{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:49:41Z","timestamp":1778258981970,"version":"3.51.4"},"reference-count":66,"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\/iccv51701.2025.01037","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11142-11152","source":"Crossref","is-referenced-by-count":1,"title":["VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks"],"prefix":"10.1109","author":[{"given":"Shiduo","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiju","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghui","family":"Gao","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoye","family":"Fei","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhangyue","family":"Yin","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xipeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref10","article-title":"Training verifiers to solve math word problems","volume":"28","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","volume-title":"OpenCompass Contributors. Opencompass: A universal evaluation platform for foundation models","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Palme: An embodied multi-modal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231193710"},{"key":"ref18","article-title":"A taxonomy for evaluating generalist robot policies","volume":"10","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"GLM","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01873"},{"key":"ref21","article-title":"Maniskill2: A unified benchmark for generalizable manipulation skills","volume-title":"International Conference on Learning Representations","author":"Gu"},{"key":"ref22","article-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Look before you leap: Unveiling the power of gpt4v in robotic vision-language planning","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref25","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980479"},{"key":"ref30","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","first-page":"80","article-title":"Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation","volume-title":"Conference on Robot Learning","author":"Li"},{"key":"ref33","article-title":"Embodied agent interface: Benchmarking $l l ~\\text{ms}$ for embodied decision making","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Evaluating real-world robot manipulation policies in simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref37","article-title":"Data scaling laws in imitation learning for robotic manipulation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref39","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","volume-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA 2024","author":"Liu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref41","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref42","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","author":"Mandlekar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref46","article-title":"Maniskill: Generalizable manipulation skill benchmark with large-scale demonstrations","author":"Mu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.050"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11900-7_17"},{"key":"ref49","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Open xembodiment: Robotic learning datasets and $\\text{rt}-\\mathrm{x}$ models","author":"Padalkar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1502-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2019.8768625"},{"key":"ref55","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume":"34","author":"Szot","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref56","article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","author":"Tao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref60","first-page":"1723","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning","author":"Walke"},{"key":"ref61","article-title":"Emergent abilities of large language models","volume-title":"Transactions on Machine Learning Research","author":"Wei","year":"2022"},{"key":"ref62","article-title":"Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation","author":"Wen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Homerobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","volume-title":"obj2mjcf: Cli for processing composite wavefront obj files for use in mujoco","author":"Zakka","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref66","article-title":"Robocas: A benchmark for robotic manipulation in complex object arrangement scenarios","author":"Zheng","year":"2024","journal-title":"arXiv preprint"}],"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\/11444456.pdf?arnumber=11444456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:45Z","timestamp":1777612365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01037","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}