{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T23:37:45Z","timestamp":1785800265035,"version":"3.56.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Kempner Institute at Harvard University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/lra.2026.3664611","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:51:31Z","timestamp":1771015891000},"page":"4697-4704","source":"Crossref","is-referenced-by-count":1,"title":["Flexible Multitask Learning With Factorized Diffusion Policy"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1486-5852","authenticated-orcid":false,"given":"Chaoqi","family":"Liu","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Chen","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8532-5631","authenticated-orcid":false,"given":"Sigmund H.","family":"H\u00f8eg","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology, Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoxiong","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1111-2150","authenticated-orcid":false,"given":"Yunzhu","family":"Li","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5207-1527","authenticated-orcid":false,"given":"Kris","family":"Hauser","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilun","family":"Du","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3664616\/mm1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127387"},{"key":"ref5","article-title":"Multi-modal manipulation via multi-modal policy consensus","author":"Chen","year":"2025"},{"key":"ref6","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Ha","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341196"},{"key":"ref8","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"},{"key":"ref9","article-title":"MoMa: Efficient early-fusion pre-training with mixture of modality-aware experts","author":"Lin","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref11","first-page":"649","article-title":"Sparse diffusion policy: A sparse, reusable, and flexible policy for robot learning","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Wang","year":"2025"},{"key":"ref12","article-title":"Efficient diffusion transformer policies with mixture of expert denoisers for multitask learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reuss","year":"2025"},{"key":"ref13","first-page":"8489","article-title":"Reduce, reuse, recycle: Compositional generation with energy-based diffusion models and MCMC","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Du","year":"2023"},{"key":"ref14","first-page":"11721","article-title":"Compositional generative modeling: A single model is not all you need","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Du","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref16","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Yu","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref19","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref20","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref21","article-title":"Video diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2022"},{"key":"ref22","article-title":"Learning real-world action-video dynamics with heterogeneous masked autoregression","author":"Wang","year":"2025"},{"key":"ref23","article-title":"Learning universal policies via text-guided video generation","author":"Du","year":"2023"},{"key":"ref24","article-title":"Compositional foundation models for hierarchical planning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ajay","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref26","first-page":"2695","article-title":"Tool-as-interface: Learning robot policies from observing human tool use","volume-title":"Proc. Conf. Robot Learn.","volume":"305","author":"Chen","year":"2025"},{"key":"ref27","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Janner","year":"2022"},{"key":"ref28","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342382"},{"key":"ref30","article-title":"OpenVLA: An open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"ref31","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot.: Sci. Syst.","author":"Team","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2017.7989250"},{"key":"ref34","article-title":"Modular multitask reinforcement learning with policy sketches","author":"Andreas","year":"2017"},{"key":"ref35","article-title":"Variational distillation of diffusion policies into mixture of experts","author":"Zhou","year":"2024"},{"key":"ref36","first-page":"3242","article-title":"Compositional diffusion-based continuous constraint solvers","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Yang","year":"2023"},{"key":"ref37","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Welling","year":"2011"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref39","first-page":"3585","article-title":"Implicit generation and modeling with energy based models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Du","year":"2019"},{"key":"ref40","first-page":"46823","article-title":"Compositional image decomposition with diffusion models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Su","year":"2024"},{"key":"ref41","article-title":"LIBERO: Benchmarking knowledge transfer for lifelong robot learning","author":"Liu","year":"2023"},{"key":"ref42","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00199"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_15"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11400564\/11395999.pdf?arnumber=11395999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:21:44Z","timestamp":1772518904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":45,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3664611","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}