yang, Sernam Lim, and 1 others. 2025a. Unveiling the ignorance of mllms: Seeing clearly, answering incorrectly. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 9087… find
  40. Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025b. Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785. — [arXiv:2503.01785](https://arxiv.org/abs/2503.01785) find
  41. Shiyin Lu, Yang Li, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, and Han-Jia Ye. 2024. Ovis: Structural embedding alignment for multimodal large language model. arXiv preprint arXiv:2405.20797. — [arXiv:2405.20797](https://arxiv.org/abs/2405.20797) find
  42. Chuofan Ma, Yi Jiang, Jiannan Wu, Zehuan Yuan, and Xiaojuan Qi. 2024. Groma: Localized visual tokenization for grounding multimodal large language models. In European Conference on Computer Vision, pages 417–435. Springer. find
  43. Minesh Mathew, Viraj Bagal, Rubèn Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. 2022. Infographicvqa. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1697–1706. find
  44. Minesh Mathew, Dimosthenis Karatzas, and CV Jawahar. 2021. Docvqa: A dataset for vqa on document images. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 2200–2209.
  45. Vivek Myers, Catherine Ji, and Benjamin Eysenbach. 2025. Horizon generalization in reinforcement learning. arXiv preprint arXiv:2501.02709. — [arXiv:2501.02709](https://arxiv.org/abs/2501.02709) find
  46. Minheng Ni, Zhengyuan Yang, Linjie Li, Chung-Ching Lin, Kevin Lin, Wangmeng Zuo, and Lijuan Wang. 2025. Point-rft: Improving multimodal reasoning with visually grounded reinforcement finetuning. arXiv preprint arXiv:2505.19702. — [arXiv:2505.19702](https://arxiv.org/abs/2505.19702) find
  47. Shuyi Ouyang, Ziwei Niu, Hongyi Wang, Yen-Wei Chen, and Lanfen Lin. 2025. Region-aware anchoring mechanism for efficient referring visual grounding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 24192– 24202. find
  48. Tanik Saikh, Tirthankar Ghosal, Amish Mittal, Asif Ekbal, and Pushpak Bhattacharyya. 2022. Scienceqa: A novel resource for question answering on scholarly articles. International Journal on Digital Libraries, 23(3):289–301. find
  49. Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, and Hongsheng Li. 2024. Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models. CoRR. find
  50. Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, and Roy Ka-Wei Lee. 2024. Math-llava: Bootstrapping mathematical reasoning for multimodal large language models. arXiv preprint arXiv:2406.17294.
  51. Fatemeh Shiri, Xiao-Yu Guo, Mona Golestan Far, Xin Yu, Reza Haf, and Yuan-Fang Li. 2024. An empirical analysis on spatial reasoning capabilities of large multimodal models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21440–21455. find
  52. Alex Su, Haozhe Wang, Weiming Ren, Fangzhen Lin, and Wenhu Chen. 2025. Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning. arXiv preprint arXiv:2505.15966. — [arXiv:2505.15966](https://arxiv.org/abs/2505.15966) find
  53. Hai-Long Sun, Zhun Sun, Houwen Peng, and Han-Jia Ye. 2025a. Mitigating visual forgetting via take-along visual conditioning for multi-modal long cot reasoning. arXiv preprint arXiv:2503.13360.
  54. Yanpeng Sun, Shan Zhang, Wei Tang, Aotian Chen, Piotr Koniusz, Kai Zou, Yuan Xue, and Anton van den Hengel. 2025b. Math blind: Failures in diagram understanding undermine reasoning in mllms. Preprint, arXiv:2503.20745. — [arXiv:2503.20745](https://arxiv.org/abs/2503.20745) find
  55. Jayant Sravan Tamarapalli, Rynaa Grover, Nilay Pande, and Sahiti Yerramilli. 2025. Countqa: How well do mllms count in the wild? arXiv preprint arXiv:2508.06585. find
  56. Wei Tang, Yanpeng Sun, Qinying Gu, and Zechao Li. 2025. Visual position prompt for mllm based visual grounding. arXiv preprint arXiv:2503.15426. — [arXiv:2503.15426](https://arxiv.org/abs/2503.15426) find
  57. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, and 1 others. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599. — Kimi k1.5: Scaling Reinforcement Learning with LLMs
  58. Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024. Eyes wide shut? exploring the visual shortcomings of multimodal llms. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9568–9578.
  59. Muhammad Usama, Syeda Aishah Asim, Syed Bilal Ali, Syed Talal Wasim, and Umair Bin Mansoor. 2025. Analysing the robustness of vision-language-models to common corruptions. arXiv preprint arXiv:2504.13690. — [arXiv:2504.13690](https://arxiv.org/abs/2504.13690) find
  60. Hongru Wang, Cheng Qian, Manling Li, Jiahao Qiu, Boyang Xue, Mengdi Wang, Heng Ji, and Kam-Fai Wong. 2025a. Toward a theory of agents as tool-use decision-makers. arXiv preprint arXiv:2506.00886. — [arXiv:2506.00886](https://arxiv.org/abs/2506.00886) find
  61. Qiuchen Wang, Ruixue Ding, Yu Zeng, Zehui Chen, Lin Chen, Shihang Wang, Pengjun Xie, Fei Huang, and Feng Zhao. 2025b. Vrag-rl: Empower vision-perception-based rag for visually rich information understanding via iterative reasoning with reinforcement learning. arXiv preprint arXiv:2505.22019.
  62. Wenbin Wang, Liang Ding, Minyan Zeng, Xiabin Zhou, Li Shen, Yong Luo, Wei Yu, and Dacheng Tao. 2025c. Divide, conquer and combine: a training-free framework for high-resolution image perception in multimodal large language models. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Inte… find
  63. Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, and 1 others. 2024. Charxiv: Charting gaps in realistic chart understanding in multimodal llms. Advances in Neural Information Processing Systems, 37:113569–113697. find
  64. Yuqian Yuan, Wentong Li, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, and Jianke Zhu. 2024. Osprey: Pixel understanding with visual instruction tuning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 28202–28211. find
  65. Penghao Wu and Saining Xie. 2024. V?: Guided visual search as a core mechanism in multimodal llms. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13084– 13094. find
  66. Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong, and Ruihua Song. 2024a. What matters in training a gpt4-style language model with multimodal inputs? In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computatio… find
  67. Linhui Xiao, Xiaoshan Yang, Xiangyuan Lan, Yaowei Wang, and Changsheng Xu. 2024a. Towards visual grounding: A survey. arXiv preprint arXiv:2412.20206. — [arXiv:2412.20206](https://arxiv.org/abs/2412.20206) find
  68. Yijia Xiao, Edward Sun, Tianyu Liu, and Wei Wang. 2024b. Logicvista: Multimodal llm logical reasoning benchmark in visual contexts. arXiv preprint arXiv:2407.04973. — [arXiv:2407.04973](https://arxiv.org/abs/2407.04973) find
  69. Guowei Xu, Peng Jin, Hao Li, Yibing Song, Lichao Sun, and Li Yuan. 2024. Llava-cot: Let vision language models reason step-by-step. arXiv preprint arXiv:2411.10440. find
  70. Weiye Xu, Jiahao Wang, Weiyun Wang, Zhe Chen, Wengang Zhou, Aijun Yang, Lewei Lu, Houqiang Li, Xiaohua Wang, Xizhou Zhu, and 1 others. 2025. Visulogic: A benchmark for evaluating visual reasoning in multi-modal large language models. arXiv preprint arXiv:2504.15279. — [arXiv:2504.15279](https://arxiv.org/abs/2504.15279) find
  71. Yunan Zeng, Yan Huang, Jinjin Zhang, Zequn Jie, Zhenhua Chai, and Liang Wang. 2024b. Investigating compositional challenges in vision-language models for visual grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14141–14151. find
  72. Guanghao Zhang, Tao Zhong, Yan Xia, Zhelun Yu, Haoyuan Li, Wanggui He, Fangxun Shu, Mushui Liu, Dong She, Yi Wang, and 1 others. 2025a. Cmm-cot: Enhancing complex multi-image comprehension via multi-modal chain-of-thought and memory augmentation. arXiv preprint arXiv:2503.05255. — [arXiv:2503.05255](https://arxiv.org/abs/2503.05255) find
  73. Jingyi Zhang, Jiaxing Huang, Huanjin Yao, Shunyu Liu, Xikun Zhang, Shijian Lu, and Dacheng Tao. 2025b. R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization. arXiv preprint arXiv:2503.12937. — [arXiv:2503.12937](https://arxiv.org/abs/2503.12937) find
  74. Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, and 1 others. 2023a. Ureader: Universal ocr-free visually-situated language understanding with multimodal large language model. arXiv preprint arXiv:2310.05126.
  75. Xintong Zhang, Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaowen Zhang, Yang Liu, Tao Yuan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, and 1 others. 2025c. Chain-of-focus: Adaptive visual search and zooming for multimodal reasoning via rl. arXiv preprint arXiv:2505.15436. — [arXiv:2505.15436](https://arxiv.org/abs/2505.15436) find
  76. Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, and 1 others. 2023b. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178.
  77. Ziwei Zheng, Michael Yang, Jack Hong, Chenxiao Zhao, Guohai Xu, Le Yang, Chao Shen, and Xing Yu. 2025. Deepeyes: Incentivizing" thinking with images" via reinforcement learning. arXiv preprint arXiv:2505.14362. — [arXiv:2505.14362](https://arxiv.org/abs/2505.14362) find
  78. Runpeng Yu, Weihao Yu, and Xinchao Wang. 2024a. Attention prompting on image for large vision-language models. In European Conference on Computer Vision, pages 251–268. Springer. find
  79. Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2024b. Mm-vet: Evaluating large multimodal models for integrated capabilities. Preprint, arXiv:2308.02490.
  80. Xuan Yu, Dayan Guan, and Yanfeng Gu. 2025. Zoom-refine: Boosting high-resolution multimodal understanding via localized zoom and self-refinement. arXiv preprint arXiv:2506.01663. — [arXiv:2506.01663](https://arxiv.org/abs/2506.01663) find
  81. Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh. 2025. R1-zero’s" aha moment" in visual reasoning on a 2b non-sft model. arXiv preprint arXiv:2503.05132. — [arXiv:2503.05132](https://arxiv.org/abs/2503.05132) find
  82. Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592.
  83. Muzhi Zhu, Hao Zhong, Canyu Zhao, Zongze Du, Zheng Huang, Mingyu Liu, Hao Chen, Cheng Zou, Jingdong Chen, Ming Yang, and 1 others. 2025. Active-o3: Empowering multimodal large language models with active perception via grpo. arXiv preprint arXiv:2505.21457. — [arXiv:2505.21457](https://arxiv.org/abs/2505.21457) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-simple-vgc-enhancing-visual-grounding/