{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:33Z","timestamp":1778048433618,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00101","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"967-976","source":"Crossref","is-referenced-by-count":0,"title":["No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts"],"prefix":"10.1109","author":[{"given":"Macaluso","family":"Girolamo","sequence":"first","affiliation":[{"name":"University of Florence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mandelli","family":"Lorenzo","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirko","family":"Bicchierai","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Berretti","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew D.","family":"Bagdanov","sequence":"additional","affiliation":[{"name":"University of Florence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref2","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667071"},{"key":"ref5","article-title":"Directly fine-tuning diffusion models on differentiable rewards","author":"Clark","year":"2023"},{"key":"ref6","article-title":"DPOK: Reinforcement learning for fine-tuning text-to-image diffusion models","author":"Fan","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00186"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00222"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref12","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925975"},{"key":"ref14","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681657"},{"key":"ref16","author":"Jiang","year":"2023","journal-title":"Motiongpt: Human motion as a foreign language"},{"key":"ref17","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the nineteenth international conference on machine learning","author":"Kakade"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref19","article-title":"Stablemotionfusion: Text-driven human motion synthesis via diffusion models","author":"Kim","year":"2022","journal-title":"Computer Graphics Forum"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566605"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00763"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01353"},{"key":"ref25","article-title":"Motionrl: Align text-to-motion generation to human preferences with multi-reward reinforcement learning","author":"Liu","year":"2024"},{"key":"ref26","article-title":"Cross-dataset adaptation for diffusion-based motion models","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Liu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref29","article-title":"Motiontransfer: Domain adaptation for human motion synthesis","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00132"},{"key":"ref31","article-title":"Learning generalizable human motion generator with reinforcement learning","author":"Mao","year":"2024"},{"key":"ref32","author":"Mao","year":"2024","journal-title":"Learning generalizable human motion generator with reinforcement learning"},{"key":"ref33","article-title":"Neural probabilistic motor primitives for humanoid control","author":"Merel","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref40","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0726"},{"key":"ref43","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref44","author":"Tevet","year":"2022","journal-title":"Human motion diffusion model"},{"key":"ref45","author":"den Oord","year":"2017","journal-title":"Neural discrete representation learning"},{"key":"ref46","author":"Wang","year":"2025","journal-title":"Aligning human motion generation with human perceptions"},{"key":"ref47","author":"Wei","year":"2024","journal-title":"Powerful and flexible: Personalized text-to-image generation via reinforcement learning"},{"key":"ref48","author":"Xu","year":"2022","journal-title":"Actformer: A gan-based transformer towards general action-conditioned 3d human motion generation"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref50","author":"Zhang","year":"2022","journal-title":"Motion-diffuse: Text-driven human motion generation with diffusion model"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_1"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492618.pdf?arnumber=11492618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:05:28Z","timestamp":1778047528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00101","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}