{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:13:53Z","timestamp":1778699633587,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127693","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9533-9539","source":"Crossref","is-referenced-by-count":2,"title":["Quart-Online: Latency-Free Multimodal Large Language Model for Quadruped Robot Learning"],"prefix":"10.1109","author":[{"given":"Xinyang","family":"Tong","sequence":"first","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxiang","family":"Ding","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiguo","family":"Fan","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Cui","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhao","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Dang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangke","family":"Lyu","sequence":"additional","affiliation":[{"name":"Westlake University,MiLAB,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Saytap: Language to quadrupedal locomotion","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"2018","article-title":"Vinl: Visual navigation and locomotion over obstacles","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Kareer"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_21"},{"key":"ref5","article-title":"Barkour: Benchmarking animal-level agility with quadruped robots","author":"Caluwaerts","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers","volume-title":"ArXiv","author":"Yang","year":"2021"},{"issue":"6","key":"ref7","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.3390\/robotics13060086","article-title":"Learning advanced locomotion for quadrupedal robots: A distributed multi-agent reinforcement learning framework with riemannian motion policies","volume":"13","author":"Wang","year":"2024","journal-title":"Robotics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160747"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2019.8793485","article-title":"Making sense of vision and touch: Self-supervised learning of multimodal representations for contact-rich tasks","volume-title":"2019 IEEE International Conference on Robotics and Automation (ICRA)","author":"Lee"},{"key":"ref12","article-title":"Hydra: Hybrid robot actions for imitation learning","volume-title":"Proceedings of the 7th Conference on Robot Learning (CoRL)","author":"Belkhale"},{"key":"ref13","article-title":"Watch and match: Supercharging imitation with regularized optimal transport","author":"Haldar","year":"2022","journal-title":"CoRL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10802742","volume-title":"Learning visual quadrupedal loco-manipulation from demonstrations","author":"He","year":"2024"},{"key":"ref16","volume-title":"Genloco: Generalized locomotion controllers for quadrupedal robots","author":"Feng","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3335777"},{"key":"ref18","volume-title":"Long-horizon locomotion and manipulation on a quadrupedal robot with large language models","author":"Ouyang","year":"2024"},{"key":"ref19","article-title":"Lanmp: A multifaceted mobile manipulation benchmark for robots","author":"Jaafar","journal-title":"RSS 2024 Workshop: Data Generation for Robotics"},{"key":"ref20","volume-title":"Learning multiple gaits within latent space for quadruped robots","author":"Wu","year":"2023"},{"key":"ref21","article-title":"Quadrupedgpt: Towards a versatile quadruped agent in open-ended worlds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801816"},{"key":"ref23","article-title":"Efficient large language models: A survey","volume":"1","author":"Wan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref25","article-title":"Llava-gemma: Accelerating multimodal foundation models with a compact language model","author":"Hinck","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Cobra: Extending mamba to multi-modal large language model for efficient inference","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Linearizing large language models","author":"Mercat","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref30","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref31","volume-title":"Rt-h: Action hierarchies using language","author":"Belkhale","year":"2024"},{"key":"ref32","volume-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"ref33","volume-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","author":"Wu","year":"2023"},{"key":"ref34","volume-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2024"},{"key":"ref35","volume-title":"3d diffuser actor: Policy diffusion with 3d scene representations","author":"Ke","year":"2024"},{"key":"ref36","volume-title":"Grounding multimodal large language models in actions","author":"Szot","year":"2024"},{"key":"ref37","volume-title":"Introducing our multimodal models","author":"Bavishi","year":"2023"},{"key":"ref38","author":"Makoviychuk","year":"2021","journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning"},{"key":"ref39","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Proceedings of The 6th Conference on Robot Learning, ser. Proceedings of Machine Learning Research, K. Liu, D. Kulic, and J. Ichnowski, Eds.","volume":"205","author":"Margolis"},{"key":"ref40","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref41","author":"Majumdar","journal-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127693.pdf?arnumber=11127693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:27Z","timestamp":1756879527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127693","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}