| Rlaif: Scaling reinforcement learning from human feedback with ai feedback H Lee, S Phatale, H Mansoor, KR Lu, T Mesnard, J Ferret, C Bishop, ... | 512 | 2023 |
| Multi-language online handwriting recognition D Keysers, T Deselaers, HA Rowley, LL Wang, V Carbune IEEE transactions on pattern analysis and machine intelligence 39 (6), 1180-1194, 2016 | 212 | 2016 |
| Using textual input and user state information to generate reply content to present in response to the textual input V Carbune, D Keysers, T Deselaers US Patent 10,192,551, 2019 | 186 | 2019 |
| Fast multi-language LSTM-based online handwriting recognition V Carbune, P Gonnet, T Deselaers, HA Rowley, A Daryin, M Calvo, ... International Journal on Document Analysis and Recognition (IJDAR) 23 (2 …, 2020 | 184 | 2020 |
| Smart assist for repeated actions V Carbune, D Keysers, T Deselaers US Patent 11,237,696, 2022 | 140 | 2022 |
| Collaborative voice controlled devices V Carbune, PG Anders, T Deselaers, S Feuz US Patent 10,559,309, 2020 | 121 | 2020 |
| LLMs cannot find reasoning errors, but can correct them given the error location G Tyen, H Mansoor, V Cărbune, P Chen, T Mak arXiv preprint arXiv:2311.08516, 2023 | 88 | 2023 |
| Rlaif vs. rlhf: Scaling reinforcement learning from human feedback with ai feedback H Lee, S Phatale, H Mansoor, T Mesnard, J Ferret, K Lu, C Bishop, E Hall, ... arXiv preprint arXiv:2309.00267, 2023 | 80 | 2023 |
| Automated assistants that accommodate multiple age groups and/or vocabulary levels PG Anders, V Carbune, D Keysers, T Deselaers, S Feuz US Patent 10,573,298, 2020 | 67 | 2020 |
| Machine-learned virtual sensor model for multiple sensors M Calvo, V Carbune, PG Anders, T Deselaers US Patent App. 15/393,322, 2018 | 57 | 2018 |
| Screenai: A vision-language model for ui and infographics understanding G Baechler, S Sunkara, M Wang, F Zubach, H Mansoor, V Etter, ... arXiv preprint arXiv:2402.04615, 2024 | 50 | 2024 |
| Multi-task machine learning for predicted touch interpretations T Deselaers, V Carbune US Patent 10,261,685, 2019 | 47* | 2019 |
| On-device machine learning platform to enable sharing of machine-learned models between applications S Feuz, V Carbune US Patent 11,537,931, 2022 | 43 | 2022 |
| Mapping input to form fields V Carbune, DM Keysers, T Deselaers US Patent App. 14/681,408, 2016 | 33 | 2016 |
| Actionable suggestions for activities DM Keysers, V Carbune, T Deselaers US Patent 10,846,612, 2020 | 30 | 2020 |
| Systems and methods for improved adversarial training of machine-learned models V Carbune, T Deselaers US Patent 11,494,667, 2022 | 27 | 2022 |
| Automated assistant adaptation of a response to an utterance and/or of processing of the utterance, based on determined interaction measure V Carbune, M Sharifi US Patent 11,455,996, 2022 | 26 | 2022 |
| Screenqa: Large-scale question-answer pairs over mobile app screenshots YC Hsiao, F Zubach, G Baechler, V Carbune, J Lin, M Wang, S Sunkara, ... arXiv preprint arXiv:2209.08199, 2022 | 26 | 2022 |
| Combining parameters of multiple search queries that share a line of inquiry M Sharifi, V Carbune US Patent 11,468,052, 2022 | 24 | 2022 |
| Streaming action fulfillment based on partial hypotheses M Sharifi, V Carbune US Patent 11,587,568, 2023 | 19 | 2023 |
Thomas DeselaersAppleVerified email at deselaers.de
