| Deep sets M Zaheer, S Kottur, S Ravanbakhsh, B Poczos, RR Salakhutdinov, ... NeurIPS, 2017 | 3709 | 2017 |
| Accurate, fully-automated NMR spectral profiling for metabolomics S Ravanbakhsh, P Liu, R Mandal, JR Grant, M Wilson, R Eisner, ... PLoS ONE 10 (5), e0124219, 2015 | 379* | 2015 |
| Equivariance Through Parameter-Sharing S Ravanbakhsh, J Schneider, B Poczos ICML, 2017 | 336 | 2017 |
| Learning to predict the cosmological structure formation S He, Y Li, Y Feng, S Ho, S Ravanbakhsh, W Chen, B Póczos PNAS, 2019 | 283 | 2019 |
| CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding F Lanusse, Q Ma, N Li, TE Collett, CL Li, S Ravanbakhsh, R Mandelbaum, ... Monthly Notices of the Royal Astronomical Society 473 (3), 3895-3906, 2018 | 263 | 2018 |
| Deep learning with sets and point clouds S Ravanbakhsh, J Schneider, B Poczos ICLR - workshop track, 2016 | 231 | 2016 |
| Deep models of interactions across sets J Hartford, DR Graham, K Leyton-Brown, S Ravanbakhsh ICML, 2018 | 208 | 2018 |
| Equivariance with learned canonicalization functions SO Kaba, AK Mondal, Y Zhang, Y Bengio, S Ravanbakhsh ICML, 2023 | 141 | 2023 |
| Estimating cosmological parameters from the dark matter distribution S Ravanbakhsh, J Oliva, S Fromenteau, L Price, S Ho, J Schneider, ... ICML, 2016 | 105 | 2016 |
| Iterated denoising energy matching for sampling from Boltzmann densities T Akhound-Sadegh, J Rector-Brooks, AJ Bose, S Mittal, P Lemos, CH Liu, ... ICML, 2024 | 93 | 2024 |
| Deep generative models for galaxy image simulations F Lanusse, R Mandelbaum, S Ravanbakhsh, CL Li, P Freeman, B Póczos Monthly Notices of the Royal Astronomical Society 504 (4), 5543-5555, 2021 | 92 | 2021 |
| Enabling dark energy science with deep generative models of galaxy images S Ravanbakhsh, F Lanusse, R Mandelbaum, J Schneider, B Poczos AAAI, 2017 | 85 | 2017 |
| On Diffusion Modeling for Anomaly Detection V Livernoche, V Jain, Y Hezaveh, S Ravanbakhsh ICLR, 2024 | 68 | 2024 |
| Boolean Matrix Factorization and Noisy Completion via Message Passing. S Ravanbakhsh, R Barnabas Poczos, Greiner International Conference on Machine Learning (ICML), 945-954, 2016 | 66 | 2016 |
| Universal Equivariant Multilayer Perceptrons S Ravanbakhsh ICML, 2020 | 64 | 2020 |
| SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks C Morris, G Rattan, S Kiefer, S Ravanbakhsh ICML, 2022 | 60 | 2022 |
| Recovering the wedge modes lost to 21-cm foregrounds S Gagnon-Hartman, Y Cui, A Liu, S Ravanbakhsh Monthly Notices of the Royal Astronomical Society 504 (4), 4716-4729, 2021 | 48 | 2021 |
| Equivariant Networks for Crystal Structures SO Kaba, S Ravanbakhsh NeurIPS, 2022 | 47 | 2022 |
| Equivariant adaptation of large pretrained models AK Mondal, SS Panigrahi, O Kaba, SR Mudumba, S Ravanbakhsh NeurIPS, 2023 | 44 | 2023 |
| Eqr: Equivariant representations for data-efficient reinforcement learning AK Mondal, V Jain, K Siddiqi, S Ravanbakhsh ICML, 2022 | 42 | 2022 |
Barnabas PoczosAssociate professor, Carnegie Mellon UniversityVerified email at cs.cmu.edu
