{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:53:05Z","timestamp":1775065985525,"version":"3.50.1"},"reference-count":56,"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\/icra55743.2025.11127706","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"2838-2845","source":"Crossref","is-referenced-by-count":5,"title":["ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Abrar","family":"Anwar","sequence":"first","affiliation":[{"name":"NVIDIA"}]},{"given":"John","family":"Welsh","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Joydeep","family":"Biswas","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Soha","family":"Pouya","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Yan","family":"Chang","sequence":"additional","affiliation":[{"name":"NVIDIA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610216"},{"key":"ref3","author":"Chiang","year":"2024","journal-title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref6","article-title":"Neural Modular Control for Embodied Question Answering","volume-title":"Conference on Robot Learning (CoRL)","author":"Das","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.089"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1197"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref12","article-title":"Vision-and-Dialog Navigation","volume-title":"Conference on Robot Learning (CoRL)","author":"Thomason","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref16","article-title":"Object Goal Navigation Using Goal-Oriented Semantic Exploration","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Chaplot","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref18","article-title":"ZSON: Zero-Shot Object-Goal Navigation Using Multimodal Goal Embeddings","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Majumdar","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref20","article-title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","volume-title":"Conference on Robot Learning (CoRL)","author":"Shah","year":"2022"},{"key":"ref21","article-title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","volume-title":"Conference on Robot Learning (CoRL)","author":"Shah","year":"2023"},{"key":"ref22","article-title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-andLanguage Navigation","volume-title":"Workshop on Language and Robot Learning (LangRob) @ CoRL","author":"Dorbala","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref24","article-title":"Embodied Semantic Scene Graph Generation","volume-title":"Conference on Robot Learning (CoRL)","author":"Li","year":"2022"},{"key":"ref25","article-title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Eysenbach","year":"2019"},{"key":"ref26","article-title":"Semi-Parametric Topological Memory for Navigation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Savinov","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00063"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref29","author":"Touvron","year":"2023","journal-title":"Llama: Open and Efficient Foundation Language Models"},{"key":"ref30","author":"Achiam","year":"2023","journal-title":"GPT-4 Technical Report"},{"key":"ref31","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Wei","year":"2022"},{"key":"ref32","article-title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Yao","year":"2023"},{"key":"ref33","author":"Zhou","year":"2022","journal-title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models"},{"key":"ref34","author":"Gao","year":"2023","journal-title":"Retrieval-Augmented Generation for Large Language Models: A Survey"},{"key":"ref35","author":"Asai","year":"2023","journal-title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection"},{"key":"ref36","article-title":"Reflexion: Language Agents with Verbal Reinforcement Learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Shinn","year":"2023"},{"key":"ref37","author":"Yao","year":"2022","journal-title":"React: Synergizing Reasoning and Acting in Language Models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref39","article-title":"Toolformer: Language Models Can Teach Themselves to Use Tools","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Schick","year":"2023"},{"key":"ref40","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan","year":"2023"},{"key":"ref41","article-title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2022"},{"key":"ref42","author":"Singh","year":"2024","journal-title":"TwoStep: Multi-agent task planning using classical planners and large language models"},{"key":"ref43","author":"Liu","year":"2023","journal-title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3360020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref48","volume-title":"Open source strikes bread - new fluffy embeddings model","author":"Lee","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tro.2024.3400831"},{"key":"ref50","volume-title":"Husky UGV - Outdoor Field Research Robot","author":"Robotics","year":"2024"},{"key":"ref51","volume-title":"Codestral model card","author":"Mistral","year":"2024"},{"key":"ref52","volume-title":"Command-r model card","year":"2024"},{"key":"ref53","author":"Dubey","year":"2024","journal-title":"The Llama 3 Herd of Models"},{"key":"ref54","volume-title":"Nova Carter - Complete Robotics Development Platform","author":"Robotics","year":"2024"},{"key":"ref55","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2023"},{"key":"ref56","volume-title":"NVIDIA NIM","year":"2024"}],"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\/11127706.pdf?arnumber=11127706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:42Z","timestamp":1756879542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127706","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}