The DOI matches its Crossref record.
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
Open accessAbstract
Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
MLLMs, especially visual MLLMs, exhibit unprecedented visual understanding capabilities.
“MLLMs, especially visual MLLMs, exhibit unprecedented visual understanding capabilities [34, 40, 78, 86, 91, 102, 103]”
From Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces (2025) · cites this paper as [102]
The Introduction says multimodal models can understand vision-language information, and the Abstract reports that LVLMs perform well on visual-language reasoning tasks. These passages support visual understanding capabilities, but do not establish the claim that those capabilities are unprecedented. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 28
- Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966. · arXiv
- Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoor- thi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023a. Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478. · arXiv
- Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023b. Shikra: Unleashing multimodal llm's referential dialogue magic. arXiv preprint arXiv:2306.15195. · arXiv
- Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Jun- yang Lin, Chang Zhou, and Baobao Chang. 2024a. An image is worth 1/2 tokens after layer 2: Plug-and- play inference acceleration for large vision-language models. 18th European Conference on Computer Vision ECCV 2024.
- Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024b. Internvl: Scal- ing up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24185-24198.
- Xiangxiang Chu, Limeng Qiao, Xinyang Lin, Shuang Xu, Yang Yang, Yiming Hu, Fei Wei, Xinyu Zhang, Bo Zhang, Xiaolin Wei, et al. 2023. Mo- bilevlm: A fast, reproducible and strong vision lan- guage assistant for mobile devices. arXiv preprint arXiv:2312.16886. · arXiv
- Kevin Clark, Urvashi Khandelwal, Omer Levy, and Christopher D Manning. 2019. What does bert look at? an analysis of bert's attention. arXiv preprint arXiv:1906.04341. · arXiv
- Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. 2021. Knowledge neu- rons in pretrained transformers. arXiv preprint arXiv:2104.08696. · arXiv
- Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision- language models with instruction tuning. Advances in Neural Information Processing Systems, 36.
- Jiaming Han, Renrui Zhang, Wenqi Shao, Peng Gao, Peng Xu, Han Xiao, Kaipeng Zhang, Chris Liu, Song Wen, Ziyu Guo, et al. 2023. Imagebind-llm: Multi-modality instruction tuning. arXiv preprint arXiv:2309.03905. · arXiv
- John Hewitt and Christopher D Manning. 2019. A struc- tural probe for finding syntax in word representations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4129-4138.
- Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2024. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 13418- 13427.
- Yanwei Li, Yuechen Zhang, Chengyao Wang, Zhisheng Zhong, Yixin Chen, Ruihang Chu, Shaoteng Liu, and Jiaya Jia. 2024. Mini-gemini: Mining the potential of multi-modality vision language models. arXiv preprint arXiv:2403.18814. · arXiv
- Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Eval- uating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355. · arXiv
- Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, 36.
- Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai- Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, 35:2507-2521.
- Daniel Omeiza, Skyler Speakman, Celia Cintas, and Komminist Weldermariam. 2019. Smooth grad- cam++: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv preprint arXiv:1908.01224. · arXiv
- Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object hallucination in image captioning. arXiv preprint arXiv:1809.02156. · arXiv
- Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, pages 8317-8326.
- Eric Todd, Millicent L Li, Arnab Sen Sharma, Aaron Mueller, Byron C Wallace, and David Bau. 2023. Function vectors in large language models. arXiv preprint arXiv:2310.15213. · arXiv
- Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023a. Label words are anchors: An information flow perspective for understanding in-context learning. arXiv preprint arXiv:2305.14160. · arXiv
- Jinfeng Wei and Xiaofeng Zhang. 2024. Dopra: Decod- ing over-accumulation penalization and re-allocation in specific weighting layer. Proceedings of the 32nd ACM International Conference on Multimedia.
- Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat- Seng Chua. 2023. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519. · arXiv
- Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Yuhao Dan, Chenlin Zhao, Guohai Xu, Chenliang Li, Junfeng Tian, et al. 2023. mplug- docowl: Modularized multimodal large language model for document understanding. arXiv preprint arXiv:2307.02499. · arXiv
- Hang Zhang, Xin Li, and Lidong Bing. 2023. Video- llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858. · arXiv
- Yuechen Zhang, Shengju Qian, Bohao Peng, Shu Liu, and Jiaya Jia. 2024. Prompt highlighter: Interac- tive control for multi-modal llms. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13215-13224.
- 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. · arXiv
- Yichen Zhu, Minjie Zhu, Ning Liu, Zhicai Ou, Xiaofeng Mou, and Jian Tang. 2024. Llava-ϕ: Efficient multi- modal assistant with small language model. arXiv preprint arXiv:2401.02330. · arXiv
Cited by
Sorted by citations
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
Yang, J., Yang, S., Gupta, A. W., Han, R., Fei-Fei, L., & Xie, S. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.00994 · Cited by 120
“…82] and the feature extraction abilities of modern vision encoders [30, 65, 69], MLLMs, especially visual MLLMs, exhibit unprecedented visual understanding capabilities [34, 40, 78, 86, 91, 102, 103], a promising direction toward developing world models [50] and embodied agents [17, 21, 37, 59].”
Metadata
- Authors
- Zhang, X., Quan, Y., Shen, C., Yuan, X., Yan, S., Xie, L., Wang, W., Gu, C., Tang, H., & Ye, J.
- Affiliations
- Beijing Jiaotong University (CN)
- Alibaba Group (China) (CN)
- Shanghai Jiao Tong University (CN)
- Peking University (CN)
- Venue
- Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- Published
- 2025
- Pages
- 2289-2299
- OpenAlex
- W4411119489
- Cited by
- 26
- References
- 0
- Citations by year
- 2026: 13 · 2025: 12
- FWCI
- 17.56
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- large vision-language models, information flow, reasoning tasks, visual grounding, redundancy, relevance, vision-language grounding
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
