CVPR 2026 Open Access Repository

Multimodal Algorithmic Reasoning Workshop

Focus Ambiguity in Visual Questions: A Disambiguation Problem, Not Instance Segmentation: Yu-Yun Tseng,

Danna Gurari; [pdf] [supp]
[bibtex]
@InProceedings{Tseng_2026_CVPR, author = {Tseng, Yu-Yun and Gurari, Danna}, title = {Focus Ambiguity in Visual Questions: A Disambiguation Problem, Not Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11507-11515} }
SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language Models: Zhiyuan Hu,

Zheng Sun,

Yi Wei,

Long Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2026_CVPR, author = {Hu, Zhiyuan and Sun, Zheng and Wei, Yi and Yu, Long}, title = {SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11543-11552} }
When Negation Is a Geometry Problem in Vision Language Models: Fawaz Sammani,

Tzoulio Chamiti,

Paul Gavrikov,

Nikos Deligiannis; [pdf] [arXiv]
[bibtex]
@InProceedings{Sammani_2026_CVPR, author = {Sammani, Fawaz and Chamiti, Tzoulio and Gavrikov, Paul and Deligiannis, Nikos}, title = {When Negation Is a Geometry Problem in Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11553-11562} }
POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency: Ashim Dahal,

Ankit Ghimire,

Saydul Akbar Murad,

Nick Rahimi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dahal_2026_CVPR, author = {Dahal, Ashim and Ghimire, Ankit and Murad, Saydul Akbar and Rahimi, Nick}, title = {POVQA: Preference-Optimized Video Question Answering with Rationales for Data Efficiency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11533-11542} }
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs: Rosie Zhao,

Anshul Shah,

Xiaoyu Zhu,

Xinke Deng,

Zhongyu Jiang,

Yang Yang,

Joerg Liebelt,

Arnab Mondal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2026_CVPR, author = {Zhao, Rosie and Shah, Anshul and Zhu, Xiaoyu and Deng, Xinke and Jiang, Zhongyu and Yang, Yang and Liebelt, Joerg and Mondal, Arnab}, title = {On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11523-11532} }
HoliGround: Holistic Assessment for Grounded Chain-of-Thought: Tom Hodemon,

Mohamed Chaouch,

Aboubacar Tuo,

Angelique Loesch; [pdf]
[bibtex]
@InProceedings{Hodemon_2026_CVPR, author = {Hodemon, Tom and Chaouch, Mohamed and Tuo, Aboubacar and Loesch, Angelique}, title = {HoliGround: Holistic Assessment for Grounded Chain-of-Thought}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {11516-11522} }