{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:21:36Z","timestamp":1780579296533,"version":"3.54.1"},"reference-count":85,"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\/iccv51701.2025.00721","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7686-7697","source":"Crossref","is-referenced-by-count":2,"title":["Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy"],"prefix":"10.1109","author":[{"given":"Zhi","family":"Hou","sequence":"first","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwen","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Duan","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengjun","family":"Pu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,MMLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronglei","family":"Tong","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntao","family":"Chen","sequence":"additional","affiliation":[{"name":"HKISI,CAS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref2","article-title":"Paligemma: A versatile 3 b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref4","article-title":"Zero-shot robotic manipulation with pretrained imageediting diffusion models","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"pio: A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2244"},{"key":"ref7","article-title":"Robocat: A selfimproving foundation agent for robotic manipulation","author":"Bousmalis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref9","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref11","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref12","article-title":"Mamba policy: Towards efficient 3d diffusion policy with hybrid selective state models","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref15","first-page":"2012","article-title":"Playfusion: Skill acquisition via diffusion from language-annotated play","volume-title":"Conference on Robot Learning","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref18","article-title":"The ingredients for robotic diffusion transformers","author":"Dasari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"8780","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref20","article-title":"Palme: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Rh20t: A robotic dataset for learning diverse skills in one-shot","volume-title":"RSS 2023 Workshop on Learning for Task and Motion Planning","author":"Fang","year":"2023"},{"key":"ref22","article-title":"Maniskill2: A unified benchmark for generalizable manipulation skills","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"In Conference on Robot Learning","author":"Ha"},{"key":"ref24","article-title":"Ghil-glue: Hierarchical control with filtered subgoal images","author":"Kyle","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Enerverse: Envisioning embodied future space for robotics manipulation","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref30","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","author":"Ke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref32","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3526436"},{"key":"ref35","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Evaluating real-world robot manipulation policies in simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Towards generalist robot policies: What matters in building vision-language-action models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref41","author":"Liu","year":"2023","journal-title":"Visual instruction tuning"},{"key":"ref42","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"key":"ref45","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref48","article-title":"Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations","author":"Mu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref49","first-page":"3894","article-title":"Goal representations for instruction following: A\\\\ semi-supervised language interface to control","volume-title":"Conference on Robot Learning","author":"Myers"},{"key":"ref50","article-title":"Dall\u2022e: Creating images from text","year":"2021","journal-title":"OpenAI"},{"key":"ref51","article-title":"Chatgpt","year":"2022","journal-title":"OpenAI"},{"key":"ref52","article-title":"Gpt-4: Multimodal capabilities","year":"2023","journal-title":"OpenAI"},{"key":"ref53","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Open xembodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.028"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3382529"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref66","article-title":"Vint: A foundation model for visual navigation","author":"Shah","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Mutex: Learning unified policies from multimodal task specifications","author":"Shah","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","first-page":"785","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref69","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/960124.806879"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref72","article-title":"Octo: An open-source generalist robot policy","author":"Model Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Predictive inverse dynamics models are scalable learners for robotic manipulation","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Sparse diffusion policy: A sparse, reusable, and flexible policy for robot learning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"One-step diffusion policy: Fast visuomotor policies via diffusion distillation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Diffusion-vla: Scaling robot foundation models via unified diffusion and autoregression","author":"Wen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Dexvla: Vision-language model with plug-in diffusion expert for general robot control","author":"Wen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"Unleashing large-scale video generative pretraining for visual robot manipulation","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","first-page":"5","article-title":"Unifying diffusion models with action detection transformers for multi-task robotic manipulation","volume-title":"In 7th Annual Conference on Robot Learning","author":"Xian"},{"key":"ref80","article-title":"Robotic skill acquisition via instruction augmentation with vision-language models","author":"Xiao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.093"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref84","article-title":"Language control diffusion: Efficiently scaling through space, time, and tasks","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"}],"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\/11444129.pdf?arnumber=11444129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:36:33Z","timestamp":1777530993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00721","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}