| Meta learning shared hierarchies K Frans, J Ho, X Chen, P Abbeel, J Schulman arXiv preprint arXiv:1710.09767, 2017 | 442 | 2017 |
| Clipdraw: Exploring text-to-drawing synthesis through language-image encoders K Frans, L Soros, O Witkowski Advances in Neural Information Processing Systems 35, 5207-5218, 2022 | 196 | 2022 |
| Outline colorization through tandem adversarial networks K Frans arXiv preprint arXiv:1704.08834, 2017 | 69 | 2017 |
| Unsupervised image to sequence translation with canvas-drawer networks K Frans, CY Cheng arXiv preprint arXiv:1809.08340, 2018 | 18 | 2018 |
| Soros, and Olaf Witkowski K Frans, B Lisa Clipdraw: Exploring text-to-drawing synthesis through language-image …, 2021 | 16 | 2021 |
| Ai charades: Language models as interactive game environments K Frans 2021 IEEE Conference on Games (CoG), 1-2, 2021 | 12 | 2021 |
| Is Value Learning Really the Main Bottleneck in Offline RL? S Park, K Frans, S Levine, A Kumar arXiv preprint arXiv:2406.09329, 2024 | 10 | 2024 |
| Powderworld: A platform for understanding generalization via rich task distributions K Frans, P Isola arXiv preprint arXiv:2211.13051, 2022 | 8 | 2022 |
| One step diffusion via shortcut models K Frans, D Hafner, S Levine, P Abbeel arXiv preprint arXiv:2410.12557, 2024 | 7 | 2024 |
| Population-based evolution optimizes a meta-learning objective K Frans, O Witkowski arXiv preprint arXiv:2103.06435, 2021 | 7 | 2021 |
| Questions for the open-ended evolution community: Reflections from the 2021 Cross Labs Innovation Science Workshop K Frans, LB Soros, O Witkowski Artificial Life 25 (1), 4, 2021 | 6 | 2021 |
| Ogbench: Benchmarking offline goal-conditioned rl S Park, K Frans, B Eysenbach, S Levine arXiv preprint arXiv:2410.20092, 2024 | 4 | 2024 |
| Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings K Frans, S Park, P Abbeel, S Levine arXiv preprint arXiv:2402.17135, 2024 | 3 | 2024 |
| Cross Labs O Witkowski Japan, 0 | 3 | |
| Prioritized Generative Replay R Wang, K Frans, P Abbeel, S Levine, AA Efros arXiv preprint arXiv:2410.18082, 2024 | 1 | 2024 |
| Powderworld: A Platform for Understanding Generalization via Rich Task Distributions K Frans Massachusetts Institute of Technology, 2023 | 1 | 2023 |
| Parallel trust region policy optimization with multiple actors K Frans, D Hafner | 1 | 2016 |
| Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration M Wilcoxson, Q Li, K Frans, S Levine arXiv preprint arXiv:2410.18076, 2024 | | 2024 |
| Selecting for Selection: Learning To Balance Adaptive and Diversifying Pressures in Evolutionary Search K Frans, LB Soros, O Witkowski arXiv preprint arXiv:2106.09153, 2021 | | 2021 |
| Image Reconstruction by Generative Adversarial Networks M Huang, K Frans, M Tory Journal A2I3R 1 (1), 2017 | | 2017 |
