{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:23:24Z","timestamp":1783736604389,"version":"3.55.0"},"reference-count":57,"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\/iros60139.2025.11247245","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11305-11312","source":"Crossref","is-referenced-by-count":2,"title":["DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model"],"prefix":"10.1109","author":[{"given":"Yang","family":"Jin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Lv","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref4","article-title":"End-to-end differentiable physics for learning and control","volume":"31","author":"de Avila Belbute-Peres","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00006"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref7","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Brax - a differentiable physics engine for large scale rigid body simulation","author":"Freeman","year":"2021"},{"key":"ref9","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref10","first-page":"11321","article-title":"Reinforcement learning from passive data via latent intentions","volume-title":"International Conference on Machine Learning","author":"Ghosh"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Dojo: A differentiable simulator for robotics","volume":"9","author":"Howell","year":"2022"},{"key":"ref17","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@ CoRL2023"},{"key":"ref18","article-title":"Diffvl: Scaling up soft body manipulation using vision-language driven differentiable physics","volume":"36","author":"Huang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"gradsim: Differentiable simulation for system identification and visuomotor control","volume-title":"International Conference on Learning Representations (ICLR)","author":"Jatavallabhula"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610566"},{"key":"ref21","article-title":"Differentiable rendering: A survey","author":"Kato","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","article-title":"Dexdeform: Dexterous deformable object manipulation with human demonstrations and differentiable physics","author":"Li","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275109"},{"key":"ref25","article-title":"Diffskill: Skill abstraction from differentiable physics for deformable object manipulations with tools","author":"Lin","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811859"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241284653"},{"key":"ref30","article-title":"Risp: Rendering-invariant state predictor with differentiable simulation and rendering for cross-domain parameter estimation","volume-title":"International Conference on Learning Representations","author":"Ma"},{"key":"ref31","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref32","first-page":"23301","article-title":"Liv: Language-image representations and rewards for robotic control","volume-title":"International Conference on Machine Learning","author":"Ma"},{"key":"ref33","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ma"},{"key":"ref34","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref35","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"},{"key":"ref36","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","author":"Mandlekar","year":"2023","journal-title":"Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@ CoRL2023"},{"key":"ref37","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref39","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole"},{"key":"ref40","article-title":"Scalable differentiable physics for learning and control","author":"Qiao","year":"2020"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref42","article-title":"Diffmimic: Efficient motion mimicking with differentiable physics","author":"Ren","year":"2023"},{"key":"ref43","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref45","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref46","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume":"36","author":"Sontakke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Gensim: Generating robotic simulation tasks via large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang"},{"key":"ref50","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.034"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610750"},{"key":"ref55","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3388769.3407454"},{"key":"ref57","article-title":"Diff-lfd: Contact-aware model-based learning from visual demonstration for robotic manipulation via differentiable physics-based simulation and rendering","volume-title":"Conference on Robot Learning (CoRL)","author":"Zhu"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11247245.pdf?arnumber=11247245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:48Z","timestamp":1765520148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247245","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}