TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908481884258304 |
|---|---|
| author | Zhou, Zewei Zhao, Seth Z. Cai, Tianhui Huang, Zhiyu Zhou, Bolei Ma, Jiaqi |
| author_facet | Zhou, Zewei Zhao, Seth Z. Cai, Tianhui Huang, Zhiyu Zhou, Bolei Ma, Jiaqi |
| contents | End-to-end training of multi-agent systems offers significant advantages in improving multi-task performance. However, training such models remains challenging and requires extensive manual design and monitoring. In this work, we introduce TurboTrain, a novel and efficient training framework for multi-agent perception and prediction. TurboTrain comprises two key components: a multi-agent spatiotemporal pretraining scheme based on masked reconstruction learning and a balanced multi-task learning strategy based on gradient conflict suppression. By streamlining the training process, our framework eliminates the need for manually designing and tuning complex multi-stage training pipelines, substantially reducing training time and improving performance. We evaluate TurboTrain on a real-world cooperative driving dataset, V2XPnP-Seq, and demonstrate that it further improves the performance of state-of-the-art multi-agent perception and prediction models. Our results highlight that pretraining effectively captures spatiotemporal multi-agent features and significantly benefits downstream tasks. Moreover, the proposed balanced multi-task learning strategy enhances detection and prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction Zhou, Zewei Zhao, Seth Z. Cai, Tianhui Huang, Zhiyu Zhou, Bolei Ma, Jiaqi Computer Vision and Pattern Recognition End-to-end training of multi-agent systems offers significant advantages in improving multi-task performance. However, training such models remains challenging and requires extensive manual design and monitoring. In this work, we introduce TurboTrain, a novel and efficient training framework for multi-agent perception and prediction. TurboTrain comprises two key components: a multi-agent spatiotemporal pretraining scheme based on masked reconstruction learning and a balanced multi-task learning strategy based on gradient conflict suppression. By streamlining the training process, our framework eliminates the need for manually designing and tuning complex multi-stage training pipelines, substantially reducing training time and improving performance. We evaluate TurboTrain on a real-world cooperative driving dataset, V2XPnP-Seq, and demonstrate that it further improves the performance of state-of-the-art multi-agent perception and prediction models. Our results highlight that pretraining effectively captures spatiotemporal multi-agent features and significantly benefits downstream tasks. Moreover, the proposed balanced multi-task learning strategy enhances detection and prediction. |
| title | TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04682 |