| Sparks of artificial general intelligence: Early experiments with gpt-4 S Bubeck, V Chandrasekaran, R Eldan, J Gehrke, E Horvitz, E Kamar, ... arXiv preprint arXiv:2303.12712, 2023 | 5460 | 2023 |
| Phi-4 technical report M Abdin, J Aneja, H Behl, S Bubeck, R Eldan, S Gunasekar, M Harrison, ... arXiv preprint arXiv:2412.08905, 2024 | 2761 | 2024 |
| Generalization and Equilibrium in Generative Adversarial Nets (GANs) S Arora, R Ge, Y Liang, T Ma, Y Zhang arXiv preprint arXiv:1703.00573, 2017 | 907 | 2017 |
| Textbooks are all you need S Gunasekar, Y Zhang, J Aneja, CCT Mendes, A Del Giorno, S Gopi, ... arXiv preprint arXiv:2306.11644, 2023 | 883 | 2023 |
| Stronger generalization bounds for deep nets via a compression approach S Arora, R Ge, B Neyshabur, Y Zhang International conference on machine learning, 254-263, 2018 | 825 | 2018 |
| Convolutional neural networks with low-rank regularization C Tai, T Xiao, Y Zhang, X Wang arXiv preprint arXiv:1511.06067, 2015 | 612 | 2015 |
| Controllable text-to-image generation with gpt-4 T Zhang, Y Zhang, V Vineet, N Joshi, X Wang arXiv preprint arXiv:2305.18583, 2023 | 448 | 2023 |
| Deep visual analogy-making SE Reed, Y Zhang, Y Zhang, H Lee Advances in neural information processing systems 28, 2015 | 398 | 2015 |
| Phi-2: The surprising power of small language models M Javaheripi, S Bubeck, M Abdin, J Aneja, S Bubeck, CCT Mendes, ... Microsoft Research Blog 1 (3), 3, 2023 | 393 | 2023 |
| Do GANs actually learn the distribution? An empirical study S Arora, Y Zhang arXiv:1706.08224, 2017 | 221 | 2017 |
| Do GANs learn the distribution? some theory and empirics S Arora, A Risteski, Y Zhang International conference on learning representations, 2018 | 201 | 2018 |
| What makes convolutional models great on long sequence modeling? Y Li, T Cai, Y Zhang, D Chen, D Dey arXiv preprint arXiv:2210.09298, 2022 | 144 | 2022 |
| Spectral filtering for general linear dynamical systems E Hazan, H Lee, K Singh, C Zhang, Y Zhang Advances in Neural Information Processing Systems 31, 2018 | 124 | 2018 |
| Unveiling transformers with lego: a synthetic reasoning task Y Zhang, A Backurs, S Bubeck, R Eldan, S Gunasekar, T Wagner arXiv preprint arXiv:2206.04301, 2022 | 122 | 2022 |
| Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, S Arora, R Ge arXiv:1906.06247, 2019 | 116 | 2019 |
| Phi-4 technical report, 2024 M Abdin, J Aneja, H Behl, S Bubeck, R Eldan, S Gunasekar, M Harrison, ... URL https://arxiv. org/abs/2412.08905 5, 19, 0 | 100 | |
| Towards Understanding the Invertibility of Convolutional Neural Networks CA Gilbert, Y Zhang, K Lee, Y Zhang, H Lee arXiv preprint arXiv:1705.08664, 2017 | 86 | 2017 |
| Efficient full-matrix adaptive regularization N Agarwal, B Bullins, X Chen, E Hazan, K Singh, C Zhang, Y Zhang International Conference on Machine Learning, 102-110, 2019 | 77 | 2019 |
| Why are convolutional nets more sample-efficient than fully-connected nets? Z Li, Y Zhang, S Arora arXiv preprint arXiv:2010.08515, 2020 | 75 | 2020 |
| Positional description matters for transformers arithmetic R Shen, S Bubeck, R Eldan, YT Lee, Y Li, Y Zhang arXiv preprint arXiv:2311.14737, 2023 | 71 | 2023 |
Sebastien BubeckOpenAIVerified email at openai.com
