| 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 | 1259 | 2025 |
| Cleanrl: High-quality single-file implementations of deep reinforcement learning algorithms S Huang, RFJ Dossa, C Ye, J Braga, D Chakraborty, K Mehta, ... Journal of Machine Learning Research 23 (274), 1-18, 2022 | 571 | 2022 |
| Rotation, Translation, and Cropping for Zero-Shot Generalization C Ye, A Khalifa, P Bontrager, J Togelius IEEE Conference on Games (CoG) 2020, 57--64, 2020 | 51 | 2020 |
| Open rl benchmark: Comprehensive tracked experiments for reinforcement learning S Huang, Q Gallouédec, F Felten, A Raffin, RFJ Dossa, Y Zhao, ... arXiv preprint arXiv:2402.03046, 2024 | 19 | 2024 |
| Teacher-generated spatial-attention labels boost robustness and accuracy of contrastive models Y Yao, C Ye, J He, GF Elsayed Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 5 | 2023 |
| Teacher-generated pseudo human spatial-attention labels boost contrastive learning models Y Yao, C Ye, J He, GF Elsayed SVRHM 2022 Workshop@ NeurIPS, 2022 | | 2022 |
| Can generative models generate novel objects the same as familiar objects? Z Xue, C Ye, GF Elsayed, J He Second Workshop on Visual Concepts, 0 | | |
Shengyi HuangAllen Institute for Artificial IntelligenceVerified email at allenai.org
