{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:48Z","timestamp":1774419648668,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887717","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Interactive Robot Action Replanning using Multimodal LLM Trained from Human Demonstration Videos"],"prefix":"10.1109","author":[{"given":"Chiori","family":"Hori","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Motonari","family":"Kambara","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[{"name":"Keio University,Tokyo,Japan"}]},{"given":"Kei","family":"Ota","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Sameer","family":"Khurana","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Siddarth","family":"Jain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Radu","family":"Corcodel","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Devesh","family":"Jha","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Diego","family":"Romeres","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1983"},{"key":"ref2","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref3","article-title":"Human action understanding-based robot planning using multimodal LLM","volume-title":"Proc. ICRA Workshop for \"Cooking Robotics: Perception and motion planning\""},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2882140"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2172420"},{"key":"ref7","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. CoRL","author":"Shridhar"},{"key":"ref8","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610981"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10133-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3410155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SII58957.2024.10417267"},{"key":"ref14","article-title":"Planning with large language models via corrective re-prompting","volume-title":"NeurIPS Foundation Models for Decision Making Workshop","author":"Raman"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","article-title":"OPT: Open Pre-trained Transformer Language Models","author":"Zhang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref21","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460857"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561308"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887717.pdf?arnumber=10887717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:56Z","timestamp":1774416236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887717","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}