| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 816 | 2023 |
| What are Bayesian neural network posteriors really like? P Izmailov, S Vikram, MD Hoffman, AGG Wilson International Conference on Machine Learning, 4629-4640, 2021 | 357 | 2021 |
| SOLAR: Deep structured representations for model-based reinforcement learning M Zhang, S Vikram, L Smith, P Abbeel, M Johnson, S Levine International Conference on Machine Learning, 7444-7453, 2019 | 290 | 2019 |
| Handwriting and Gestures in the Air, Recognizing on the Fly S Vikram, L Li, S Russell Proceedings of the CHI 13, 1179-1184, 2013 | 126* | 2013 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 108 | 2024 |
| Capturing meaning in product reviews with character-level generative text models ZC Lipton, S Vikram, J McAuley arXiv preprint arXiv:1511.03683, 2015 | 87* | 2015 |
| Estimating reactions and recommending products with generative models of reviews J Ni, ZC Lipton, S Vikram, J McAuley Proceedings of the Eighth International Joint Conference on Natural Language …, 2017 | 52 | 2017 |
| Interactive bayesian hierarchical clustering S Vikram, S Dasgupta International Conference on Machine Learning, 2081-2090, 2016 | 51 | 2016 |
| How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies? Q Vuong, S Vikram, H Su, S Gao, HI Christensen arXiv preprint arXiv:1903.11774, 2019 | 43 | 2019 |
| Automatic structured variational inference L Ambrogioni, K Lin, E Fertig, S Vikram, M Hinne, D Moore, M van Gerven International Conference on Artificial Intelligence and Statistics, 676-684, 2021 | 31 | 2021 |
| Methods of predicting pathogenicity of genetic sequence variants IS Haque, EA Evans, SM Vikram, MD Rasmussen US Patent App. 15/189,957, 2016 | 31 | 2016 |
| Evaluating and improving the reliability of gas-phase sensor system calibrations across new locations for ambient measurements and personal exposure monitoring S Vikram, A Collier-Oxandale, MH Ostertag, M Menarini, C Chermak, ... Atmospheric Measurement Techniques 12 (8), 4211-4239, 2019 | 23 | 2019 |
| Automatic Differentiation Variational Inference with Mixtures W Morningstar, S Vikram, C Ham, A Gallagher, J Dillon International Conference on Artificial Intelligence and Statistics, 3250-3258, 2021 | 18 | 2021 |
| Evaluating Approximate Inference in Bayesian Deep Learning AG Wilson, P Izmailov, MD Hoffman, Y Gal, Y Li, MF Pradier, S Vikram, ... NeurIPS 2021 Competitions and Demonstrations Track, 113-124, 2022 | 16 | 2022 |
| The LORACs prior for VAEs: Letting the trees speak for the data S Vikram, MD Hoffman, MJ Johnson The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 13 | 2019 |
| Training Chain-of-Thought via Latent-Variable Inference D Phan, MD Hoffman, D Dohan, S Douglas, TA Le, A Parisi, P Sountsov, ... arXiv preprint arXiv:2312.02179, 2023 | 8* | 2023 |
| Estimating the changing infection rate of COVID-19 using Bayesian models of mobility L Liu, S Vikram, J Lao, X Ben, A D’Amour, S O’Banion, M Sandler, ... medRxiv, 2020.08. 06.20169664, 2020 | 7 | 2020 |
| RecurrentGemma: Moving Past Transformers for Efficient Open Language Models A Botev, S De, SL Smith, A Fernando, GC Muraru, R Haroun, L Berrada, ... arXiv preprint arXiv:2404.07839, 2024 | 1 | 2024 |
| Interactive comment on “Evaluating and Improving the Reliability of Gas-Phase Sensor System Calibrations Across New Locations for Ambient Measurements and Personal Exposure … S Vikram | | 2019 |
| Bayesian Structured Representation Learning S Vikram University of California, San Diego, 2019 | | 2019 |
Matthew D. HoffmanResearch Scientist, Google Research在 google.com 的电子邮件经过验证
