PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments

Zhou, Weijie, Xiong, Xuantang, Peng, Yi, Tao, Manli, Zhao, Chaoyang, Dong, Honghui, Tang, Ming, Wang, Jinqiao

Open source

DOI
10.48550/arxiv.2510.21111
Published
2025
Container
Not recorded
Publisher
arXiv
Open access
yes

Credibility signals

limited evidence Score 43/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.48550/arxiv.2510.21111,
  title = {PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments},
  author = {Zhou, Weijie and Xiong, Xuantang and Peng, Yi and Tao, Manli and Zhao, Chaoyang and Dong, Honghui and Tang, Ming and Wang, Jinqiao},
  year = {2025},
  doi = {10.48550/arxiv.2510.21111},
  url = {https://doi.org/10.48550/arxiv.2510.21111}
}

RIS

TY  - JOUR
TI  - PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
AU  - Zhou, Weijie
AU  - Xiong, Xuantang
AU  - Peng, Yi
AU  - Tao, Manli
AU  - Zhao, Chaoyang
AU  - Dong, Honghui
AU  - Tang, Ming
AU  - Wang, Jinqiao
PY  - 2025
DO  - 10.48550/arxiv.2510.21111
UR  - https://doi.org/10.48550/arxiv.2510.21111
ER  - 

APA

Weijie, Z., Xuantang, X., Yi, P., Manli, T., Chaoyang, Z., Honghui, D., Ming, T., & Jinqiao, W. (2025). PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments. https://doi.org/10.48550/arxiv.2510.21111

Source records