@article{hongbo2026,
title = {VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?},
author = {Zhao, Hongbo and Wang, Meng and Zhu, Fei and Liu, Wenzhuo and Ni, Bolin and Zeng, Fanhu and Meng, Gaofeng and Zhang, Zhaoxiang and Liu, Cheng-Lin},
journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
year = {2026},
month = {Jan},
doi = {10.18653/2026.emnlp-main.145},
url = {https://doi.org/10.18653/2026.emnlp-main.145},
}
Zhao, Hongbo et al. (2026). VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/2026.emnlp-main.145
Zhao, Hongbo, et al.. "VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, https://doi.org/10.18653/2026.emnlp-main.145.
Zhao, Hongbo, et al.. "VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026). https://doi.org/10.18653/2026.emnlp-main.145
Zhao, Hongbo et al., 2026. VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing. Available at: <https://doi.org/10.18653/2026.emnlp-main.145>.
TY - JOUR
TI - VTCBench: Can Vision-Language Models Understand Long Contexts with Vision-Text Compression?
AU - Zhao, Hongbo
AU - Wang, Meng
AU - Zhu, Fei
AU - Liu, Wenzhuo
AU - Ni, Bolin
AU - Zeng, Fanhu
AU - Meng, Gaofeng
AU - Zhang, Zhaoxiang
AU - Liu, Cheng-Lin
PY - 2026
JO - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
DO - 10.18653/2026.emnlp-main.145
UR - https://doi.org/10.18653/2026.emnlp-main.145
ER -