default search action
BibTeX records: Anikait Singh
@inproceedings{DBLP:conf/cvpr/DangSZES25,
author = {Meihua Dang and
Anikait Singh and
Linqi Zhou and
Stefano Ermon and
Jiaming Song},
title = {Personalized Preference Fine-tuning of Diffusion Models},
booktitle = {{IEEE/CVF} Conference on Computer Vision and Pattern Recognition,
{CVPR} 2025, Nashville, TN, USA, June 11-15, 2025},
pages = {8020--8030},
publisher = {Computer Vision Foundation / {IEEE}},
year = {2025},
url = {https://openaccess.thecvf.com/content/CVPR2025/html/Dang\_Personalized\_Preference\_Fine-tuning\_of\_Diffusion\_Models\_CVPR\_2025\_paper.html},
doi = {10.1109/CVPR52734.2025.00751},
timestamp = {Wed, 20 Aug 2025 10:18:56 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/DangSZES25.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2501-04682,
author = {Violet Xiang and
Charlie Snell and
Kanishk Gandhi and
Alon Albalak and
Anikait Singh and
Chase Blagden and
Duy Phung and
Rafael Rafailov and
Nathan Lile and
Dakota Mahan and
Louis Castricato and
Jan{-}Philipp Fr{\"{a}}nken and
Nick Haber and
Chelsea Finn},
title = {Towards System 2 Reasoning in LLMs: Learning How to Think With Meta
Chain-of-Thought},
journal = {CoRR},
volume = {abs/2501.04682},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2501.04682},
doi = {10.48550/ARXIV.2501.04682},
eprinttype = {arXiv},
eprint = {2501.04682},
timestamp = {Tue, 18 Feb 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2501-04682.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2501-06655,
author = {Meihua Dang and
Anikait Singh and
Linqi Zhou and
Stefano Ermon and
Jiaming Song},
title = {Personalized Preference Fine-tuning of Diffusion Models},
journal = {CoRR},
volume = {abs/2501.06655},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2501.06655},
doi = {10.48550/ARXIV.2501.06655},
eprinttype = {arXiv},
eprint = {2501.06655},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2501-06655.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2502-17387,
author = {Alon Albalak and
Duy Phung and
Nathan Lile and
Rafael Rafailov and
Kanishk Gandhi and
Louis Castricato and
Anikait Singh and
Chase Blagden and
Violet Xiang and
Dakota Mahan and
Nick Haber},
title = {Big-Math: {A} Large-Scale, High-Quality Math Dataset for Reinforcement
Learning in Language Models},
journal = {CoRR},
volume = {abs/2502.17387},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2502.17387},
doi = {10.48550/ARXIV.2502.17387},
eprinttype = {arXiv},
eprint = {2502.17387},
timestamp = {Fri, 21 Mar 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2502-17387.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2502-19312,
author = {Anikait Singh and
Sheryl Hsu and
Kyle Hsu and
Eric Mitchell and
Stefano Ermon and
Tatsunori Hashimoto and
Archit Sharma and
Chelsea Finn},
title = {{FSPO:} Few-Shot Preference Optimization of Synthetic Preference Data
in LLMs Elicits Effective Personalization to Real Users},
journal = {CoRR},
volume = {abs/2502.19312},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2502.19312},
doi = {10.48550/ARXIV.2502.19312},
eprinttype = {arXiv},
eprint = {2502.19312},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2502-19312.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2503-01307,
author = {Kanishk Gandhi and
Ayush Chakravarthy and
Anikait Singh and
Nathan Lile and
Noah D. Goodman},
title = {Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four
Habits of Highly Effective STaRs},
journal = {CoRR},
volume = {abs/2503.01307},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2503.01307},
doi = {10.48550/ARXIV.2503.01307},
eprinttype = {arXiv},
eprint = {2503.01307},
timestamp = {Tue, 08 Apr 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2503-01307.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2510-02263,
author = {Yuxiao Qu and
Anikait Singh and
Yoonho Lee and
Amrith Setlur and
Ruslan Salakhutdinov and
Chelsea Finn and
Aviral Kumar},
title = {{RLAD:} Training LLMs to Discover Abstractions for Solving Reasoning
Problems},
journal = {CoRR},
volume = {abs/2510.02263},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2510.02263},
doi = {10.48550/ARXIV.2510.02263},
eprinttype = {arXiv},
eprint = {2510.02263},
timestamp = {Sun, 09 Nov 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2510-02263.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2510-07307,
author = {Rushi Qiang and
Yuchen Zhuang and
Anikait Singh and
Percy Liang and
Chao Zhang and
Sherry Yang and
Bo Dai},
title = {MLE-Smith: Scaling {MLE} Tasks with Automated Multi-Agent Pipeline},
journal = {CoRR},
volume = {abs/2510.07307},
year = {2025},
url = {https://doi.org/10.48550/arXiv.2510.07307},
doi = {10.48550/ARXIV.2510.07307},
eprinttype = {arXiv},
eprint = {2510.07307},
timestamp = {Tue, 11 Nov 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2510-07307.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:conf/rlc/RafailovHSKSKHK24,
author = {Rafael Rafailov and
Kyle Beltran Hatch and
Anikait Singh and
Aviral Kumar and
Laura Smith and
Ilya Kostrikov and
Philippe Hansen{-}Estruch and
Victor Kolev and
Philip J. Ball and
Jiajun Wu and
Sergey Levine and
Chelsea Finn},
title = {{D5RL:} Diverse Datasets for Data-Driven Deep Reinforcement Learning},
journal = {{RLJ}},
volume = {5},
pages = {2178--2197},
year = {2024},
url = {https://rlj.cs.umass.edu/2024/papers/Paper305.html},
timestamp = {Fri, 10 Oct 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/rlc/RafailovHSKSKHK24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TajwarSSR0XEFK24,
author = {Fahim Tajwar and
Anikait Singh and
Archit Sharma and
Rafael Rafailov and
Jeff Schneider and
Tengyang Xie and
Stefano Ermon and
Chelsea Finn and
Aviral Kumar},
title = {Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy
Data},
booktitle = {Forty-first International Conference on Machine Learning, {ICML} 2024,
Vienna, Austria, July 21-27, 2024},
publisher = {OpenReview.net},
year = {2024},
url = {https://openreview.net/forum?id=bWNPx6t0sF},
timestamp = {Mon, 02 Sep 2024 16:45:29 +0200},
biburl = {https://dblp.org/rec/conf/icml/TajwarSSR0XEFK24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/ONeillRMGPLPGMJ24,
author = {Abby O'Neill and
Abdul Rehman and
Abhiram Maddukuri and
Abhishek Gupta and
Abhishek Padalkar and
Abraham Lee and
Acorn Pooley and
Agrim Gupta and
Ajay Mandlekar and
Ajinkya Jain and
Albert Tung and
Alex Bewley and
Alexander Herzog and
Alex Irpan and
Alexander Khazatsky and
Anant Rai and
Anchit Gupta and
Andrew E. Wang and
Anikait Singh and
Animesh Garg and
Aniruddha Kembhavi and
Annie Xie and
Anthony Brohan and
Antonin Raffin and
Archit Sharma and
Arefeh Yavary and
Arhan Jain and
Ashwin Balakrishna and
Ayzaan Wahid and
Ben Burgess{-}Limerick and
Beomjoon Kim and
Bernhard Sch{\"{o}}lkopf and
Blake Wulfe and
Brian Ichter and
Cewu Lu and
Charles Xu and
Charlotte Le and
Chelsea Finn and
Chen Wang and
Chenfeng Xu and
Cheng Chi and
Chenguang Huang and
Christine Chan and
Christopher Agia and
Chuer Pan and
Chuyuan Fu and
Coline Devin and
Danfei Xu and
Daniel Morton and
Danny Driess and
Daphne Chen and
Deepak Pathak and
Dhruv Shah and
Dieter B{\"{u}}chler and
Dinesh Jayaraman and
Dmitry Kalashnikov and
Dorsa Sadigh and
Edward Johns and
Ethan Paul Foster and
Fangchen Liu and
Federico Ceola and
Fei Xia and
Feiyu Zhao and
Freek Stulp and
Gaoyue Zhou and
Gaurav S. Sukhatme and
Gautam Salhotra and
Ge Yan and
Gilbert Feng and
Giulio Schiavi and
Glen Berseth and
Gregory Kahn and
Guanzhi Wang and
Hao Su and
Haoshu Fang and
Haochen Shi and
Henghui Bao and
Heni Ben Amor and
Henrik I. Christensen and
Hiroki Furuta and
Homer Walke and
Hongjie Fang and
Huy Ha and
Igor Mordatch and
Ilija Radosavovic and
Isabel Leal and
Jacky Liang and
Jad Abou{-}Chakra and
Jaehyung Kim and
Jaimyn Drake and
Jan Peters and
Jan Schneider and
Jasmine Hsu and
Jeannette Bohg and
Jeffrey T. Bingham and
Jeffrey Wu and
Jensen Gao and
Jiaheng Hu and
Jiajun Wu and
Jialin Wu and
Jiankai Sun and
Jianlan Luo and
Jiayuan Gu and
Jie Tan and
Jihoon Oh and
Jimmy Wu and
Jingpei Lu and
Jingyun Yang and
Jitendra Malik and
Jo{\~{a}}o Silv{\'{e}}rio and
Joey Hejna and
Jonathan Booher and
Jonathan Tompson and
Jonathan Yang and
Jordi Salvador and
Joseph J. Lim and
Junhyek Han and
Kaiyuan Wang and
Kanishka Rao and
Karl Pertsch and
Karol Hausman and
Keegan Go and
Keerthana Gopalakrishnan and
Ken Goldberg and
Kendra Byrne and
Kenneth Oslund and
Kento Kawaharazuka and
Kevin Black and
Kevin Lin and
Kevin Zhang and
Kiana Ehsani and
Kiran Lekkala and
Kirsty Ellis and
Krishan Rana and
Krishnan Srinivasan and
Kuan Fang and
Kunal Pratap Singh and
Kuo{-}Hao Zeng and
Kyle Hatch and
Kyle Hsu and
Laurent Itti and
Lawrence Yunliang Chen and
Lerrel Pinto and
Li Fei{-}Fei and
Liam Tan and
Linxi Jim Fan and
Lionel Ott and
Lisa Lee and
Luca Weihs and
Magnum Chen and
Marion Lepert and
Marius Memmel and
Masayoshi Tomizuka and
Masha Itkina and
Mateo Guaman Castro and
Max Spero and
Maximilian Du and
Michael Ahn and
Michael C. Yip and
Mingtong Zhang and
Mingyu Ding and
Minho Heo and
Mohan Kumar Srirama and
Mohit Sharma and
Moo Jin Kim and
Naoaki Kanazawa and
Nicklas Hansen and
Nicolas Heess and
Nikhil J. Joshi and
Niko S{\"{u}}nderhauf and
Ning Liu and
Norman Di Palo and
Nur Muhammad (Mahi) Shafiullah and
Oier Mees and
Oliver Kroemer and
Osbert Bastani and
Pannag R. Sanketi and
Patrick Tree Miller and
Patrick Yin and
Paul Wohlhart and
Peng Xu and
Peter David Fagan and
Peter Mitrano and
Pierre Sermanet and
Pieter Abbeel and
Priya Sundaresan and
Qiuyu Chen and
Quan Vuong and
Rafael Rafailov and
Ran Tian and
Ria Doshi and
Roberto Mart{\'{\i}}n{-}Mart{\'{\i}}n and
Rohan Baijal and
Rosario Scalise and
Rose Hendrix and
Roy Lin and
Runjia Qian and
Ruohan Zhang and
Russell Mendonca and
Rutav Shah and
Ryan Hoque and
Ryan Julian and
Samuel Bustamante{-}Gomez and
Sean Kirmani and
Sergey Levine and
Shan Lin and
Sherry Moore and
Shikhar Bahl and
Shivin Dass and
Shubham D. Sonawani and
Shuran Song and
Sichun Xu and
Siddhant Haldar and
Siddharth Karamcheti and
Simeon Adebola and
Simon Guist and
Soroush Nasiriany and
Stefan Schaal and
Stefan Welker and
Stephen Tian and
Subramanian Ramamoorthy and
Sudeep Dasari and
Suneel Belkhale and
Sungjae Park and
Suraj Nair and
Suvir Mirchandani and
Takayuki Osa and
Tanmay Gupta and
Tatsuya Harada and
Tatsuya Matsushima and
Ted Xiao and
Thomas Kollar and
Tianhe Yu and
Tianli Ding and
Todor Davchev and
Tony Z. Zhao and
Travis Armstrong and
Trevor Darrell and
Trinity Chung and
Vidhi Jain and
Vincent Vanhoucke and
Wei Zhan and
Wenxuan Zhou and
Wolfram Burgard and
Xi Chen and
Xiaolong Wang and
Xinghao Zhu and
Xinyang Geng and
Xiyuan Liu and
Liangwei Xu and
Xuanlin Li and
Yao Lu and
Yecheng Jason Ma and
Yejin Kim and
Yevgen Chebotar and
Yifan Zhou and
Yifeng Zhu and
Yilin Wu and
Ying Xu and
Yixuan Wang and
Yonatan Bisk and
Yoonyoung Cho and
Youngwoon Lee and
Yuchen Cui and
Yue Cao and
Yueh{-}Hua Wu and
Yujin Tang and
Yuke Zhu and
Yunchu Zhang and
Yunfan Jiang and
Yunshuang Li and
Yunzhu Li and
Yusuke Iwasawa and
Yutaka Matsuo and
Zehan Ma and
Zhuo Xu and
Zichen Jeff Cui and
Zichen Zhang and
Zipeng Lin},
title = {Open X-Embodiment: Robotic Learning Datasets and {RT-X} Models : Open
X-Embodiment Collaboration},
booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA}
2024, Yokohama, Japan, May 13-17, 2024},
pages = {6892--6903},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICRA57147.2024.10611477},
doi = {10.1109/ICRA57147.2024.10611477},
timestamp = {Wed, 05 Nov 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icra/ONeillRMGPLPGMJ24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/BhatejaGGSTVCLK24,
author = {Chethan Bhateja and
Derek Guo and
Dibya Ghosh and
Anikait Singh and
Manan Tomar and
Quan Vuong and
Yevgen Chebotar and
Sergey Levine and
Aviral Kumar},
title = {Robotic Offline {RL} from Internet Videos via Value-Function Learning},
booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA}
2024, Yokohama, Japan, May 13-17, 2024},
pages = {16977--16984},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ICRA57147.2024.10611575},
doi = {10.1109/ICRA57147.2024.10611575},
timestamp = {Mon, 19 Aug 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icra/BhatejaGGSTVCLK24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-14367,
author = {Fahim Tajwar and
Anikait Singh and
Archit Sharma and
Rafael Rafailov and
Jeff Schneider and
Tengyang Xie and
Stefano Ermon and
Chelsea Finn and
Aviral Kumar},
title = {Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy
Data},
journal = {CoRR},
volume = {abs/2404.14367},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2404.14367},
doi = {10.48550/ARXIV.2404.14367},
eprinttype = {arXiv},
eprint = {2404.14367},
timestamp = {Sat, 25 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2404-14367.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2408-08441,
author = {Rafael Rafailov and
Kyle Hatch and
Anikait Singh and
Laura Smith and
Aviral Kumar and
Ilya Kostrikov and
Philippe Hansen{-}Estruch and
Victor Kolev and
Philip J. Ball and
Jiajun Wu and
Chelsea Finn and
Sergey Levine},
title = {{D5RL:} Diverse Datasets for Data-Driven Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2408.08441},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2408.08441},
doi = {10.48550/ARXIV.2408.08441},
eprinttype = {arXiv},
eprint = {2408.08441},
timestamp = {Fri, 10 Oct 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2408-08441.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2410-02725,
author = {Rohin Manvi and
Anikait Singh and
Stefano Ermon},
title = {Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better,
Even Mid-Generation},
journal = {CoRR},
volume = {abs/2410.02725},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2410.02725},
doi = {10.48550/ARXIV.2410.02725},
eprinttype = {arXiv},
eprint = {2410.02725},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2410-02725.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2412-08812,
author = {Yoonho Lee and
Jonathan Williams and
Henrik Marklund and
Archit Sharma and
Eric Mitchell and
Anikait Singh and
Chelsea Finn},
title = {Test-Time Alignment via Hypothesis Reweighting},
journal = {CoRR},
volume = {abs/2412.08812},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2412.08812},
doi = {10.48550/ARXIV.2412.08812},
eprinttype = {arXiv},
eprint = {2412.08812},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2412-08812.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/ZitkovichYXXXXW23,
author = {Brianna Zitkovich and
Tianhe Yu and
Sichun Xu and
Peng Xu and
Ted Xiao and
Fei Xia and
Jialin Wu and
Paul Wohlhart and
Stefan Welker and
Ayzaan Wahid and
Quan Vuong and
Vincent Vanhoucke and
Huong T. Tran and
Radu Soricut and
Anikait Singh and
Jaspiar Singh and
Pierre Sermanet and
Pannag R. Sanketi and
Grecia Salazar and
Michael S. Ryoo and
Krista Reymann and
Kanishka Rao and
Karl Pertsch and
Igor Mordatch and
Henryk Michalewski and
Yao Lu and
Sergey Levine and
Lisa Lee and
Tsang{-}Wei Edward Lee and
Isabel Leal and
Yuheng Kuang and
Dmitry Kalashnikov and
Ryan Julian and
Nikhil J. Joshi and
Alex Irpan and
Brian Ichter and
Jasmine Hsu and
Alexander Herzog and
Karol Hausman and
Keerthana Gopalakrishnan and
Chuyuan Fu and
Pete Florence and
Chelsea Finn and
Kumar Avinava Dubey and
Danny Driess and
Tianli Ding and
Krzysztof Marcin Choromanski and
Xi Chen and
Yevgen Chebotar and
Justice Carbajal and
Noah Brown and
Anthony Brohan and
Montserrat Gonzalez Arenas and
Kehang Han},
editor = {Jie Tan and
Marc Toussaint and
Kourosh Darvish},
title = {{RT-2:} Vision-Language-Action Models Transfer Web Knowledge to Robotic
Control},
booktitle = {Conference on Robot Learning, CoRL 2023, 6-9 November 2023, Atlanta,
GA, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {229},
pages = {2165--2183},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v229/zitkovich23a.html},
timestamp = {Mon, 20 Jan 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/ZitkovichYXXXXW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/NakamotoZSM0FKL23,
author = {Mitsuhiko Nakamoto and
Simon Zhai and
Anikait Singh and
Max Sobol Mark and
Yi Ma and
Chelsea Finn and
Aviral Kumar and
Sergey Levine},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Cal-QL: Calibrated Offline {RL} Pre-Training for Efficient Online
Fine-Tuning},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/c44a04289beaf0a7d968a94066a1d696-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/NakamotoZSM0FKL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/SinghKVCL23,
author = {Anikait Singh and
Aviral Kumar and
Quan Vuong and
Yevgen Chebotar and
Sergey Levine},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {ReDS: Offline {RL} With Heteroskedastic Datasets via Support Constraints},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/4b5d47949866d06ab5c03022b4a5a551-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/SinghKVCL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/rss/KumarSENYFL23,
author = {Aviral Kumar and
Anikait Singh and
Frederik D. Ebert and
Mitsuhiko Nakamoto and
Yanlai Yang and
Chelsea Finn and
Sergey Levine},
editor = {Kostas E. Bekris and
Kris Hauser and
Sylvia L. Herbert and
Jingjin Yu},
title = {Pre-Training for Robots: Offline {RL} Enables Learning New Tasks in
a Handful of Trials},
booktitle = {Robotics: Science and Systems XIX, Daegu, Republic of Korea, July
10-14, 2023},
year = {2023},
url = {https://doi.org/10.15607/RSS.2023.XIX.019},
doi = {10.15607/RSS.2023.XIX.019},
timestamp = {Thu, 20 Jul 2023 14:53:22 +0200},
biburl = {https://dblp.org/rec/conf/rss/KumarSENYFL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-05479,
author = {Mitsuhiko Nakamoto and
Yuexiang Zhai and
Anikait Singh and
Max Sobol Mark and
Yi Ma and
Chelsea Finn and
Aviral Kumar and
Sergey Levine},
title = {Cal-QL: Calibrated Offline {RL} Pre-Training for Efficient Online
Fine-Tuning},
journal = {CoRR},
volume = {abs/2303.05479},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.05479},
doi = {10.48550/ARXIV.2303.05479},
eprinttype = {arXiv},
eprint = {2303.05479},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-05479.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-15818,
author = {Anthony Brohan and
Noah Brown and
Justice Carbajal and
Yevgen Chebotar and
Xi Chen and
Krzysztof Choromanski and
Tianli Ding and
Danny Driess and
Avinava Dubey and
Chelsea Finn and
Pete Florence and
Chuyuan Fu and
Montse Gonzalez Arenas and
Keerthana Gopalakrishnan and
Kehang Han and
Karol Hausman and
Alexander Herzog and
Jasmine Hsu and
Brian Ichter and
Alex Irpan and
Nikhil J. Joshi and
Ryan Julian and
Dmitry Kalashnikov and
Yuheng Kuang and
Isabel Leal and
Lisa Lee and
Tsang{-}Wei Edward Lee and
Sergey Levine and
Yao Lu and
Henryk Michalewski and
Igor Mordatch and
Karl Pertsch and
Kanishka Rao and
Krista Reymann and
Michael S. Ryoo and
Grecia Salazar and
Pannag Sanketi and
Pierre Sermanet and
Jaspiar Singh and
Anikait Singh and
Radu Soricut and
Huong T. Tran and
Vincent Vanhoucke and
Quan Vuong and
Ayzaan Wahid and
Stefan Welker and
Paul Wohlhart and
Jialin Wu and
Fei Xia and
Ted Xiao and
Peng Xu and
Sichun Xu and
Tianhe Yu and
Brianna Zitkovich},
title = {{RT-2:} Vision-Language-Action Models Transfer Web Knowledge to Robotic
Control},
journal = {CoRR},
volume = {abs/2307.15818},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.15818},
doi = {10.48550/ARXIV.2307.15818},
eprinttype = {arXiv},
eprint = {2307.15818},
timestamp = {Mon, 20 Jan 2025 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-15818.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-13041,
author = {Chethan Bhateja and
Derek Guo and
Dibya Ghosh and
Anikait Singh and
Manan Tomar and
Quan Vuong and
Yevgen Chebotar and
Sergey Levine and
Aviral Kumar},
title = {Robotic Offline {RL} from Internet Videos via Value-Function Pre-Training},
journal = {CoRR},
volume = {abs/2309.13041},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.13041},
doi = {10.48550/ARXIV.2309.13041},
eprinttype = {arXiv},
eprint = {2309.13041},
timestamp = {Sun, 06 Oct 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-13041.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-08864,
author = {Open X.{-}Embodiment Collaboration and
Abhishek Padalkar and
Acorn Pooley and
Ajinkya Jain and
Alex Bewley and
Alexander Herzog and
Alex Irpan and
Alexander Khazatsky and
Anant Raj and
Anikait Singh and
Anthony Brohan and
Antonin Raffin and
Ayzaan Wahid and
Ben Burgess{-}Limerick and
Beomjoon Kim and
Bernhard Sch{\"{o}}lkopf and
Brian Ichter and
Cewu Lu and
Charles Xu and
Chelsea Finn and
Chenfeng Xu and
Cheng Chi and
Chenguang Huang and
Christine Chan and
Chuer Pan and
Chuyuan Fu and
Coline Devin and
Danny Driess and
Deepak Pathak and
Dhruv Shah and
Dieter B{\"{u}}chler and
Dmitry Kalashnikov and
Dorsa Sadigh and
Edward Johns and
Federico Ceola and
Fei Xia and
Freek Stulp and
Gaoyue Zhou and
Gaurav S. Sukhatme and
Gautam Salhotra and
Ge Yan and
Giulio Schiavi and
Gregory Kahn and
Hao Su and
Haoshu Fang and
Haochen Shi and
Heni Ben Amor and
Henrik I. Christensen and
Hiroki Furuta and
Homer Walke and
Hongjie Fang and
Igor Mordatch and
Ilija Radosavovic and
et al.},
title = {Open X-Embodiment: Robotic Learning Datasets and {RT-X} Models},
journal = {CoRR},
volume = {abs/2310.08864},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.08864},
doi = {10.48550/ARXIV.2310.08864},
eprinttype = {arXiv},
eprint = {2310.08864},
timestamp = {Thu, 15 May 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-08864.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/KumarHSL22,
author = {Aviral Kumar and
Joey Hong and
Anikait Singh and
Sergey Levine},
title = {Should {I} Run Offline Reinforcement Learning or Behavioral Cloning?},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=AP1MKT37rJ},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/KumarHSL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-05618,
author = {Aviral Kumar and
Joey Hong and
Anikait Singh and
Sergey Levine},
title = {When Should We Prefer Offline Reinforcement Learning Over Behavioral
Cloning?},
journal = {CoRR},
volume = {abs/2204.05618},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.05618},
doi = {10.48550/ARXIV.2204.05618},
eprinttype = {arXiv},
eprint = {2204.05618},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-05618.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-05178,
author = {Aviral Kumar and
Anikait Singh and
Frederik Ebert and
Yanlai Yang and
Chelsea Finn and
Sergey Levine},
title = {Pre-Training for Robots: Offline {RL} Enables Learning New Tasks from
a Handful of Trials},
journal = {CoRR},
volume = {abs/2210.05178},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.05178},
doi = {10.48550/ARXIV.2210.05178},
eprinttype = {arXiv},
eprint = {2210.05178},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-05178.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-01052,
author = {Anikait Singh and
Aviral Kumar and
Quan Vuong and
Yevgen Chebotar and
Sergey Levine},
title = {Offline {RL} With Realistic Datasets: Heteroskedasticity and Support
Constraints},
journal = {CoRR},
volume = {abs/2211.01052},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.01052},
doi = {10.48550/ARXIV.2211.01052},
eprinttype = {arXiv},
eprint = {2211.01052},
timestamp = {Sat, 06 Sep 2025 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-01052.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/KumarSTFL21,
author = {Aviral Kumar and
Anikait Singh and
Stephen Tian and
Chelsea Finn and
Sergey Levine},
editor = {Aleksandra Faust and
David Hsu and
Gerhard Neumann},
title = {A Workflow for Offline Model-Free Robotic Reinforcement Learning},
booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}},
series = {Proceedings of Machine Learning Research},
volume = {164},
pages = {417--428},
publisher = {{PMLR}},
year = {2021},
url = {https://proceedings.mlr.press/v164/kumar22a.html},
timestamp = {Wed, 19 Jan 2022 17:10:33 +0100},
biburl = {https://dblp.org/rec/conf/corl/KumarSTFL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10813,
author = {Aviral Kumar and
Anikait Singh and
Stephen Tian and
Chelsea Finn and
Sergey Levine},
title = {A Workflow for Offline Model-Free Robotic Reinforcement Learning},
journal = {CoRR},
volume = {abs/2109.10813},
year = {2021},
url = {https://arxiv.org/abs/2109.10813},
eprinttype = {arXiv},
eprint = {2109.10813},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-10813.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-11-13 01:21 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: