{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:06Z","timestamp":1777865526136,"version":"3.51.4"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00418","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4391-4402","source":"Crossref","is-referenced-by-count":0,"title":["TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction"],"prefix":"10.1109","author":[{"given":"Zewei","family":"Zhou","sequence":"first","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Seth Z.","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Tianhui","family":"Cai","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Zhiyu","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]},{"given":"Jiaqi","family":"Ma","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00139"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363300"},{"key":"ref5","article-title":"Trend: Unsupervised 3d representation learning via temporal forecasting for lidar perception","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Gradient-based multi-objective deep learning: Algorithms, theories, applications, and beyond","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International conference on machine learning","author":"Chen","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01138"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00159"},{"key":"ref10","article-title":"Masked autoencoders as spatiotemporal learners","volume":"abs\/2205.09113","author":"Feichtenhofer","year":"2022","journal-title":"ArXiv"},{"key":"ref11","article-title":"Mitigating gradient bias in multi-objective learning: A provably convergent approach","volume-title":"International Conference on Learning Representations","author":"Fernando","year":"2023"},{"key":"ref12","article-title":"Stamp: Scalable task and model-agnostic collaborative perception","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3349324"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01289"},{"key":"ref17","article-title":"Lidar-based 4 d panoptic segmentation via dynamic shifting network","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref21","article-title":"Revisiting scalarization in multi-task learning: A theoretical perspective","volume":"36","author":"Hu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"V2x-r: Cooperative lidar-4d radar fusion for 3d object detection with denoising diffusion","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3167103"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109751"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246231"},{"key":"ref27","article-title":"Learning distilled collaboration graph for multi-agent perception","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)","author":"Li","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192802"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802492"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1428"},{"issue":"1","key":"ref31","first-page":"9999","article-title":"Libmtl: A python library for deep multi-task learning","volume":"24","author":"Lin","year":"2023","journal-title":"The Journal of Machine Learning Research"},{"key":"ref32","article-title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning","author":"Lin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref34","article-title":"Smooth tchebycheff scalarization for multi-objective optimization","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28141"},{"key":"ref36","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00197"},{"key":"ref38","article-title":"Towards vehicle-to-everything autonomous driving: A survey on collaborative perception","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"An extensible framework for open heterogeneous collaborative perception","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu","year":"2024"},{"key":"ref40","author":"Meng","year":"2024","journal-title":"Agentalign: Misalignment-adapted multiagent perception for resilient inter-agent sensor correlations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3322409"},{"key":"ref42","author":"Ruan","year":"2023","journal-title":"Learning Cooperative Trajectory Representations for Motion Forecasting"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01704"},{"key":"ref45","article-title":"Sparsedrive: End-to-end autonomous driving via sparse scene representation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01304"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00800"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"ref49","article-title":"Asynchrony-robust collaborative perception via bird\u2019s eye view flow","author":"Wei","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","first-page":"178","article-title":"T-mae: temporal masked autoencoders for point cloud representation learning","volume-title":"European Conference on Computer Vision","author":"Wei","year":"2024"},{"key":"ref51","article-title":"T-mae: Temporal masked autoencoders for point cloud representation learning","volume-title":"European Conference on Computer Vision (ECCV)","author":"Gevers","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref53","article-title":"Cmp: Cooperative motion prediction with multi-agent communication","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"One is plenty: A polymorphic feature interpreter for immutable heterogeneous collaborative perception","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_26"},{"key":"ref56","author":"Xiang","year":"2025","journal-title":"V2x-realo: An open online framework and dataset for cooperative perception in reality"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29541"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00907"},{"key":"ref65","article-title":"Pred: pre-training via semantic rendering on lidar point clouds","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02137"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00531"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1497"},{"key":"ref71","article-title":"End-to-end autonomous driving through v 2 x cooperation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref73","article-title":"E2emfd: Towards end-to-end synchronous multimodal fusion detection","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","first-page":"11096","article-title":"Random hypervolume scalarizations for provable multi-objective black box optimization","volume-title":"International conference on machine learning","author":"Zhang","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127303"},{"key":"ref76","article-title":"Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Coopre: Cooperative pretraining for v2x cooperative perception","author":"Seth","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2022.103909"},{"key":"ref79","article-title":"V2XPnP: Vehicle-to-everything spatio-temporal fusion for multi-agent perception and prediction","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02139"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444635.pdf?arnumber=11444635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:20Z","timestamp":1777531580000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00418","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}