{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:11Z","timestamp":1777865531754,"version":"3.51.4"},"reference-count":58,"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\/iccv51701.2025.01250","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13460-13470","source":"Crossref","is-referenced-by-count":0,"title":["CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction"],"prefix":"10.1109","author":[{"given":"Zhefei","family":"Gong","sequence":"first","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxiang","family":"Ding","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangke","family":"Lyu","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoxin","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref6","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref8","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","author":"Jeff Cui","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proceedings of the 5th Conference on Robot Learning","author":"Florence","year":"2022"},{"key":"ref12","article-title":"Dart: Denoising autoregressive transformer for scalable text-to-image generation","author":"Gu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"Gupta","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2012.6252962"},{"key":"ref15","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref17","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"International Conference on Machine Learning","author":"Janner","year":"2022"},{"key":"ref18","first-page":"7354","article-title":"Strictly batch imitation learning by energy-based distribution matching","volume":"33","author":"Jarrett","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Computational tradeoffs in image synthesis: Diffusion, masked-token, and next-token prediction","author":"Kilian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref21","article-title":"Behavior generation with latent actions","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Imagefolder: Autoregressive image generation with folded tokens","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_10"},{"key":"ref26","article-title":"Manicm: Real-time 3d diffusion policy via consistency model for robotic manipulation","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Star: Scale-wise text-to-image generation via auto-regressive representations","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","volume-title":"7th Annual Conference on Robot Learning","author":"Mandlekar","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref31","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Alvinn: An autonomous land vehicle in a neural network. Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.071"},{"key":"ref33","article-title":"Efficient autoregressive audio modeling via next-scale prediction","author":"Qiu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Robot learning with sensorimotor pre-training","author":"Radosavovic","year":"2023","journal-title":"arXiv"},{"issue":"140","key":"ref35","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref36","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Goal-conditioned imitation learning using scorebased diffusion policies","author":"Reuss","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref39","article-title":"Behavior transformers: Cloning k modes with one stone","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems","author":"Muhammad","year":"2022"},{"key":"ref40","article-title":"Outra-geously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801816"},{"key":"ref42","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref46","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Sparse diffusion policy: A sparse, reusable, and flexible policy for robot learning","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Equibot: Sim (3)equivariant diffusion policy for generalizable and data efficient learning","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref51","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Zeng","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/262"},{"key":"ref53","article-title":"Var-clip: Text-to-image generator with visual auto-regressive modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref55","article-title":"Cobra: Extending mamba to multimodal large language model for efficient inference","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref58","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"}],"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\/11445238.pdf?arnumber=11445238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:42Z","timestamp":1777531602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01250","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}