X‐Gen: Synergizing Extended LSTM and Generative Diffusion for Cognition‐Aware Motion Forecasting.
Saved in:
| Title: | X‐Gen: Synergizing Extended LSTM and Generative Diffusion for Cognition‐Aware Motion Forecasting. |
|---|---|
| Authors: | Liu, Liu1 (AUTHOR) liuliu@cueb.edu.cn, Xu, Zhifei2 (AUTHOR), Murray, Richard (AUTHOR) rmurray@wiley.com |
| Source: | International Journal of Intelligent Systems. 6/3/2026, Vol. 2026, p1-14. 14p. |
| Subjects: | Long short-term memory, Probabilistic generative models, Knowledge representation (Information theory), Machine learning, Autonomous vehicles |
| Abstract: | 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‐world traffic. To bridge this cognitive gap, we introduce X‐Gen, 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‐Gen establishes a direct semantic alignment between continuous kinematic states and the high‐dimensional embedding space of a pretrained Llama‐3‐8B backbone via quantized low‐rank adaptation (Q‐LoRA). This architecture allows the system to internalize scene semantics as a coherent "World Model." Furthermore, to resolve long‐range topological dependencies, we propose a lane‐aware cognitive gating mechanism powered by the extended LSTM (xLSTM). Leveraging xLSTM's 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‐scale Waymo open motion dataset demonstrates that X‐Gen establishes new state‐of‐the‐art benchmarks in both accuracy and diversity metrics. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Intelligent Systems is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194259788 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: X‐Gen: Synergizing Extended LSTM and Generative Diffusion for Cognition‐Aware Motion Forecasting. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Liu%2C+Liu%22">Liu, Liu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> liuliu@cueb.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Zhifei%22">Xu, Zhifei</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Murray%2C+Richard%22">Murray, Richard</searchLink> (AUTHOR)<i> rmurray@wiley.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Intelligent+Systems%22">International Journal of Intelligent Systems</searchLink>. 6/3/2026, Vol. 2026, p1-14. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+representation+%28Information+theory%29%22">Knowledge representation (Information theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Autonomous+vehicles%22">Autonomous vehicles</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: 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‐world traffic. To bridge this cognitive gap, we introduce X‐Gen, 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‐Gen establishes a direct semantic alignment between continuous kinematic states and the high‐dimensional embedding space of a pretrained Llama‐3‐8B backbone via quantized low‐rank adaptation (Q‐LoRA). This architecture allows the system to internalize scene semantics as a coherent "World Model." Furthermore, to resolve long‐range topological dependencies, we propose a lane‐aware cognitive gating mechanism powered by the extended LSTM (xLSTM). Leveraging xLSTM's 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‐scale Waymo open motion dataset demonstrates that X‐Gen establishes new state‐of‐the‐art benchmarks in both accuracy and diversity metrics. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Intelligent Systems is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194259788 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1155/int/3301987 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 1 Subjects: – SubjectFull: Long short-term memory Type: general – SubjectFull: Probabilistic generative models Type: general – SubjectFull: Knowledge representation (Information theory) Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Autonomous vehicles Type: general Titles: – TitleFull: X‐Gen: Synergizing Extended LSTM and Generative Diffusion for Cognition‐Aware Motion Forecasting. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Liu, Liu – PersonEntity: Name: NameFull: Xu, Zhifei – PersonEntity: Name: NameFull: Murray, Richard IsPartOfRelationships: – BibEntity: Dates: – D: 03 M: 06 Text: 6/3/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 08848173 Numbering: – Type: volume Value: 2026 Titles: – TitleFull: International Journal of Intelligent Systems Type: main |
| ResultId | 1 |
