{"ID":2861944,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00627","arxiv_id":"2510.00627","title":"Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction","abstract":"Trajectory prediction is a fundamental task in Autonomous Vehicles (AVs) and Intelligent Transportation Systems (ITS), supporting efficient motion planning and real-time traffic safety management. Diffusion models have recently demonstrated strong performance in probabilistic trajectory prediction, but their large model size and slow sampling process hinder real-world deployment. This paper proposes Collaborative-Distilled Diffusion Models (CDDM), a novel method for real-time and lightweight trajectory prediction. Built upon Collaborative Progressive Distillation (CPD), CDDM progressively transfers knowledge from a high-capacity teacher diffusion model to a lightweight student model, jointly reducing both the number of sampling steps and the model size across distillation iterations. A dual-signal regularized distillation loss is further introduced to incorporate guidance from both the teacher and ground-truth data, mitigating potential overfitting and ensuring robust performance. Extensive experiments on the ETH-UCY pedestrian benchmark and the nuScenes vehicle benchmark demonstrate that CDDM achieves state-of-the-art prediction accuracy. The well-distilled CDDM retains 96.2% and 95.5% of the baseline model's ADE and FDE performance on pedestrian trajectories, while requiring only 231K parameters and 4 or 2 sampling steps, corresponding to 161x compression, 31x acceleration, and 9 ms latency. Qualitative results further show that CDDM generates diverse and accurate trajectories under dynamic agent behaviors and complex social interactions. By bridging high-performing generative models with practical deployment constraints, CDDM enables resource-efficient probabilistic prediction for AVs and ITS. Code is available at https://github.com/bingzhangw/CDDM.","short_abstract":"Trajectory prediction is a fundamental task in Autonomous Vehicles (AVs) and Intelligent Transportation Systems (ITS), supporting efficient motion planning and real-time traffic safety management. Diffusion models have recently demonstrated strong performance in probabilistic trajectory prediction, but their large mode...","url_abs":"https://arxiv.org/abs/2510.00627","url_pdf":"https://arxiv.org/pdf/2510.00627v1","authors":"[\"Bingzhang Wang\",\"Kehua Chen\",\"Yinhai Wang\"]","published":"2025-10-01T08:00:31Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":608858,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2861944,"paper_url":"https://arxiv.org/abs/2510.00627","paper_title":"Collaborative-Distilled Diffusion Models (CDDM) for Accelerated and Lightweight Trajectory Prediction","repo_url":"https://github.com/bingzhangw/CDDM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}