Autonomous Understanding Through Open-world Perception and Integrated Language models for On-road Tasks
Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chang_2026_CVPR, author = {Chang, Chun-Peng and Wang, Chen-Yu and Caesar, Holger and Pagani, Alain}, title = {Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {644-654} }
ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Picek_2026_CVPR, author = {Picek, Lukas and \v{C}erm\'ak, Michal and Hanzl, Marek and \v{C}erm\'ak, Vojt\v{e}ch}, title = {ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {685-694} }
Drive Like Humans, Plan Like Machines: An Explicit Sense and Safety Aware Autonomous Driving Framework-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2026_CVPR, author = {Wang, Xia and An, Ziyan and Zhang, Yuhang and Ma, Meiyi and Work, Daniel B. and Sprinkle, Jonathan}, title = {Drive Like Humans, Plan Like Machines: An Explicit Sense and Safety Aware Autonomous Driving Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {695-706} }
Spatial-aware Vision Language Model for Autonomous Driving-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2026_CVPR, author = {Wei, Weijie and Luo, Zhipeng and Ling, Feng and Liong, Venice Erin}, title = {Spatial-aware Vision Language Model for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {707-717} }
Automingo: Seeing the Unseen - Vision-Language Edge Case Dataset for Detection and Analysis of Autonomous Driving-
[pdf]
[supp]
[bibtex]@InProceedings{Divis_2026_CVPR, author = {Divis, Vaclav and \'Alvarez, \'I\~nigo Barcelo and Nubla, Alejandro Farinas and Sanchez, Enrique and Briales, Antonio Hernandez-Ros and Valach, Ond\v{r}ej and Gruber, Ivan and Hr\'uz, Marek}, title = {Automingo: Seeing the Unseen - Vision-Language Edge Case Dataset for Detection and Analysis of Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {665-674} }
TopoMaskV3: 3D Mask Head with Dense Offset and Height Predictions for Road Topology Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Kalfaoglu_2026_CVPR, author = {Kalfaoglu, Muhammet Esat and \"Ozt\"urk, Halil Ibrahim and Kilinc, Ozsel and Temizel, Alptekin}, title = {TopoMaskV3: 3D Mask Head with Dense Offset and Height Predictions for Road Topology Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {675-684} }
OmniSieve: Query-Guided Adaptive Token Allocation for Efficient Multi-View Vision-Language Reasoning-
[pdf]
[bibtex]@InProceedings{Chhimpa_2026_CVPR, author = {Chhimpa, Preetam and Ghosh, Indrajit}, title = {OmniSieve: Query-Guided Adaptive Token Allocation for Efficient Multi-View Vision-Language Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {655-664} }