{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:09:05Z","timestamp":1783490945108,"version":"3.55.0"},"reference-count":55,"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\/iccv51701.2025.01225","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13183-13192","source":"Crossref","is-referenced-by-count":1,"title":["GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kelin","family":"Yu","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harshit","family":"Soora","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furong","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pratap","family":"Tokekar","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruohan","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Burda","year":"2018","journal-title":"Exploration by random network distillation"},{"key":"ref2","author":"Chen","year":"2024","journal-title":"Object-centric dexterous manipulation from human motion data"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref4","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Video prediction models as rewards for reinforcement learning","volume":"36","author":"Escontrela","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","author":"Fu","year":"2018","journal-title":"Learning robust rewards with adversarial inverse reinforcement learning"},{"key":"ref7","article-title":"FLIP: Flow-centric generative planning for general-purpose manipulation tasks","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Gao","year":"2025"},{"key":"ref8","author":"Guo","year":"2024","journal-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128690"},{"key":"ref10","author":"Haarnoja","year":"2018","journal-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3443595"},{"key":"ref12","author":"Ho","year":"2016","journal-title":"Generative adversarial imitation learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127562"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-35280-8_1432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_27"},{"key":"ref18","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"8th Annual Conference on Robot Learning","author":"Huang","year":"2024"},{"key":"ref19","article-title":"Robots pre-train robots: Manipulation-centric robotic representation from large-scale robot datasets","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127989"},{"key":"ref22","author":"Ko","year":"2023","journal-title":"Learning to Act from Actionless Videos through Dense Correspondences"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_16"},{"key":"ref24","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128755"},{"key":"ref26","article-title":"LEAGUE++: EMPOWERING CONTINUAL ROBOT LEARNING THROUGH GUIDED SKILL ACQUISITION WITH LARGE LANGUAGE MODELS","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Li","year":"2024"},{"key":"ref27","article-title":"Code as policies: Language model programs for embodied control","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Dreamitate: Real-world visuomotor policy learning via video generation","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Flowretrieval: Flow-guided data retrieval for few-shot imitation learning","volume-title":"8th Annual Conference on Robot Learning","author":"Lin","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","author":"Jason Ma","year":"2023","journal-title":"Liv: Language-image representations and rewards for robotic control"},{"key":"ref32","article-title":"Eureka: Human-level reward design via coding large language models","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127585"},{"key":"ref34","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3577424"},{"key":"ref38","author":"Tang","year":"2024","journal-title":"Embodiment-agnostic action planning via object-part scene flow"},{"key":"ref39","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref41","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref42","article-title":"This&that: Language-gesture controlled video generation for robot planning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","author":"Wang","year":"2024","journal-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2173"},{"key":"ref45","author":"Xie","year":"2024","journal-title":"Text2reward: Reward shaping with language models for reinforcement learning"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref47","author":"Xu","year":"2024","journal-title":"Flow as the cross-domain manipulation interface"},{"key":"ref48","author":"Yan","year":"2021","journal-title":"Videogpt: Video generation using vq-vae and transformers"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610873"},{"key":"ref50","article-title":"Mastering visual continuous control: Improved dataaugmented reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Yarats","year":"2022"},{"key":"ref51","article-title":"Mimictouch: Leveraging multi-modal human tactile demonstrations for contact-rich manipulation","volume-title":"8th Annual Conference on Robot Learning","author":"Yu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.151"},{"key":"ref53","author":"Yu","year":"2021","journal-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning"},{"key":"ref54","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Tracevla: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","author":"Zheng","year":"2024","journal-title":"arXiv preprint"}],"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\/11443327.pdf?arnumber=11443327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:03Z","timestamp":1777611543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01225","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}