{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:36:05Z","timestamp":1784644565841,"version":"3.55.0"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127315","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8996-9002","source":"Crossref","is-referenced-by-count":9,"title":["Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-Guided 3D Policy"],"prefix":"10.1109","author":[{"given":"Ricardo","family":"Garcia","sequence":"first","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref2","article-title":"PolarNet: 3D point clouds for language-guided robotic manipulation","author":"Chen","year":"2023","journal-title":"CoRL"},{"key":"ref3","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"CoRL"},{"key":"ref4","article-title":"Act3D: 3D feature field transformers for multi-task robotic manipulation","author":"Gervet","year":"2023","journal-title":"CoRL"},{"key":"ref5","article-title":"R3M: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"CoRL"},{"key":"ref6","article-title":"Real-world robot learning with masked visual pre-training","author":"Radosavovic","year":"2023","journal-title":"CoRL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.032"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01709"},{"key":"ref9","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"CoRL"},{"key":"ref10","article-title":"PALM-E: An embodied multimodallanguage model","author":"Driess","year":"2023","journal-title":"ICML"},{"key":"ref11","author":"Team","year":"2024","journal-title":"Octo: An open-source generalist robot policy"},{"key":"ref12","article-title":"OpenVLA: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"CoRL"},{"key":"ref13","article-title":"Open X-Embodiment: Robotic learning datasets and RT- X models","author":"Vuong","year":"2023","journal-title":"CoRL"},{"key":"ref14","year":"2024","journal-title":"Llama 3 model card"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref17","article-title":"Instruction-driven history-aware policies for robotic ma-nipulations","author":"Guhur","year":"2023","journal-title":"CoRL"},{"key":"ref18","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","author":"Shridhar","year":"2023","journal-title":"CoRL"},{"key":"ref19","article-title":"VLMbench: A compositional benchmark for vision-and-language manipulation","author":"Zheng","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref22","article-title":"Transporter networks: Rearranging the visual world for robotic ma-nipulation","author":"Zeng","year":"2020","journal-title":"CoRL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01873"},{"key":"ref24","article-title":"VIMA: robot manipulation with multimodal prompts","author":"Jiang","year":"2023","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.133"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref27","article-title":"AI2-Thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv:1712.05474"},{"key":"ref28","article-title":"Isaac Gym: High performance gpu based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref29","article-title":"Con-cept2Robot: Learning manipulation concepts from instructions and human demonstrations","author":"Shao","year":"2021","journal-title":"IJRR"},{"key":"ref30","article-title":"Interactive language: Talking to robots in real time","author":"Lynch","year":"2023","journal-title":"IEEE RA - L"},{"key":"ref31","article-title":"Language-conditioned imitation learning for robot manipulation tasks","author":"Stepputtis","year":"2020","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018","journal-title":"CoRL"},{"key":"ref33","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2022","journal-title":"CoRL"},{"key":"ref34","article-title":"RVT: Robotic view transformer for 3D object manipulation","author":"Goyal","year":"2023","journal-title":"CoRL"},{"key":"ref35","article-title":"3D Diffuser Actor: Policy diffusion with 3D scene representations","author":"Ke","year":"2024","journal-title":"CoRL"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.055","article-title":"RVT2: Learning precise manipulation from few demonstrations","author":"Goyal","year":"2024","journal-title":"RSS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"I CML"},{"key":"ref40","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2023","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref42","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv:2302.11550"},{"key":"ref43","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022","journal-title":"ICML"},{"key":"ref44","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Brohan","year":"2023","journal-title":"CoRL"},{"key":"ref45","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023","journal-title":"arXiv:2311.17842"},{"key":"ref46","article-title":"GPT-4V(ision) system card","author":"OpenAI","year":"2023","journal-title":"preprint"},{"key":"ref47","article-title":"Auto-Lambda: Disentangling dynamic task relationships","author":"Liu","year":"2022","journal-title":"TMLR"},{"key":"ref48","article-title":"Open3D: A modern library for 3D data processing","author":"Zhou","year":"2018","journal-title":"arXiv:1801.09847"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00525"},{"key":"ref52","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11127315.pdf?arnumber=11127315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:46Z","timestamp":1756880266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127315","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}