{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:36:42Z","timestamp":1757608602536,"version":"3.44.0"},"reference-count":73,"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\/icra55743.2025.11128293","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15595-15602","source":"Crossref","is-referenced-by-count":0,"title":["Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners"],"prefix":"10.1109","author":[{"given":"Wen Zheng Terence","family":"Ng","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianda","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Self-driving like a human driver instead of a robocac: Personalized comfortable driving experience for autonomous vehicles","author":"Bae","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104352"},{"key":"ref3","first-page":"16","article-title":"Personalized dynamics models for adaptive assistive navigation systems","volume-title":"Conference on Robot Learning","author":"OhnBar","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525832"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3277903"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref7","first-page":"420","article-title":"Preference learning in assistive robotics: Observational repeated inverse rein-forcement learning","volume-title":"Machine learning for healthcare conference","author":"Woodworth","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196105"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811553"},{"issue":"136","key":"ref11","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Ma-chine Learning Research"},{"key":"ref12","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"A bayesian approach for policy learning from trajectory preference queries","volume":"25","author":"Wilson","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.00920"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106886"},{"key":"ref18","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Transactions on Machine Learning Re-search"},{"key":"ref21","article-title":"An image is worth 16\u00d7 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"journal-title":"Abbas, Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments","article-title":"Leveraging optimal transport for enhanced offline reinforcement learning in sur-gical robotic environments","author":"Zare","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3351797"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref25","first-page":"6152","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and un-supervised pre-training","volume-title":"International Conference on Machine Learning","author":"Lee","year":"2021"},{"key":"ref26","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref28","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","year":"2022"},{"key":"ref30","first-page":"20132","article-title":"A minimalist approach to offline reinforce-ment learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Models of human preference for learning reward functions","author":"Knox","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"2014","article-title":"Few-shot preference learning for human-in-the-loop rl","volume-title":"Conference on Robot Learning","author":"Hejna","year":"2023"},{"key":"ref33","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"International Conference on Learning Representations","author":"Kim","year":"2023"},{"key":"ref35","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref37","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref39","article-title":"Classifier-free diffusion guidance","volume":"abs\/2207.12598","author":"Ho","year":"2022","journal-title":"ArXiv"},{"key":"ref40","first-page":"8780","article-title":"Diffusion models beat gans on image syn-thesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Is conditional generative modeling all you need for decision making?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ajay","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00832"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"issue":"2","key":"ref55","first-page":"3","article-title":"Hierarchi-cal text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1165"},{"key":"ref58","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref59","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019","journal-title":"arXiv preprint"},{"key":"ref60","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","article-title":"Is reinforcement learning (not) for natural language processing: Benchmarks, baselines, and building blocks for natural language policy optimization","author":"Ramamurthy","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref64","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"A general theoretical paradigm to understand learning from human preferences","author":"Azar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Kto: Model alignment as prospect theoretic optimization","author":"Ethayarajh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Contrastive preference optimization: Pushing the boundaries of 11m performance in machine translation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Slic-hf: Sequence likelihood calibration with human feedback","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"International Conference on Machine Learning"},{"key":"ref70","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref72","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume":"31","author":"Conti","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref73","article-title":"Quality-similar diversity via population based reinforcement learning","author":"Wu","year":"2022","journal-title":"Representations"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128293.pdf?arnumber=11128293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:07:16Z","timestamp":1756879636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128293","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}