{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:16Z","timestamp":1766061676059,"version":"3.48.0"},"reference-count":37,"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\/iros60139.2025.11247239","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"6235-6242","source":"Crossref","is-referenced-by-count":0,"title":["STACKGEN: Generating Stable Structures from Silhouettes via Diffusion"],"prefix":"10.1109","author":[{"given":"Luzhe","family":"Sun","sequence":"first","affiliation":[{"name":"Toyota Technological Institute at Chicago (TTIC),Chicago,IL,USA"}]},{"given":"Takuma","family":"Yoneda","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago (TTIC),Chicago,IL,USA"}]},{"given":"Samuel W.","family":"Wheeler","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory,Lemont,IL,USA"}]},{"given":"Tianchong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago (TTIC),Chicago,IL,USA"}]},{"given":"Matthew R.","family":"Walter","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago (TTIC),Chicago,IL,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1306572110"},{"article-title":"To fall or not to fall: A visual approach to physical stability prediction","year":"2016","author":"Li","key":"ref2"},{"article-title":"Learning physical intuition of block towers by example","volume-title":"Proc. Int\u2019l Conf. on Machine Learning (ICML)","author":"Lerer","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2016.08.012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385617"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau8479"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRoM.2015.7367821"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abp9758"},{"key":"ref10","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int\u2019l Conf. on Machine Learning (ICML)","author":"Nichol","key":"ref12"},{"article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int\u2019l Conf. on Machine Learning (ICML)","author":"Ramesh","key":"ref13"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref14"},{"article-title":"Reasoning about physical interactions with object-oriented prediction and planning","volume-title":"Proc. Int\u2019l Conf. on Learning Representations (ICLR)","author":"Janner","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_43"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-022-01394-8"},{"key":"ref22","article-title":"Modeling expectation violation in intuitive physics with coarse probabilistic object representations","author":"Smith","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"IntPhys: A framework and benchmark for visual intuitive physics reasoning","year":"2018","author":"Riochet","key":"ref23"},{"article-title":"Probing physics knowledge using tools from developmental psychology","year":"2018","author":"Piloto","key":"ref24"},{"article-title":"Learning to poke by poking: Experiential learning of intuitive physics","year":"2016","author":"Agrawal","key":"ref25"},{"key":"ref26","article-title":"Unsupervised learning for physical interaction through video prediction","author":"Finn","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref28","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"article-title":"Shelving, stacking, hanging: Relational pose diffusion for multi-modal rearrangement","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Simeonov","key":"ref30"},{"article-title":"6-DoF stability field via diffusion models","year":"2023","author":"Yoneda","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611595"},{"article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int\u2019l Conf. on Machine Learning (ICML)","author":"Sohl-Dickstein","key":"ref35"},{"key":"ref36","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int\u2019l Conf. on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref37"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247239.pdf?arnumber=11247239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:59Z","timestamp":1766061479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247239","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}