{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:53:34Z","timestamp":1791478414125,"version":"4.3.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSERC Canada Graduate Research Scholarship - Doctoral"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/lra.2026.3726383","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T19:11:23Z","timestamp":1787339483000},"page":"11785-11792","source":"Crossref","is-referenced-by-count":3,"title":["CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2747-2131","authenticated-orcid":false,"given":"Catherine","family":"Glossop","sequence":"first","affiliation":[{"name":"University of California","place":["Berkeley, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9193-9197","authenticated-orcid":false,"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California","place":["Berkeley, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Bhorkar","sequence":"additional","affiliation":[{"name":"University of California","place":["Berkeley, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7541-3278","authenticated-orcid":false,"given":"Dhruv","family":"Shah","sequence":"additional","affiliation":[{"name":"Princeton University","place":["Princeton, NJ, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-2743","authenticated-orcid":false,"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[{"name":"University of California","place":["Berkeley, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Improving image generation with better captions","author":"Betker","year":"2023","journal-title":"OpenAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref3","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Brohan","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref5","article-title":"Lagging inference networks and posterior collapse in variational autoencoders","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"He","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"key":"ref7","article-title":"PaliGemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024"},{"key":"ref8","first-page":"711","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Shah","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196644"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2925731"},{"key":"ref13","first-page":"33431","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Black","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref16","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref19","first-page":"23171","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Gadre","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref23","first-page":"2679","article-title":"Openvla: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Kim","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"ref25","first-page":"3866","article-title":"Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Xu","year":"2024"},{"key":"ref26","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Huang","year":"2023"},{"key":"ref27","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Nasiriany","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802716"},{"key":"ref30","first-page":"2683","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"ref32","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref33","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024"},{"key":"ref34","first-page":"666","article-title":"LeLaN: Learning a language-conditioned navigation policy from in-the-wild video","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Hirose","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127404"},{"key":"ref36","first-page":"4158","article-title":"Scaling robot policy learning via zero-shot labeling with foundation models","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Blank","year":"2024"},{"key":"ref37","first-page":"302","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Zhang","year":"2023"},{"key":"ref38","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2023"},{"key":"ref39","article-title":"CHOP: Counterfactual human preference labels improve obstacle avoidance in visuomotor navigation policies","author":"Seneviratne","year":"2026"},{"key":"ref40","article-title":"CoINS: Counterfactual interactive navigation via skill-aware VLM","author":"Zhou","year":"2026"},{"key":"ref41","first-page":"4022","article-title":"Counterfactual VLA: Self-reflective vision-language-action model with adaptive reasoning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Peng","year":"2026"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/160"},{"key":"ref43","article-title":"GigaWorld-0: World models as data engine to empower embodied AI","author":"Team","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref47","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Team","year":"2025"},{"key":"ref48","first-page":"1723","article-title":"Bridgedata V2: A dataset for robot learning at scale","volume-title":"Proc. Conf. Robot Learn.","author":"Walke","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2026.XXII.074"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"ref51","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot.: Sci. Syst.","author":"Model","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11656882\/11663071.pdf?arnumber=11663071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:51:16Z","timestamp":1788843076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11663071\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":51,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3726383","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}