Large Language and Vision Models for Autonomous Driving
VLA4CoDrive: Vision-Language-Action Dataset for Cooperative Autonomous Driving-
[pdf]
[bibtex]@InProceedings{Boroujeni_2026_WACV, author = {Boroujeni, Sayed Pedram Haeri and Razi, Abolfazl}, title = {VLA4CoDrive: Vision-Language-Action Dataset for Cooperative Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1789-1799} }
Lightweight Multi-Scale Fusion for Real-Time Autonomous Driving Segmentation-
[pdf]
[bibtex]@InProceedings{Nadeem_2026_WACV, author = {Nadeem, Muhammad and Lee, Hyeyoung}, title = {Lightweight Multi-Scale Fusion for Real-Time Autonomous Driving Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1721-1728} }
Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cai_2026_WACV, author = {Cai, Yuliang and Ye, Dongqiangzi and Chen, Zitian and Wu, Chongruo}, title = {Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1739-1746} }
FROST-Drive: Scalable and Efficient End-to-End Driving with a Frozen Vision Encoder-
[pdf]
[arXiv]
[bibtex]@InProceedings{Dong_2026_WACV, author = {Dong, Zeyu and Zhu, Yimin and Wu, Yu and Sun, Yu}, title = {FROST-Drive: Scalable and Efficient End-to-End Driving with a Frozen Vision Encoder}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1729-1738} }
2COOOL: An Evaluation Benchmark for Generating Incident Reports on Out-of-Distribution Hazards in Autonomous Driving-
[pdf]
[bibtex]@InProceedings{AlShami_2026_WACV, author = {AlShami, Ali K. and Rabinowitz, Ryan and Boult, Terrance E. and Kalita, Jugal}, title = {2COOOL: An Evaluation Benchmark for Generating Incident Reports on Out-of-Distribution Hazards in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1800-1809} }
Role of Language-Guidance in Knowledge Distillation for Semantic Segmentation Under Limited Field-Of-View Autonomous Driving-
[pdf]
[supp]
[bibtex]@InProceedings{Shin_2026_WACV, author = {Shin, Yeon Woo and Park, Keun Hee and Turaga, Pavan and Jeon, Eun Som}, title = {Role of Language-Guidance in Knowledge Distillation for Semantic Segmentation Under Limited Field-Of-View Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1761-1771} }
Benchmarking Vision-Language Models for Traffic Scene Understanding in Inclement Winter Weather: The AWDB Benchmark-
[pdf]
[bibtex]@InProceedings{Awad_2026_WACV, author = {Awad, Ali and Kosireddy, Tagore and Mokkapati, Krishna and Bajracharya, Nibendra and Saleem, Ashraf and Nguyen, Vinh and Lucas, Evan}, title = {Benchmarking Vision-Language Models for Traffic Scene Understanding in Inclement Winter Weather: The AWDB Benchmark}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1747-1760} }
GATEPose: A Graph Attention Transformer Enhanced with Pose and Orientation Angles for Pedestrian Crossing Intention Prediction-
[pdf]
[bibtex]@InProceedings{AlShami_2026_WACV, author = {AlShami, Ali K. and Boult, Terrance E. and Kalita, Jugal}, title = {GATEPose: A Graph Attention Transformer Enhanced with Pose and Orientation Angles for Pedestrian Crossing Intention Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1810-1819} }
Trust-Guided Multimodal LLM Integration with Reinforcement Learning for Autonomous Driving-
[pdf]
[supp]
[bibtex]@InProceedings{Chennaka_2026_WACV, author = {Chennaka, Sairam and Nidamanuri, Jaswanth}, title = {Trust-Guided Multimodal LLM Integration with Reinforcement Learning for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1780-1788} }
Less Is More: Agentic Prompt Design for Safe VLM Action Selection-
[pdf]
[supp]
[bibtex]@InProceedings{Yahyapour_2026_WACV, author = {Yahyapour, Elahe and Ai, Chengbo}, title = {Less Is More: Agentic Prompt Design for Safe VLM Action Selection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {March}, year = {2026}, pages = {1772-1779} }