{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:58:41Z","timestamp":1780498721050,"version":"3.54.1"},"reference-count":52,"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\/iros60139.2025.11245863","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"16993-17000","source":"Crossref","is-referenced-by-count":4,"title":["CoMamba: Real-time Cooperative Perception Unlocked with State-Space Models"],"prefix":"10.1109","author":[{"given":"Jinlong","family":"Li","sequence":"first","affiliation":[{"name":"Texas A&M University,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Cleveland State University,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baolu","family":"Li","sequence":"additional","affiliation":[{"name":"Cleveland State University,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Independent Researcher,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiachen","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Yu","sequence":"additional","affiliation":[{"name":"Cleveland State University,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengzhong","family":"Tu","sequence":"additional","affiliation":[{"name":"Texas A&M University,Riverside"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref2","article-title":"Cobevt: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","author":"Xu","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363300"},{"key":"ref4","article-title":"Generative ai for autonomous driving: Frontiers and opportunities","author":"Wang","year":"2025"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00033"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3479222"},{"key":"ref10","article-title":"Stamp: Scalable task and model-agnostic collaborative perception","author":"Gao","year":"2025"},{"key":"ref11","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref12","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proceedings of the 11th International Conference on Learning Representations (ICLR)","author":"Dao"},{"key":"ref13","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022"},{"key":"ref14","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref16","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024"},{"key":"ref17","article-title":"Spikemba: Multi-modal spiking saliency mamba for temporal video grounding","author":"Li","year":"2024"},{"key":"ref18","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_28"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160546"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3282567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"ref26","first-page":"29 541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00406"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"ref29","first-page":"4874","article-title":"Where2comm: Communication-efficient collaborative perception via spatial confidence maps","volume-title":"Advances in neural information processing systems","volume":"35","author":"Hu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02137"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161460"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160871"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3260040"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3371974"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186727"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3084519"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610591"},{"key":"ref40","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref41","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024"},{"key":"ref42","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume-title":"Advances in neural information processing systems","volume":"34","author":"Gu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564825"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref47","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref48","article-title":"Airv2x: Unified air-ground vehicle-to-everything collaboration","author":"Gao","year":"2025"},{"key":"ref49","article-title":"Mmhu: A massive-scale multimodal benchmark for human behavior understanding","author":"Li","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3673227"},{"key":"ref51","article-title":"V2x-llm: Enhancing v2x integration and understanding in connected vehicle corridors","author":"Wu","year":"2025"},{"key":"ref52","article-title":"V2x-unipool: Unifying multimodal perception and knowledge reasoning for autonomous driving","author":"Luo","year":"2025"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11245863.pdf?arnumber=11245863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:19Z","timestamp":1766061319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245863","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}