| Model-based reinforcement learning for atari L Kaiser, M Babaeizadeh, P Milos, B Osinski, RH Campbell, ... 8th International Conference on Learning Representations (ICLR), 2019 | 1268 | 2019 |
| Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... arXiv preprint arXiv:2507.06261, 2025 | 1217 | 2025 |
| Stochastic Variational Video Prediction M Babaeizadeh, C Finn, D Erhan, RH Campbell, S Levine 6th International Conference on Learning Representations (ICLR), 2018 | 710 | 2018 |
| Phenaki: Variable length video generation from open domain textual description R Villegas, M Babaeizadeh, PJ Kindermans, H Moraldo, H Zhang, ... arXiv preprint arXiv:2210.02399, 2022 | 585 | 2022 |
| Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU M Babaeizadeh, I Frosio, S Tyree, J Clemons, J Kautz 5th International Conference on Learning Representations (ICLR), 2017 | 423 | 2017 |
| Seq-nms for video object detection W Han, P Khorrami, TL Paine, P Ramachandran, M Babaeizadeh, H Shi, ... arXiv preprint arXiv:1602.08465, 2016 | 420 | 2016 |
| Fast generation for convolutional autoregressive models P Ramachandran, TL Paine, P Khorrami, M Babaeizadeh, S Chang, ... arXiv preprint arXiv:1704.06001, 2017 | 208* | 2017 |
| Videoflow: A flow-based generative model for video M Kumar, M Babaeizadeh, D Erhan, C Finn, S Levine, L Dinh, D Kingma arXiv preprint arXiv:1903.01434 2 (5), 3, 2019 | 162 | 2019 |
| Videoflow: A conditional flow-based model for stochastic video generation M Kumar, M Babaeizadeh, D Erhan, C Finn, S Levine, L Dinh, D Kingma arXiv preprint arXiv:1903.01434, 2019 | 129 | 2019 |
| FitVid: High-Capacity Pixel-Level Video Prediction M Babaeizadeh, MT Saffar, S Nair, S Levine, C Finn, D Erhan | 116* | |
| Creating a calendar event using context TJ Hazen, D Bishop, N Duta, M Babaeizadeh, P Longo US Patent 9,372,851, 2016 | 108* | 2016 |
| GA3C: GPU-based A3C for deep reinforcement learning M Babaeizadeh, I Frosio, S Tyree, J Clemons, J Kautz CoRR abs/1611.06256, 2016 | 105 | 2016 |
| Noiseout: A simple way to prune neural networks M Babaeizadeh, P Smaragdis, RH Campbell arXiv preprint arXiv:1611.06211, 2016 | 68* | 2016 |
| Information prioritization through empowerment in visual model-based RL H Bharadhwaj, M Babaeizadeh, D Erhan, S Levine arXiv preprint arXiv:2204.08585, 2022 | 44 | 2022 |
| Trass: Time reversal as self-supervision S Nair, M Babaeizadeh, C Finn, S Levine, V Kumar 2020 IEEE International Conference on Robotics and Automation (ICRA), 115-121, 2020 | 40* | 2020 |
| Adjustable real-time style transfer M Babaeizadeh, G Ghiasi arXiv preprint arXiv:1811.08560, 2018 | 28 | 2018 |
| Storybench: A multifaceted benchmark for continuous story visualization E Bugliarello, HH Moraldo, R Villegas, M Babaeizadeh, MT Saffar, ... Advances in Neural Information Processing Systems 36, 78095-78125, 2023 | 16 | 2023 |
| Models, pixels, and rewards: Evaluating design trade-offs in visual model-based reinforcement learning M Babaeizadeh, MT Saffar, D Hafner, H Kannan, C Finn, S Levine, ... arXiv preprint arXiv:2012.04603, 2020 | 16 | 2020 |
| Toward scalable machine learning and data mining: the bioinformatics case F Faghri, SH Hashemi, M Babaeizadeh, MA Nalls, S Sinha, RH Campbell arXiv preprint arXiv:1710.00112, 2017 | 12 | 2017 |
| A comprehensive classification of incident handling information M Nowruzi, HH Jazi, M Dehghan, M Shahmoradi, SH Hashemi, ... 6th International symposium on telecommunications (IST), 1071-1075, 2012 | 9 | 2012 |
Dumitru ErhanSenior Director of Research @ Google DeepMindVerified email at google.com
