| Bayesian Inverse Reinforcement Learning. D Ramachandran, E Amir IJCAI 7, 2586-2591, 2007 | 1011 | 2007 |
| The dialog state tracking challenge series JD Williams, M Henderson, A Raux, B Thomson, A Black, ... AI Magazine 35 (4), 121-124, 2014 | 531 | 2014 |
| Belief tracking and action selection in spoken dialog systems R Gupta, D Ramachandran, A Raux, N Mehta, S Krawczyk, M Hoffman US Patent 8,676,583, 2014 | 390 | 2014 |
| First-orderized researchcyc: Expressivity and efficiency in a common-sense ontology D Ramachandran, P Reagan, K Goolsbey AAAI workshop on contexts and ontologies: theory, practice and applications …, 2005 | 119* | 2005 |
| Do language embeddings capture scales? X Zhang, D Ramachandran, I Tenney, Y Elazar, D Roth arXiv preprint arXiv:2010.05345, 2020 | 84 | 2020 |
| State tracking over machine-learned relational trees in a dialog system A Ratnaparkhi, BB Douglas, WL Jarrold, D Ramachandran, PZ Yeh US Patent 10,120,955, 2018 | 75 | 2018 |
| How large are lions? inducing distributions over quantitative attributes Y Elazar, A Mahabal, D Ramachandran, T Bedrax-Weiss, D Roth arXiv preprint arXiv:1906.01327, 2019 | 68 | 2019 |
| Lambada: Backward chaining for automated reasoning in natural language M Kazemi, N Kim, D Bhatia, X Xu, D Ramachandran arXiv preprint arXiv:2212.13894, 2022 | 67 | 2022 |
| System and method for natural language driven search and discovery in large data sources P Yeh, W Jarrold, A Ratnaparkhi, D Ramachandran, P Patel-Schneider, ... US Patent 10,631,057, 2020 | 65 | 2020 |
| Improving hybrid vehicle fuel efficiency using inverse reinforcement learning A Vogel, D Ramachandran, R Gupta, A Raux Proceedings of the AAAI Conference on Artificial Intelligence 26 (1), 384-390, 2012 | 53 | 2012 |
| System and method for natural language driven search and discovery in large data sources P Yeh, W Jarrold, A Ratnaparkhi, D Ramachandran, P Patel-Schneider, ... US Patent 10,847,175, 2020 | 52 | 2020 |
| Which linguist invented the lightbulb? presupposition verification for question-answering N Kim, E Pavlick, BK Ayan, D Ramachandran arXiv preprint arXiv:2101.00391, 2021 | 41 | 2021 |
| Landmark-based location belief tracking for voice-controlled navigation system A Raux, R Gupta, D Ramachandran, Y Ma US Patent 9,127,950, 2015 | 38 | 2015 |
| Rich human feedback for text-to-image generation Y Liang, J He, G Li, P Li, A Klimovskiy, N Carolan, J Sun, J Pont-Tuset, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 36 | 2024 |
| Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking J Eisenstein, C Nagpal, A Agarwal, A Beirami, A D'Amour, DJ Dvijotham, ... arXiv preprint arXiv:2312.09244, 2023 | 36 | 2023 |
| Smoothed sarsa: reinforcement learning for robot delivery tasks R Gupta, D Ramachandran US Patent 8,326,780, 2012 | 30 | 2012 |
| ManifoldBoost: stagewise function approximation for fully-, semi-and un-supervised learning N Loeff, D Forsyth, D Ramachandran Proceedings of the 25th international conference on machine learning, 600-607, 2008 | 27 | 2008 |
| Smoothed sarsa: reinforcement learning for robot delivery tasks D Ramachandran, R Gupta 2009 IEEE International Conference on Robotics and Automation, 2125-2132, 2009 | 26 | 2009 |
| Landmark-based location belief tracking in a spoken dialog system Y Ma, A Raux, D Ramachandran, R Gupta Proceedings of the 13th annual meeting of the special interest group on …, 2012 | 25 | 2012 |
| Probabilistic ontology trees for belief tracking in dialog systems N Mehta, R Gupta, A Raux, D Ramachandran, S Krawczyk Proceedings of the SIGDIAL 2010 Conference, 37-46, 2010 | 24 | 2010 |
