{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:00:58Z","timestamp":1780473658607,"version":"3.54.1"},"reference-count":40,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"vor","delay-in-days":153,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Motion forecasting in autonomous driving has historically relied on discriminative baselines that prioritize statistical correlation over causal reasoning, often failing to capture the complex social dynamics of real\u2010world traffic. To bridge this cognitive gap, we introduce X\u2010Gen, a novel generative framework that synergizes the inferential depth of foundation models with the probabilistic precision of diffusion models. Unlike prior approaches constrained by heuristic textual prompts, X\u2010Gen establishes a direct semantic alignment between continuous kinematic states and the high\u2010dimensional embedding space of a pretrained Llama\u20103\u20108B backbone via quantized low\u2010rank adaptation (Q\u2010LoRA). This architecture allows the system to internalize scene semantics as a coherent \u201cWorld Model.\u201d Furthermore, to resolve long\u2010range topological dependencies, we propose a lane\u2010aware cognitive gating mechanism powered by the extended LSTM (xLSTM). Leveraging xLSTM\u2019s matrix memory and exponential gating, this module selectively filters spatial constraints with linear computational complexity, effectively pruning the search space for navigational intent. Finally, we eschew restrictive parametric distributions in favor of a conditional diffusion decoder, which formulates trajectory synthesis as an iterative denoising process guided by the aligned cognitive features. Empirical validation on the large\u2010scale Waymo open motion dataset demonstrates that X\u2010Gen establishes new state\u2010of\u2010the\u2010art benchmarks in both accuracy and diversity metrics.<\/jats:p>","DOI":"10.1155\/int\/3301987","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T07:04:42Z","timestamp":1780470282000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["X\u2010Gen: Synergizing Extended LSTM and Generative Diffusion for Cognition\u2010Aware Motion Forecasting"],"prefix":"10.1155","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2807-7934","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9951-0518","authenticated-orcid":false,"given":"Zhifei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"e_1_2_10_1_2","first-page":"5998","article-title":"Attention is all You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_2_2","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume":"33","author":"Brown T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_3_2","unstructured":"RadfordA. KimJ. W. HallacyC.et al. Learning Transferable Visual Models From Natural Language Supervision International Conference on Machine Learning (ICML) 2021 New York NY PMLR 8748\u20138763."},{"key":"e_1_2_10_4_2","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron H.","year":"2023","journal-title":"arXiv Preprint arXiv:2302.13971"},{"key":"e_1_2_10_5_2","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron H.","year":"2023","journal-title":"arXiv Preprint arXiv:2307.09288"},{"key":"e_1_2_10_6_2","article-title":"The Llama 3 Herd of Models","author":"Dubey A.","year":"2024","journal-title":"arXiv Preprint arXiv:2407.21783"},{"key":"e_1_2_10_7_2","article-title":"xLSTM: Extended Long Short-Term Memory","author":"Beck M.","year":"2024","journal-title":"arXiv Preprint arXiv:2405.04517"},{"key":"e_1_2_10_8_2","article-title":"Mamba: Linear-Time Sequence Modeling With Selective State Spaces","author":"Gu A.","year":"2023","journal-title":"arXiv Preprint arXiv:2312.00752"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"HeK. ChenX. XieS.et al. Masked Autoencoders are Scalable Vision Learners IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 New York NY IEEE 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_2_10_10_2","unstructured":"ChenT. KornblithS. NorouziM.et al. A Simple Framework for Contrastive Learning of Visual Representations International Conference on Machine Learning (ICML) 2020 New York NY PMLR 1597\u20131607."},{"key":"e_1_2_10_11_2","first-page":"21271","article-title":"Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning","volume":"33","author":"Grill J. B.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_12_2","first-page":"6531","article-title":"Motion Transformer With Global Intention Localization and Local Movement Refinement","volume":"35","author":"Shi S.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3352811"},{"key":"e_1_2_10_14_2","unstructured":"NgiamJ. CaineB. VasudevanV.et al. Scene Transformer: A Unified Architecture for Predicting Multiple Agent Trajectories International Conference on Learning Representations (ICLR) 2022 Rio de Janeiro Brazil ICLR."},{"key":"e_1_2_10_15_2","doi-asserted-by":"crossref","unstructured":"NayakantiN. Al-RfouR. ZhouA.et al. Wayformer: Motion Forecasting via Simple and Efficient Attention Networks IEEE International Conference on Robotics and Automation (ICRA) 2023 New York NY IEEE 2980\u20132987.","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"ZhouZ. WangJ. LiY. H.et al. Query-Centric Trajectory Prediction IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 New York NY IEEE 17863\u201317873.","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"JiangC. M. CornmanA. ParkC.et al. Motiondiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023 New York NY IEEE 9644\u20139653.","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"SeffA. CeraB. ChenD.et al. Motionlm: Multi-Agent Motion Forecasting as Language Modeling IEEE\/CVF International Conference on Computer Vision (ICCV) 2023 New York NY IEEE 16779\u201316789.","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"ChangW. J. PittalugaF. TomizukaM.et al. Safe-Sim: Safety-Critical Closed-Loop Traffic Simulation With Diffusion-Controllable Adversaries European Conference on Computer Vision (ECCV) 2025 Berlin Germany Springer 242\u2013258.","DOI":"10.1007\/978-3-031-72664-4_14"},{"key":"e_1_2_10_20_2","article-title":"Langtraj: Diffusion Model and Dataset for language-conditioned Trajectory Simulation","author":"Chang W. J.","year":"2025","journal-title":"arXiv Preprint arXiv:2504.11521"},{"key":"e_1_2_10_21_2","unstructured":"TanS. IvanovicB. ChenY.et al. Promptable Closed-Loop Traffic Simulation Conference on Robot Learning (CoRL) 2025 Santa Clara CA NVIDIA 5087\u20135105."},{"key":"e_1_2_10_22_2","unstructured":"ZhongZ. RempeD. ChenY.et al. Language-Guided Traffic Simulation via Scene-Level Diffusion Conference on Robot Learning (CoRL) 2023 144\u2013177."},{"key":"e_1_2_10_23_2","doi-asserted-by":"crossref","unstructured":"SuoS. RegaladoS. CasasS.et al. TrafficSim: Learning to Simulate Realistic multi-agent Behaviors IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021 New York NY PMLR 10400\u201310409.","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"e_1_2_10_24_2","doi-asserted-by":"crossref","unstructured":"XuD. ChenY. IvanovicB.et al. Bi-Level Imitation for Traffic Simulation IEEE International Conference on Robotics and Automation (ICRA) 2023 New York NY IEEE 2929\u20132936.","DOI":"10.1109\/ICRA48891.2023.10161167"},{"key":"e_1_2_10_25_2","unstructured":"PhilionJ. PengX. B. andFidlerS. Trajeglish: Traffic Modeling as Next-Token Prediction International Conference on Learning Representations (ICLR) 2024 New York NY PMLR."},{"key":"e_1_2_10_26_2","doi-asserted-by":"crossref","unstructured":"EttingerS. ChengS. CaineB.et al. Large Scale Interactive Motion Forecasting for Autonomous Driving: the Waymo Open Motion Dataset IEEE\/CVF International Conference on Computer Vision (ICCV) 2021 New York NY IEEE 9710\u20139719.","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"e_1_2_10_27_2","article-title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","author":"Wilson B.","year":"2023","journal-title":"arXiv Preprint arXiv:2301.00493"},{"key":"e_1_2_10_28_2","article-title":"NuPlan: A Closed-Loop ML-Based Planning Benchmark for Autonomous Vehicles","author":"Caesar H.","year":"2021","journal-title":"arXiv Preprint arXiv:2106.11810"},{"key":"e_1_2_10_29_2","doi-asserted-by":"crossref","unstructured":"GaoJ. SunC. ZhaoH.et al. VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized Representation IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 New York NY IEEE 11525\u201311533.","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"e_1_2_10_30_2","unstructured":"WagnerR. Ta\u015f\u00d6 S. KlempM.et al. Jointmotion: Joint Self-Supervision for Joint Motion Prediction Conference on Robot Learning (CoRL) 2024 New York NY PMLR."},{"key":"e_1_2_10_31_2","article-title":"RedMotion: Motion Prediction via Redundancy Reduction","author":"Wagner R.","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"e_1_2_10_32_2","article-title":"RetroMotion: Retrocausal Motion Forecasting Models are Instructable","author":"Wagner R.","year":"2025","journal-title":"arXiv Preprint arXiv:2505.20414"},{"key":"e_1_2_10_33_2","article-title":"Driving With LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","author":"Chen L.","year":"2023","journal-title":"arXiv Preprint arXiv:2310.01957"},{"key":"e_1_2_10_34_2","doi-asserted-by":"crossref","unstructured":"SimaC. RenzK. ChittaK.et al. DriveLM: Driving With Graph Visual Question Answering European Conference on Computer Vision (ECCV) 2024 New York NY Springer.","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"e_1_2_10_35_2","article-title":"LG-Traj: LLM Guided Pedestrian Trajectory Prediction","author":"Chib P. S.","year":"2024","journal-title":"arXiv Preprint arXiv:2403.08032"},{"key":"e_1_2_10_36_2","unstructured":"Language-Based Multimodal Trajectory Prediction IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 New York NY IEEE."},{"key":"e_1_2_10_37_2","doi-asserted-by":"crossref","unstructured":"DemmlerT. HartungL. TamkeA.et al. Dynamic Intent Queries for Motion Transformer-Based Trajectory Prediction IEEE Intelligent Vehicles Symposium (IV) 2025 New York NY IEEE.","DOI":"10.1109\/IV64158.2025.11097417"},{"key":"e_1_2_10_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28130"},{"key":"e_1_2_10_39_2","doi-asserted-by":"crossref","unstructured":"XuC. LiT. TangC.et al. PreTraM: Self-Supervised Pre-Training via Connecting Trajectory and Map European Conference on Computer Vision (ECCV) 2022 34\u201350.","DOI":"10.1007\/978-3-031-19842-7_3"},{"key":"e_1_2_10_40_2","doi-asserted-by":"crossref","unstructured":"ChenH. WangJ. ShaoK.et al. Traj-MAE: Masked Autoencoders for Trajectory Prediction IEEE\/CVF International Conference on Computer Vision (ICCV) 2023 New York NY IEEE 16512\u201316523.","DOI":"10.1109\/ICCV51070.2023.00767"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/3301987","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/3301987","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/3301987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T07:04:54Z","timestamp":1780470294000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/3301987"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1155\/int\/3301987"],"URL":"https:\/\/doi.org\/10.1155\/int\/3301987","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-11-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3301987"}}