{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:24Z","timestamp":1757608704816,"version":"3.44.0"},"reference-count":66,"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"}],"funder":[{"DOI":"10.13039\/100000006","name":"the Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-24-1-2036"],"award-info":[{"award-number":["N00014-24-1-2036"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2113401,IIS-2220876"],"award-info":[{"award-number":["IIS-2113401,IIS-2220876"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128192","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"10846-10853","source":"Crossref","is-referenced-by-count":0,"title":["Implicit Contact Diffuser: Sequential Contact Reasoning With Latent Point Cloud Diffusion"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Huang","sequence":"first","affiliation":[{"name":"University of Michigan,Ann Arbor"}]},{"given":"Yinong","family":"He","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor"}]},{"given":"Yating","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor"}]},{"given":"Dmitry","family":"Berenson","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560766"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3333699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981862"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.900639"},{"key":"ref6","first-page":"137","article-title":"Contact-invariant optimization for hand manipulation","volume-title":"Proceedings of the ACM SIGGRAPH\/Eurographics symposium on computer animation","author":"Mordatch"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"article-title":"Calamari: Contact-aware and language conditioned spatial action mapping for contact-rich manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Wi","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610189"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10001-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref14","article-title":"Equivact: Sim (3)-equivariant visuomotor policies beyond rigid object manipulation","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref16","first-page":"256","article-title":"Learning visible connectivity dynamics for cloth smoothing","volume-title":"Conference on Robot Learning. PMLR","author":"Lin"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160653"},{"key":"ref19","first-page":"835","article-title":"Se (3)-equivariant relational rearrangement with neural descriptor fields","volume-title":"Conference on Robot Learning. PMLR","author":"Simeonov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812097"},{"key":"ref22","article-title":"Virdo++: Real-world, visuo-tactile dynamics and perception of deformable objects","author":"Wi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"2052","article-title":"Learning the dynamics of compliant tool-environment interaction for visuo-tactile contact servoing","volume-title":"Conference on Robot Learning. PMLR","author":"Van der Merwe"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.080"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160526"},{"key":"ref26","article-title":"Act3d: Infinite resolution action detection transformer for robotic manipulation","author":"Gervet","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Conference on Robot Learning. PMLR","author":"Ha"},{"key":"ref28","first-page":"2012","article-title":"Playfusion: Skill acquisition via diffusion from language-annotated play","volume-title":"Conference on Robot Learning. PMLR","author":"Chen"},{"key":"ref29","article-title":"Waypointbased imitation learning for robotic manipulation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Conference on Robot Learning. PMLR","author":"Mishra"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3382529"},{"key":"ref32","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"arXiv preprint","author":"Janner","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref34","article-title":"Is conditional generative modeling all you need for decisionmaking?","author":"Ajay","year":"2022","journal-title":"arXiv preprint"},{"journal-title":"Hierarchical diffusion for offline decision making","year":"2023","author":"Li","key":"ref35"},{"key":"ref36","article-title":"Shelving, stacking, hanging: Relational pose diffusion for multi-modal rearrangement","author":"Simeonov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","article-title":"Robocook: Long-horizon elasto-plastic object manipulation with diverse tools","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Diffskill: Skill abstraction from differentiable physics for deformable object manipulations with tools","author":"Lin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Planning with spatial-temporal abstraction from point clouds for deformable object manipulation","author":"Lin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3308061"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3158377"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3353075"},{"key":"ref44","first-page":"5020","article-title":"Sub-goal trees a framework for goal-based reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Jurgenson"},{"key":"ref45","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","author":"Nair","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"key":"ref47","article-title":"Planning with goalconditioned policies","volume":"32","author":"Nasiriany","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Nod-tamp: Multi-step manipulation planning with neural object descriptors","author":"Cheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning. PMLR","author":"Sohl-Dickstein"},{"key":"ref50","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref51","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11). Citeseer","author":"Welling"},{"article-title":"Chaineddiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Xian","key":"ref52"},{"key":"ref53","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01198"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref56","first-page":"10021","article-title":"Lion: Latent point diffusion models for 3d shape generation","volume":"35","author":"Vahdat","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02413"},{"key":"ref60","article-title":"Inference via interpolation: Contrastive representations provably enable planning and inference","author":"Eysenbach","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","first-page":"35 603","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume":"35","author":"Eysenbach","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160765"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561012"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00331"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128192.pdf?arnumber=11128192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:46:41Z","timestamp":1756882001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128192","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}