{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:20:42Z","timestamp":1783045242748,"version":"3.54.6"},"reference-count":227,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52472437"],"award-info":[{"award-number":["52472437"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.inffus.2026.104457","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:53:52Z","timestamp":1778244832000},"page":"104457","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A comprehensive survey of pretrained models for autonomous driving: Methods and applications"],"prefix":"10.1016","volume":"135","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4909-3242","authenticated-orcid":false,"given":"Renze","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0170-8700","authenticated-orcid":false,"given":"Zhishuai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8256-9208","authenticated-orcid":false,"given":"Linzhen","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3467-8000","authenticated-orcid":false,"given":"Yinghan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7145-4483","authenticated-orcid":false,"given":"Hongchen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.inffus.2026.104457_bib0001","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/TIV.2023.3318070","article-title":"Recent advancements in end-to-end autonomous driving using deep learning: a survey","volume":"9","author":"Chib","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"10","key":"10.1016\/j.inffus.2026.104457_bib0002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3729420","article-title":"A survey of autonomous driving from a deep learning perspective","volume":"57","author":"Zhao","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.inffus.2026.104457_bib0003","first-page":"9573","article-title":"The pitfalls of simplicity bias in neural networks","volume":"33","author":"Shah","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0004","first-page":"9995","article-title":"What shapes feature representations? exploring datasets, architectures, and training","volume":"33","author":"Hermann","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"10.1016\/j.inffus.2026.104457_bib0005","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104457_bib0006","article-title":"Causal confusion in imitation learning","volume":"32","author":"De Haan","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14864","article-title":"Is ego status all you need for open-loop end-to-end autonomous driving?","author":"Li","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0008","unstructured":"K.L. Hermann, H. Mobahi, T. Fel, M.C. Mozer, On the foundations of shortcut learning, (2023). https:\/\/arxiv.org\/pdf\/2310.16228."},{"key":"10.1016\/j.inffus.2026.104457_bib0009","series-title":"Conference on Robot Learning","first-page":"3239","article-title":"Shortcut learning in generalist robot policies: the role of dataset diversity and fragmentation","author":"Xing","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0010","doi-asserted-by":"crossref","first-page":"19645","DOI":"10.52202\/068431-1428","article-title":"Effective adaptation in multi-task co-training for unified autonomous driving","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0011","first-page":"1","article-title":"A comprehensive survey on pretrained foundation models: a history from bert to chatgpt","author":"Zhou","year":"2024","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.inffus.2026.104457_bib0012","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","article-title":"Pre-trained models: past, present and future","volume":"2","author":"Han","year":"2021","journal-title":"AI Open"},{"key":"10.1016\/j.inffus.2026.104457_bib0013","unstructured":"D. Hernandez, J. Kaplan, T. Henighan, S. McCandlish, Scaling laws for transfer, (2021). https:\/\/arxiv.org\/pdf\/2102.01293."},{"key":"10.1016\/j.inffus.2026.104457_bib0014","unstructured":"T.-R. Chiang, On a benefit of mask language modeling: Robustness to simplicity bias, (2021). https:\/\/arxiv.org\/pdf\/2110.05301."},{"key":"10.1016\/j.inffus.2026.104457_bib0015","doi-asserted-by":"crossref","first-page":"38516","DOI":"10.52202\/068431-2791","article-title":"On feature learning in the presence of spurious correlations","volume":"35","author":"Izmailov","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0016","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"5131","article-title":"On the inductive bias of masked language modeling: from statistical to syntactic dependencies","author":"Zhang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0017","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1162\/tacl_a_00335","article-title":"An empirical study on robustness to spurious correlations using pre-trained language models","volume":"8","author":"Tu","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.inffus.2026.104457_bib0018","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"948","article-title":"Lip-loc: Lidar image pretraining for cross-modal localization","author":"Shubodh","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0019","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5217","article-title":"Temporal consistent 3D liDAR representation learning for semantic perception in autonomous driving","author":"Nunes","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0020","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"910","article-title":"Drive like a human: rethinking autonomous driving with large language models","author":"Fu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0021","unstructured":"Y. Huang, Y. Chen, Z. Li, Applications of large scale foundation models for autonomous driving, (2023). https:\/\/arxiv.org\/pdf\/2311.12144."},{"key":"10.1016\/j.inffus.2026.104457_bib0022","unstructured":"Z. Yang, X. Jia, H. Li, J. Yan, Llm4drive: A survey of large language models for autonomous driving, (2023) arXiv\u20132311. https:\/\/arxiv.org\/pdf\/2311.01043."},{"key":"10.1016\/j.inffus.2026.104457_bib0023","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"958","article-title":"A survey on multimodal large language models for autonomous driving","author":"Cui","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0024","first-page":"1","article-title":"Vision language models in autonomous driving: a survey and outlook","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0025","doi-asserted-by":"crossref","unstructured":"S. Fourati, W. Jaafar, N. Baccar, S. Alfattani, XLM for Autonomous Driving Systems: A Comprehensive Review, (2024). https:\/\/arxiv.org\/pdf\/2409.10484.","DOI":"10.2139\/ssrn.5517080"},{"key":"10.1016\/j.inffus.2026.104457_bib0026","unstructured":"X. Yan, H. Zhang, Y. Cai, J. Guo, W. Qiu, B. Gao, K. Zhou, Y. Zhao, H. Jin, J. Gao, et al., Forging vision foundation models for autonomous driving: Challenges, methodologies, and opportunities, (2024). https:\/\/arxiv.org\/pdf\/2401.08045."},{"key":"10.1016\/j.inffus.2026.104457_bib0027","doi-asserted-by":"crossref","unstructured":"Y. Li, K. Katsumata, E. Javanmardi, M. Tsukada, Large Language Models for Human-like Autonomous Driving: A Survey, (2024). https:\/\/arxiv.org\/pdf\/2407.19280.","DOI":"10.1109\/ITSC58415.2024.10919629"},{"key":"10.1016\/j.inffus.2026.104457_bib0028","doi-asserted-by":"crossref","unstructured":"Y. Zhu, S. Wang, W. Zhong, N. Shen, Y. Li, S. Wang, Z. Li, C. Wu, Z. He, L. Li, A Survey on Large Language Model-empowered Autonomous Driving, (2024). https:\/\/arxiv.org\/pdf\/2409.14165?.","DOI":"10.1016\/j.eng.2025.07.038"},{"key":"10.1016\/j.inffus.2026.104457_bib0029","unstructured":"H. Gao, Y. Li, K. Long, M. Yang, Y. Shen, A Survey for Foundation Models in Autonomous Driving, (2024). https:\/\/arxiv.org\/pdf\/2402.01105."},{"key":"10.1016\/j.inffus.2026.104457_bib0030","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"11","key":"10.1016\/j.inffus.2026.104457_bib0031","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: the kitti dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.inffus.2026.104457_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11621","article-title":"Nuscenes: a multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0033","unstructured":"M. Huh, P. Agrawal, A.A. Efros, What makes ImageNet good for transfer learning?, (2016). https:\/\/arxiv.org\/pdf\/1608.08614."},{"key":"10.1016\/j.inffus.2026.104457_bib0034","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4918","article-title":"Rethinking imagenet pre-training","author":"He","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0035","series-title":"2022 26Th International Conference on Pattern Recognition (ICPR)","first-page":"3736","article-title":"Learning to drive using sparse imitation reinforcement learning","author":"Han","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0036","doi-asserted-by":"crossref","first-page":"37637","DOI":"10.1109\/ACCESS.2023.3266284","article-title":"Joint multiclass object detection and semantic segmentation for autonomous driving","volume":"11","author":"Abdigapporov","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104457_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5240","article-title":"Rangevit: towards vision transformers for 3d semantic segmentation in autonomous driving","author":"Ando","year":"2023"},{"issue":"3","key":"10.1016\/j.inffus.2026.104457_bib0038","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1109\/LRA.2023.3238137","article-title":"Opa-3d: occlusion-aware pixel-wise aggregation for monocular 3d object detection","volume":"8","author":"Su","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104457_bib0039","unstructured":"Y. Feng, J. Jiang, M. Tang, R. Jin, Y. Gao, Rethinking supervised pre-training for better downstream transferring, (2021). https:\/\/arxiv.org\/pdf\/2110.06014."},{"key":"10.1016\/j.inffus.2026.104457_bib0040","unstructured":"Y. Shi, I. Daunhawer, J.E. Vogt, P. Torr, A. Sanyal, How robust are pre-trained models to distribution shift?, in: ICML 2022: Workshop on Spurious Correlations, Invariance and Stability."},{"issue":"1","key":"10.1016\/j.inffus.2026.104457_bib0041","first-page":"857","article-title":"Self-supervised learning: generative or contrastive","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2026.104457_bib0042","unstructured":"A. Radford, K. Narasimhan, T. Salimans, I. Sutskever, et al., Improving language understanding by generative pre-training (2018)."},{"key":"10.1016\/j.inffus.2026.104457_bib0043","series-title":"International Conference on Machine Learning","first-page":"1691","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0044","doi-asserted-by":"crossref","first-page":"29667","DOI":"10.52202\/075280-1291","article-title":"Pointgpt: auto-regressively generative pre-training from point clouds","volume":"36","author":"Chen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0045","unstructured":"T. Feng, W. Wang, Y. Yang, A survey of world models for autonomous driving, (2025). https:\/\/arxiv.org\/pdf\/2501.11260?."},{"key":"10.1016\/j.inffus.2026.104457_bib0046","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14673","article-title":"Visual point cloud forecasting enables scalable autonomous driving","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0047","unstructured":"C. Min, D. Zhao, L. Xiao, Y. Nie, B. Dai, Uniworld: Autonomous driving pre-training via world models, (2023). https:\/\/arxiv.org\/pdf\/2308.07234."},{"key":"10.1016\/j.inffus.2026.104457_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15522","article-title":"Driveworld: 4d pre-trained scene understanding via world models for autonomous driving","author":"Min","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0049","series-title":"Proceedings of NAACL-HLT","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Kenton","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0050","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0051","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9653","article-title":"Simmim: a simple framework for masked image modeling","author":"Xie","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0052","doi-asserted-by":"crossref","first-page":"35632","DOI":"10.52202\/068431-2582","article-title":"MCMAE: Masked convolution meets masked autoencoders","volume":"35","author":"Gao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0053","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"552","article-title":"Peco: perceptual codebook for bert pre-training of vision transformers","volume":"37","author":"Dong","year":"2023"},{"issue":"1","key":"10.1016\/j.inffus.2026.104457_bib0054","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1007\/s11263-023-01852-4","article-title":"Context autoencoder for self-supervised representation learning","volume":"132","author":"Chen","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104457_bib0055","series-title":"International Conference on Learning Representations","article-title":"BEiT: BERT pre-Training of image transformers","author":"Bao","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0056","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19313","article-title":"Point-bert: pre-training 3d point cloud transformers with masked point modeling","author":"Yu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0057","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14668","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"Wei","year":"2022"},{"issue":"5","key":"10.1016\/j.inffus.2026.104457_bib0058","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1007\/s11263-023-01898-4","article-title":"Mimic before reconstruct: enhancing masked autoencoders with feature mimicking","volume":"132","author":"Gao","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104457_bib0059","series-title":"European Conference on Computer Vision","first-page":"604","article-title":"Masked autoencoders for point cloud self-supervised learning","author":"Pang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0060","series-title":"European Conference on Computer Vision","first-page":"657","article-title":"Masked discrimination for self-supervised learning on point clouds","author":"Liu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0061","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"350","article-title":"Masked autoencoder for self-supervised pre-training on lidar point clouds","author":"Hess","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0062","article-title":"Occupancy-mae: self-supervised pre-training large-scale lidar point clouds with masked occupancy autoencoders","author":"Min","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0063","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13445","article-title":"Mv-jar: masked voxel jigsaw and reconstruction for lidar-based self-supervised pre-training","author":"Xu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0064","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3531","article-title":"Bev-mae: bird\u2019s eye view masked autoencoders for point cloud pre-training in autonomous driving scenarios","volume":"38","author":"Lin","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0065","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3733","article-title":"Unsupervised feature learning via non-parametric instance discrimination","author":"Wu","year":"2018"},{"key":"10.1016\/j.inffus.2026.104457_bib0066","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0067","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0068","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0069","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15750","article-title":"Exploring simple siamese representation learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0070","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10252","article-title":"Self-supervised pretraining of 3d features on any point-cloud","author":"Zhang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0071","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16","first-page":"574","article-title":"Pointcontrast: unsupervised pre-training for 3d point cloud understanding","author":"Xie","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0072","unstructured":"R. Chen, Y. Mu, R. Xu, W. Shao, C. Jiang, H. Xu, Y. Qiao, Z. Li, P. Luo, CO3: Cooperative unsupervised 3D representation learning for autonomous driving, in: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.inffus.2026.104457_bib0073","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6535","article-title":"Spatio-temporal self-supervised representation learning for 3d point clouds","author":"Huang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0074","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1500","article-title":"Simipu: simple 2d image and 3d point cloud unsupervised pre-training for spatial-aware visual representations","volume":"36","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0075","unstructured":"L. Kong, X. Xu, Y. Liu, J. Cen, R. Chen, W. Zhang, L. Pan, K. Chen, Z. Liu, LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving, (2025). https:\/\/arxiv.org\/pdf\/2501.04005?."},{"key":"10.1016\/j.inffus.2026.104457_bib0076","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0077","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3024","article-title":"Dense contrastive learning for self-supervised visual pre-training","author":"Wang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0078","series-title":"2024 International Conference on 3D Vision (3DV)","first-page":"559","article-title":"Bevcontrast: self-supervision in bev space for automotive lidar point clouds","author":"Sautier","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0079","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1144","article-title":"Spatially consistent representation learning","author":"Roh","year":"2021"},{"issue":"12","key":"10.1016\/j.inffus.2026.104457_bib0080","doi-asserted-by":"crossref","first-page":"9052","DOI":"10.1109\/TPAMI.2024.3415112","article-title":"A survey on self-supervised learning: algorithms, applications, and future trends","volume":"46","author":"Gui","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104457_bib0081","unstructured":"Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, R. Soricut, Albert: A lite bert for self-supervised learning of language representations, (2019). https:\/\/arxiv.org\/pdf\/1909.11942."},{"key":"10.1016\/j.inffus.2026.104457_bib0082","series-title":"International Conference on Learning Representations","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"10.1016\/j.inffus.2026.104457_bib0083","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1422","article-title":"Unsupervised visual representation learning by context prediction","author":"Doersch","year":"2015"},{"key":"10.1016\/j.inffus.2026.104457_bib0084","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1910","article-title":"Iterative reorganization with weak spatial constraints: solving arbitrary jigsaw puzzles for unsupervised representation learning","author":"Wei","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0085","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"16089","article-title":"Ponder: point cloud pre-training via neural rendering","author":"Huang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0086","doi-asserted-by":"crossref","first-page":"46041","DOI":"10.52202\/075280-1996","article-title":"PRED: Pre-training via semantic rendering on lidar point clouds","volume":"36","author":"Yang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0087","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15238","article-title":"Unipad: a universal pre-training paradigm for autonomous driving","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0088","unstructured":"J. Xiong, G. Liu, L. Huang, C. Wu, T. Wu, Y. Mu, Y. Yao, H. Shen, Z. Wan, J. Huang, et al., Autoregressive models in vision: A survey, (2024). https:\/\/arxiv.org\/pdf\/2411.05902."},{"key":"10.1016\/j.inffus.2026.104457_bib0089","unstructured":"C. Azevedo, T. Gilles, S. Sabatini, D. Tsishkou, Exploiting map information for self-supervised learning in motion forecasting, arXiv preprint arXiv: 2210.04672(2022)."},{"key":"10.1016\/j.inffus.2026.104457_bib0090","unstructured":"L. Wen, D. Fu, X. Li, X. Cai, M.A. Tao, P. Cai, M. Dou, B. Shi, L. He, Y. Qiao, Dilu: a knowledge-Driven approach to autonomous driving with large language models, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.inffus.2026.104457_bib0091","unstructured":"X. Yue, L. Bai, M. Wei, J. Pang, X. Liu, L. Zhou, W. Ouyang, Understanding masked autoencoders from a local contrastive perspective, (2023). https:\/\/arxiv.org\/pdf\/2310.01994."},{"key":"10.1016\/j.inffus.2026.104457_bib0092","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"17839","article-title":"Geomim: towards better 3d knowledge transfer via masked image modeling for multi-view 3d understanding","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0093","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13570","article-title":"Geomae: masked geometric target prediction for self-supervised point cloud pre-training","author":"Tian","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0094","series-title":"European Conference on Computer Vision","first-page":"17","article-title":"Proposalcontrast: unsupervised pre-training for lidar-based 3d object detection","author":"Yin","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0095","unstructured":"Y.-J. Li, M. Gladkova, Y. Xia, R. Wang, D. Cremers, Vxp: Voxel-cross-pixel large-scale image-lidar place recognition, (2024). https:\/\/arxiv.org\/pdf\/2403.14594."},{"key":"10.1016\/j.inffus.2026.104457_bib0096","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"117","article-title":"Location-aware self-supervised transformers for semantic segmentation","author":"Caron","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0097","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3354552","article-title":"Self-supervised representation learning from temporal ordering of automated driving sequences","author":"Lang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104457_bib0098","unstructured":"X. Xu, Y. Li, T. Zhang, J. Yang, M. Johnson-Roberson, X. Huang, Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception, (2024). https:\/\/arxiv.org\/pdf\/2405.17942?."},{"key":"10.1016\/j.inffus.2026.104457_bib0099","series-title":"International Conference on Learning Representations","article-title":"Predicting inductive biases of pre-trained models","author":"Lovering","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103015","article-title":"Saliencyi2PLoc: saliency-guided image\u2013point cloud localization using contrastive learning","volume":"118","author":"Li","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104457_bib0101","unstructured":"H. Zheng, L. Shen, A. Tang, Y. Luo, H. Hu, B. Du, D. Tao, Learn from model beyond fine-tuning: A survey, (2023). https:\/\/arxiv.org\/pdf\/2310.08184."},{"key":"10.1016\/j.inffus.2026.104457_bib0102","doi-asserted-by":"crossref","unstructured":"Z. Xu, Y. Zhang, E. Xie, Z. Zhao, Y. Guo, K.K.Y. Wong, Z. Li, H. Zhao, Drivegpt4: Interpretable end-to-end autonomous driving via large language model, (2023). https:\/\/arxiv.org\/abs\/2310.01412.","DOI":"10.1109\/LRA.2024.3440097"},{"key":"10.1016\/j.inffus.2026.104457_bib0103","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0104","series-title":"European Conference on Computer Vision","first-page":"165","article-title":"Improving agent behaviors with rl fine-tuning for autonomous driving","author":"Peng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0105","unstructured":"Z. Han, C. Gao, J. Liu, J. Zhang, S.Q. Zhang, Parameter-efficient fine-tuning for large models: A comprehensive survey, (2024). https:\/\/arxiv.org\/pdf\/2403.14608."},{"key":"10.1016\/j.inffus.2026.104457_bib0106","series-title":"International Conference on Machine Learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0107","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15120","article-title":"Lmdrive: closed-loop end-to-end driving with large language models","author":"Shao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0108","series-title":"International Conference on Learning Representations","article-title":"LoRA: low-Rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0109","doi-asserted-by":"crossref","unstructured":"L. Chen, O. Sinavski, J. H\u00fcnermann, A. Karnsund, A.J. Willmott, D. Birch, D. Maund, J. Shotton, Driving with llms: Fusing object-level vector modality for explainable autonomous driving, (2023). https:\/\/arxiv.org\/pdf\/2310.01957.","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"10.1016\/j.inffus.2026.104457_bib0110","series-title":"2024 IEEE Intelligent Vehicles Symposium (IV)","first-page":"502","article-title":"Drive as veteran: fine-tuning of an onboard large language model for highway autonomous driving","author":"Wang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0111","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0112","unstructured":"J. Gu, Z. Han, S. Chen, A. Beirami, B. He, G. Zhang, R. Liao, Y. Qin, V. Tresp, P. Torr, A systematic survey of prompt engineering on vision-language foundation models, (2023). https:\/\/arxiv.org\/pdf\/2307.12980."},{"key":"10.1016\/j.inffus.2026.104457_bib0113","unstructured":"A. Efrat, O. Levy, The turking test: Can language models understand instructions?, (2020). https:\/\/arxiv.org\/pdf\/2010.11982."},{"key":"10.1016\/j.inffus.2026.104457_bib0114","unstructured":"Q. Dong, L. Li, D. Dai, C. Zheng, Z. Wu, B. Chang, X. Sun, J. Xu, Z. Sui, A survey on in-context learning, (2022). https:\/\/arxiv.org\/pdf\/2301.00234."},{"key":"10.1016\/j.inffus.2026.104457_bib0115","series-title":"Proceedings of the 61St Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"4644","article-title":"Unified demonstration retriever for in-Context learning","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0116","unstructured":"Y. Cui, H. Lin, S. Yang, Y. Wang, Y. Huang, H. Chen, Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects, (2025). https:\/\/arxiv.org\/pdf\/2505.20223?."},{"key":"10.1016\/j.inffus.2026.104457_bib0117","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","article-title":"The power of scale for parameter-Efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0118","series-title":"Proceedings of the 59Th Annual Meeting of the Association for Computational Linguistics and the 11Th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"4582","article-title":"Prefix-Tuning: optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0119","doi-asserted-by":"crossref","DOI":"10.1109\/TSMC.2023.3283021","article-title":"Milestones in autonomous driving and intelligent vehicles-part ii: perception and planning","author":"Chen","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern.: Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"31","article-title":"Fine-grained segmentation networks: self-supervised segmentation for improved long-term visual localization","author":"Larsson","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0121","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","article-title":"Accurate visual localization for automotive applications","author":"Brosh","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0122","series-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"4365","article-title":"Global visual localization in liDAR-maps through shared 2D-3D embedding space","author":"Cattaneo","year":"2020"},{"key":"10.1016\/j.inffus.2026.104457_bib0123","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3989","article-title":"Semantic pose verification for outdoor visual localization with self-supervised contrastive learning","author":"Orhan","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0124","series-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"11763","article-title":"Slice transformer and self-supervised learning for 6dof localization in 3d point cloud maps","author":"Ibrahim","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103351","article-title":"Contrastive learning-based place descriptor representation for cross-modality place recognition","author":"Meng","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104457_bib0126","unstructured":"C. Yang, L. Huang, E.J. Crowley, Contrastive object-level pre-training with spatial noise curriculum learning, (2021). https:\/\/arxiv.org\/pdf\/2111.13651."},{"key":"10.1016\/j.inffus.2026.104457_bib0127","first-page":"28864","article-title":"Unsupervised object-level representation learning from scene images","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0128","first-page":"22682","article-title":"Aligning pretraining for detection via object-level contrastive learning","volume":"34","author":"Wei","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0129","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"7546","article-title":"Multisiam: self-supervised multi-instance siamese representation learning for autonomous driving","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0130","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3293","article-title":"Exploring geometry-aware contrast and clustering harmonization for self-supervised 3d object detection","author":"Liang","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0131","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16061","article-title":"Point-level region contrast for object detection pre-training","author":"Bai","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0132","series-title":"2022 IEEE 25Th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"4341","article-title":"Self-supervised pretraining for point cloud object detection in autonomous driving","author":"Shi","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0133","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14627","article-title":"Univip: a unified framework for self-supervised visual pre-training","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0134","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4196","article-title":"Codo: contrastive learning with downstream background invariance for detection","author":"Zhao","year":"2022"},{"issue":"2","key":"10.1016\/j.inffus.2026.104457_bib0135","doi-asserted-by":"crossref","first-page":"2116","DOI":"10.1109\/LRA.2022.3142440","article-title":"Segcontrast: 3d point cloud feature representation learning through self-supervised segment discrimination","volume":"7","author":"Nunes","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104457_bib0136","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6662","article-title":"Vlpd: context-aware pedestrian detection via vision-language semantic self-supervision","author":"Liu","year":"2023"},{"issue":"9","key":"10.1016\/j.inffus.2026.104457_bib0137","doi-asserted-by":"crossref","first-page":"7975","DOI":"10.1109\/TCSVT.2024.3383914","article-title":"Integrating language-derived appearance elements with visual cues in pedestrian detection","volume":"34","author":"Park","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104457_bib0138","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4493","article-title":"Occfeat: self-supervised occupancy feature prediction for pretraining bev segmentation networks","author":"Sirko-Galouchenko","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0139","series-title":"European Conference on Computer Vision","first-page":"296","article-title":"Unim 2 ae: multi-modal masked autoencoders with unified 3d representation for 3d perception in autonomous driving","author":"Zou","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0140","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"2456","article-title":"Patchcontrast: self-supervised pre-training for 3d object detection","author":"Shrout","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0141","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"6670","article-title":"PSA-SSL: Pose and size-aware self-Supervised learning on LiDAR point clouds","author":"Nisar","year":"2025"},{"issue":"7","key":"10.1016\/j.inffus.2026.104457_bib0142","doi-asserted-by":"crossref","first-page":"3877","DOI":"10.1007\/s11263-025-02351-4","article-title":"LiDAR-guided geometric pretraining for vision-Centric 3D object detection","volume":"133","author":"Huang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.inffus.2026.104457_bib0143","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"3778","article-title":"PF3Det: a prompted foundation feature assisted visual LiDAR 3D detector","author":"Li","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0144","doi-asserted-by":"crossref","unstructured":"S.Z. Zhao, H. Xiang, C. Xu, X. Xia, B. Zhou, J. Ma, CooPre: Cooperative pretraining for v2x cooperative perception, (2024). https:\/\/arxiv.org\/pdf\/2408.11241.","DOI":"10.1109\/IROS60139.2025.11246787"},{"key":"10.1016\/j.inffus.2026.104457_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2566","article-title":"Learning correspondence from the cycle-consistency of time","author":"Wang","year":"2019"},{"key":"10.1016\/j.inffus.2026.104457_bib0146","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14561","article-title":"Dropmae: masked autoencoders with spatial-attention dropout for tracking tasks","author":"Wu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0147","series-title":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","first-page":"3122","article-title":"Multi-agent driving behavior prediction across different scenarios with self-supervised domain knowledge","author":"Ma","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0148","series-title":"European Conference on Computer Vision","first-page":"234","article-title":"Social-ssl: self-supervised cross-sequence representation learning based on transformers for multi-agent trajectory prediction","author":"Tsao","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0149","series-title":"European Conference on Computer Vision","first-page":"34","article-title":"Pretram: self-supervised pre-training via connecting trajectory and map","author":"Xu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0150","series-title":"The Twelfth International Conference on Learning Representations","article-title":"SEPT: Towards efficient scene representation learning for motion prediction","author":"Lan","year":"2023"},{"issue":"4","key":"10.1016\/j.inffus.2026.104457_bib0151","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1007\/s11280-022-01121-3","article-title":"PreCLN: pretrained-based contrastive learning network for vehicle trajectory prediction","volume":"26","author":"Yan","year":"2023","journal-title":"World Wide Web"},{"key":"10.1016\/j.inffus.2026.104457_bib0152","series-title":"2023 IEEE 26Th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"3717","article-title":"Rmp: a random mask pretrain framework for motion prediction","author":"Yang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0153","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8351","article-title":"Traj-mae: masked autoencoders for trajectory prediction","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0154","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8679","article-title":"Forecast-mae: self-supervised pre-training for motion forecasting with masked autoencoders","author":"Cheng","year":"2023"},{"key":"10.1016\/j.inffus.2026.104457_bib0155","unstructured":"A. Keysan, A. Look, E. Kosman, G. G\u00fcrsun, J. Wagner, Y. Yu, B. Rakitsch, Can you text what is happening? integrating pre-trained language encoders into trajectory prediction models for autonomous driving, (2023). https:\/\/arxiv.org\/pdf\/2309.05282."},{"key":"10.1016\/j.inffus.2026.104457_bib0156","unstructured":"Y. Zhou, H. Shao, L. Wang, S.L. Waslander, H. Li, Y. Liu, SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction, arXiv preprint arXiv: 2410.08669(2024)."},{"key":"10.1016\/j.inffus.2026.104457_bib0157","doi-asserted-by":"crossref","unstructured":"P.S. Chib, P. Singh, LG-Traj: LLM Guided Pedestrian Trajectory Prediction, (2024). https:\/\/arxiv.org\/pdf\/2403.08032.","DOI":"10.1109\/ICCVW69036.2025.00709"},{"key":"10.1016\/j.inffus.2026.104457_bib0158","article-title":"Redmotion: motion prediction via redundancy reduction","author":"Wagner","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104457_bib0159","article-title":"Traj-llm: a new exploration for empowering trajectory prediction with pre-trained large language models","author":"Lan","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0160","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"980","article-title":"Large language models powered context-aware motion prediction in autonomous driving","author":"Zheng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0161","doi-asserted-by":"crossref","unstructured":"M. Peng, X. Guo, X. Chen, M. Zhu, K. Chen, X. Wang, Y. Wang, et al., LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Models, (2024). https:\/\/arxiv.org\/pdf\/2403.18344.","DOI":"10.1016\/j.commtr.2025.100170"},{"key":"10.1016\/j.inffus.2026.104457_bib0162","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103086","article-title":"Behavior-Pred: a semantic-enhanced trajectory pre-training framework for motion forecasting","volume":"120","author":"Shi","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104457_bib0163","unstructured":"J. Mao, Y. Qian, H. Zhao, Y. Wang, Gpt-driver: Learning to drive with gpt, (2023a). https:\/\/arxiv.org\/pdf\/2310.01415."},{"key":"10.1016\/j.inffus.2026.104457_bib0164","unstructured":"J. Mao, J. Ye, Y. Qian, M. Pavone, Y. Wang, A language agent for autonomous driving, arXiv preprint arXiv: 2311.10813(2023b). https:\/\/arxiv.org\/pdf\/2311.10813."},{"key":"10.1016\/j.inffus.2026.104457_bib0165","unstructured":"Y. Zheng, Z. Xing, Q. Zhang, B. Jin, P. Li, Y. Zheng, Z. Xia, K. Zhan, X. Lang, Y. Chen, et al., PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning, (2024). https:\/\/arxiv.org\/pdf\/2406.01587."},{"key":"10.1016\/j.inffus.2026.104457_bib0166","unstructured":"Y. Wang, R. Jiao, S.S. Zhan, C. Lang, C. Huang, Z. Wang, Z. Yang, Q. Zhu, Empowering autonomous driving with large language models: a safety perspective, in: ICLR 2024 Workshop on Large Language Model (LLM) Agents."},{"key":"10.1016\/j.inffus.2026.104457_bib0167","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"966","article-title":"Surrealdriver: designing LLM-powered generative driver agent framework based on human drivers\u2019 driving-thinking data","author":"Jin","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0168","series-title":"European Conference on Computer Vision","first-page":"22","article-title":"Asynchronous large language model enhanced planner for autonomous driving","author":"Chen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0169","doi-asserted-by":"crossref","unstructured":"X. Ye, F. Tao, A. Mallik, B. Yaman, L. Ren, Lord: Large models based opposite reward design for autonomous driving, (2024). https:\/\/arxiv.org\/pdf\/2403.18965.","DOI":"10.1109\/WACV61041.2025.00496"},{"key":"10.1016\/j.inffus.2026.104457_bib0170","doi-asserted-by":"crossref","unstructured":"Z. Huang, Z. Sheng, Y. Qu, J. You, S. Chen, VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving, (2024). https:\/\/arxiv.org\/pdf\/2412.15544.","DOI":"10.1016\/j.trc.2025.105321"},{"key":"10.1016\/j.inffus.2026.104457_bib0171","unstructured":"E. Doroudian, H. Taghavifar, CLIP-RLDrive: Human-Aligned Autonomous Driving via CLIP-Based Reward Shaping in Reinforcement Learning, (2024). https:\/\/arxiv.org\/pdf\/2412.16201."},{"key":"10.1016\/j.inffus.2026.104457_bib0172","unstructured":"Z. Zhou, J. Zhang, J. Zhang, B. Wang, T. Shi, A. Khamis, In-context learning for automated driving scenarios, (2024). https:\/\/arxiv.org\/pdf\/2405.04135."},{"key":"10.1016\/j.inffus.2026.104457_bib0173","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIV.2024.3485964","article-title":"Autoreward: closed-loop reward design with large language models for autonomous driving","author":"Han","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0174","unstructured":"R. Hazra, A. Sygkounas, A. Persson, A. Loutfi, P.Z.D. Martires, REvolve: Reward Evolution with Large Language Models using Human Feedback, (2024). https:\/\/arxiv.org\/pdf\/2406.01309."},{"key":"10.1016\/j.inffus.2026.104457_bib0175","doi-asserted-by":"crossref","unstructured":"C. Xu, J. Liu, Y. Guo, Y. Zhang, P. Hang, J. Sun, Towards Human-Centric Autonomous Driving: A Fast-Slow Architecture Integrating Large Language Model Guidance with Reinforcement Learning, (2025). https:\/\/arxiv.org\/pdf\/2505.06875.","DOI":"10.1109\/ITSC60802.2025.11423568"},{"key":"10.1016\/j.inffus.2026.104457_bib0176","unstructured":"H. Sha, Y. Mu, Y. Jiang, L. Chen, C. Xu, P. Luo, S.E. Li, M. Tomizuka, W. Zhan, M. Ding, Languagempc: Large language models as decision makers for autonomous driving, arXiv preprint arXiv: 2310.03026(2023)."},{"issue":"13","key":"10.1016\/j.inffus.2026.104457_bib0177","doi-asserted-by":"crossref","first-page":"5899","DOI":"10.3390\/s23135899","article-title":"Llm adaptive pid control for b5g truck platooning systems","volume":"23","author":"de Zarz\u00e0","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.inffus.2026.104457_bib0178","unstructured":"K. Long, H. Shi, J. Liu, X. Li, VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving, (2024). https:\/\/arxiv.org\/pdf\/2408.04821."},{"key":"10.1016\/j.inffus.2026.104457_bib0179","doi-asserted-by":"crossref","first-page":"58443","DOI":"10.1109\/ACCESS.2020.2983149","article-title":"A survey of autonomous driving: common practices and emerging technologies","volume":"8","author":"Yurtsever","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.inffus.2026.104457_bib0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.geits.2023.100125","article-title":"Deep transfer learning for intelligent vehicle perception: a survey","author":"Liu","year":"2023","journal-title":"Green Energy Intell. Transp."},{"issue":"3","key":"10.1016\/j.inffus.2026.104457_bib0181","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TIV.2022.3167103","article-title":"A survey on trajectory-prediction methods for autonomous driving","volume":"7","author":"Huang","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0182","doi-asserted-by":"crossref","DOI":"10.1109\/TIV.2023.3274536","article-title":"Motion planning for autonomous driving: the state of the art and future perspectives","author":"Teng","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.inffus.2026.104457_bib0183","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113816","article-title":"Self-driving cars: a survey","volume":"165","author":"Badue","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.inffus.2026.104457_bib0184","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3435937","article-title":"End-to-end autonomous driving: challenges and frontiers","author":"Chen","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104457_bib0185","unstructured":"G. Wang, H. Niu, D. Zhu, J. Hu, X. Zhan, G. Zhou, A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving, (2021). https:\/\/arxiv.org\/pdf\/2110.11573."},{"key":"10.1016\/j.inffus.2026.104457_bib0186","series-title":"2022 IEEE Intelligent Vehicles Symposium (IV)","first-page":"1290","article-title":"Segmented encoding for sim2real of RL-based end-to-End autonomous driving","author":"Chung","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0187","unstructured":"H. Gao, S. Chen, B. Jiang, B. Liao, Y. Shi, X. Guo, Y. Pu, H. Yin, X. Li, X. Zhang, et al., Rad: Training an end-to-end driving policy via large-scale 3dgs-based reinforcement learning, (2025). https:\/\/arxiv.org\/pdf\/2502.13144?."},{"key":"10.1016\/j.inffus.2026.104457_bib0188","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Policy pre-training for autonomous driving via self-supervised geometric modeling","author":"Wu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0189","series-title":"European Conference on Computer Vision","first-page":"111","article-title":"Learning to drive by watching youtube videos: action-conditioned contrastive policy pretraining","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0190","series-title":"10Th International Conference on Learning Representations, ICLR 2022","article-title":"TASK-INDUCED REPRESENTATION LEARNING","author":"Yamada","year":"2022"},{"key":"10.1016\/j.inffus.2026.104457_bib0191","unstructured":"P. Liu, H. Liu, H. Liu, X. Liu, J. Ni, J. Ma, VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion, (2025). https:\/\/arxiv.org\/pdf\/2502.18042?."},{"key":"10.1016\/j.inffus.2026.104457_bib0192","unstructured":"X. Tian, J. Gu, B. Li, Y. Liu, Y. Wang, Z. Zhao, K. Zhan, P. Jia, X. Lang, H. Zhao, DriveVLM: the convergence of autonomous driving and large vision-Language models, in: 8Th Annual Conference on Robot Learning."},{"key":"10.1016\/j.inffus.2026.104457_bib0193","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"12068","article-title":"SOLVE: Synergy of language-Vision and end-to-End networks for autonomous driving","author":"Chen","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0194","unstructured":"B. Jiang, S. Chen, B. Liao, X. Zhang, W. Yin, Q. Zhang, C. Huang, W. Liu, X. Wang, Senna: Bridging large vision-language models and end-to-end autonomous driving, (2024). https:\/\/arxiv.org\/pdf\/2410.22313."},{"key":"10.1016\/j.inffus.2026.104457_bib0195","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3347","article-title":"Dme-driver: integrating human decision logic and 3d scene perception in autonomous driving","volume":"39","author":"Han","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0196","unstructured":"J.-J. Hwang, R. Xu, H. Lin, W.-C. Hung, J. Ji, K. Choi, D. Huang, T. He, P. Covington, B. Sapp, et al., Emma: End-to-end multimodal model for autonomous driving, (2024). https:\/\/arxiv.org\/pdf\/2410.23262."},{"key":"10.1016\/j.inffus.2026.104457_bib0197","series-title":"Proceedings of the Winter Conference on Applications of Computer Vision","first-page":"1001","article-title":"Openemma: open-source multimodal model for end-to-end autonomous driving","author":"Xing","year":"2025"},{"key":"10.1016\/j.inffus.2026.104457_bib0198","doi-asserted-by":"crossref","unstructured":"H. Fu, D. Zhang, Z. Zhao, J. Cui, D. Liang, C. Zhang, D. Zhang, H. Xie, B. Wang, X. Bai, Orion: A holistic end-to-end autonomous driving framework by vision-language instructed action generation, (2025). https:\/\/arxiv.org\/pdf\/2503.19755?.","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"10.1016\/j.inffus.2026.104457_bib0199","unstructured":"Y. Li, K. Xiong, X. Guo, F. Li, S. Yan, G. Xu, L. Zhou, L. Chen, H. Sun, B. Wang, et al., ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving, (2025). https:\/\/arxiv.org\/pdf\/2506.08052?."},{"key":"10.1016\/j.inffus.2026.104457_bib0200","unstructured":"X. Zhou, X. Han, F. Yang, Y. Ma, A.C. Knoll, Opendrivevla: Towards end-to-end autonomous driving with large vision language action model, (2025a). https:\/\/arxiv.org\/pdf\/2503.23463."},{"key":"10.1016\/j.inffus.2026.104457_bib0201","unstructured":"Z. Zhou, T. Cai, S.Z. Zhao, Y. Zhang, Z. Huang, B. Zhou, J. Ma, AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning, (2025b). https:\/\/arxiv.org\/pdf\/2506.13757."},{"key":"10.1016\/j.inffus.2026.104457_bib0202","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2024.3440097","article-title":"Drivegpt4: interpretable end-to-end autonomous driving via large language model","author":"Xu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.inffus.2026.104457_bib0203","doi-asserted-by":"crossref","unstructured":"J. Yuan, S. Sun, D. Omeiza, B. Zhao, P. Newman, L. Kunze, M. Gadd, Rag-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model, (2024). https:\/\/arxiv.org\/pdf\/2402.10828.","DOI":"10.15607\/RSS.2024.XX.075"},{"key":"10.1016\/j.inffus.2026.104457_bib0204","unstructured":"W. Liu, J. Zhang, B. Zheng, Y. Hu, Y. Lin, Z. Zeng, X-driver: Explainable autonomous driving with vision-language models, (2025). https:\/\/arxiv.org\/pdf\/2505.05098?."},{"key":"10.1016\/j.inffus.2026.104457_bib0205","series-title":"European Conference on Computer Vision","first-page":"292","article-title":"Reason2drive: towards interpretable and chain-based reasoning for autonomous driving","author":"Nie","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0206","unstructured":"Z. Yuan, J. Tang, J. Luo, R. Chen, C. Qian, L. Sun, X. Chu, Y. Cai, D. Zhang, S. Li, AutoDrive-R: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving, (2025). https:\/\/arxiv.org\/pdf\/2509.01944."},{"key":"10.1016\/j.inffus.2026.104457_bib0207","series-title":"European Conference on Computer Vision","first-page":"256","article-title":"Drivelm: driving with graph visual question answering","author":"Sima","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0208","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"7325","article-title":"Multi-modal gpt-4 aided action planning and reasoning for self-driving vehicles","author":"Chi","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0209","unstructured":"P. Zheng, Y. Zhao, Z. Gong, H. Zhu, S. Wu, SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving, (2024). https:\/\/arxiv.org\/pdf\/2407.21293."},{"key":"10.1016\/j.inffus.2026.104457_bib0210","unstructured":"G. Team, R. Anil, S. Borgeaud, J.-B. Alayrac, J. Yu, R. Soricut, J. Schalkwyk, A.M. Dai, A. Hauth, K. Millican, et al., Gemini: a family of highly capable multimodal models, (2023). https:\/\/arxiv.org\/pdf\/2312.11805."},{"key":"10.1016\/j.inffus.2026.104457_bib0211","doi-asserted-by":"crossref","unstructured":"Y. Gao, M. Piccinini, Y. Zhang, D. Wang, K. Moller, R. Brusnicki, B. Zarrouki, A. Gambi, J.F. Totz, K. Storms, et al., Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis, (2025). https:\/\/arxiv.org\/pdf\/2506.11526.","DOI":"10.1109\/OJITS.2026.3660686"},{"key":"10.1016\/j.inffus.2026.104457_bib0212","series-title":"International Joint Conference on Artificial Intelligence","article-title":"Fine-tuning pre-trained models for robustness under noisy labels","author":"Ahn","year":"2024"},{"issue":"11","key":"10.1016\/j.inffus.2026.104457_bib0213","doi-asserted-by":"crossref","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","article-title":"Learning from noisy labels with deep neural networks: a survey","volume":"34","author":"Song","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0214","article-title":"Openannotate2: multi-modal auto-annotating for autonomous driving","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"7","key":"10.1016\/j.inffus.2026.104457_bib0215","doi-asserted-by":"crossref","first-page":"8237","DOI":"10.1109\/TITS.2024.3399708","article-title":"An efficient semi-automated scheme for infrastructure lidar annotation","volume":"25","author":"Wu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0216","unstructured":"G.W. Zakarias, L.K. Hansen, Z.-H. Tan, Bissl: Enhancing the alignment between self-supervised pretraining and downstream fine-tuning via bilevel optimization, (2024). https:\/\/arxiv.org\/pdf\/2410.02387."},{"key":"10.1016\/j.inffus.2026.104457_bib0217","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"4519","article-title":"On the generalization ability of unsupervised pretraining","author":"Deng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104457_bib0218","first-page":"15382","article-title":"A theoretical analysis of fine-tuning with linear teachers","volume":"34","author":"Shachaf","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0219","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4276","article-title":"Learning to pre-train graph neural networks","volume":"35","author":"Lu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104457_bib0220","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0221","doi-asserted-by":"crossref","unstructured":"H. Zhang, B. Huang, Z. Li, X. Xiao, H.Y. Leong, Z. Zhang, X. Long, T. Wang, H. Xu, Sensitivity-lora: Low-load sensitivity-based fine-tuning for large language models, (2025). https:\/\/aclanthology.org\/anthology-files\/anthology-files\/pdf\/findings\/2025.findings-emnlp.709.pdf, arXiv preprint arXiv: 2509.09119.","DOI":"10.18653\/v1\/2025.findings-emnlp.709"},{"key":"10.1016\/j.inffus.2026.104457_bib0222","unstructured":"Y. Wang, Y. Yu, J. Liang, R. He, A comprehensive survey on trustworthiness in reasoning with large language models, (2025). https:\/\/arxiv.org\/pdf\/2509.03871."},{"issue":"5","key":"10.1016\/j.inffus.2026.104457_bib0223","doi-asserted-by":"crossref","first-page":"3503","DOI":"10.1007\/s10462-021-10088-y","article-title":"Explainable artificial intelligence: a comprehensive review","volume":"55","author":"Minh","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.inffus.2026.104457_bib0224","unstructured":"B. Jaulmes, J.-C. Arouete, M. Barry, M. Alam, A survey on verifying reasoning chains generated by large language models (2026)."},{"key":"10.1016\/j.inffus.2026.104457_bib0225","doi-asserted-by":"crossref","unstructured":"A. Alansari, H. Luqman, Large language models hallucination: A comprehensive survey, (2025). https:\/\/arxiv.org\/pdf\/2510.06265.","DOI":"10.1016\/j.cosrev.2026.100970"},{"issue":"2","key":"10.1016\/j.inffus.2026.104457_bib0226","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.inffus.2026.104457_bib0227","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"7765","article-title":"Does fine-tuning llms on new knowledge encourage hallucinations?","author":"Gekhman","year":"2024"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003374?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003374?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:05:38Z","timestamp":1783044338000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":227,"alternative-id":["S1566253526003374"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104457","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A comprehensive survey of pretrained models for autonomous driving: Methods and applications","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104457","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104457"}}