Deja vu: Contextual sparsity for efficient llms at inference time Z Liu, J Wang, T Dao, T Zhou, B Yuan, Z Song, A Shrivastava, C Zhang, ... International Conference on Machine Learning, 22137-22176, 2023 | 77 | 2023 |
H2o: Heavy-hitter oracle for efficient generative inference of large language models Z Zhang, Y Sheng, T Zhou, T Chen, L Zheng, R Cai, Z Song, Y Tian, C Ré, ... Advances in Neural Information Processing Systems 36, 2024 | 53 | 2024 |
A model for the triboelectric nanogenerator with inductive load and its energy boost potential M Lu, W Yin, A Peyton, Z Qu, X Meng, Y Xie, P Zhao, J Luo, Q Zhao, Y Tao, ... Nano Energy 63, 103883, 2019 | 36 | 2019 |
Algorithm and hardness for dynamic attention maintenance in large language models J Brand, Z Song, T Zhou arXiv preprint arXiv:2304.02207, 2023 | 29 | 2023 |
The closeness of in-context learning and weight shifting for softmax regression S Li, Z Song, Y Xia, T Yu, T Zhou arXiv preprint arXiv:2304.13276, 2023 | 24 | 2023 |
Faster algorithm for structured john ellipsoid computation Z Song, X Yang, Y Yang, T Zhou arXiv preprint arXiv:2211.14407, 2022 | 23 | 2022 |
A mathematical abstraction for balancing the trade-off between creativity and reality in large language models R Sinha, Z Song, T Zhou arXiv preprint arXiv:2306.02295, 2023 | 17 | 2023 |
Solving regularized exp, cosh and sinh regression problems Z Li, Z Song, T Zhou arXiv preprint arXiv:2303.15725, 2023 | 17 | 2023 |
Space-efficient interior point method, with applications to linear programming and maximum weight bipartite matching SC Liu, Z Song, H Zhang, L Zhang, T Zhou arXiv preprint arXiv:2009.06106, 2020 | 14 | 2020 |
Superiority of softmax: Unveiling the performance edge over linear attention Y Deng, Z Song, T Zhou arXiv preprint arXiv:2310.11685, 2023 | 10 | 2023 |
Fourier Circuits in Neural Networks: Unlocking the Potential of Large Language Models in Mathematical Reasoning and Modular Arithmetic J Gu, C Li, Y Liang, Z Shi, Z Song, T Zhou arXiv preprint arXiv:2402.09469, 2024 | 2 | 2024 |
Faster Sinkhorn's Algorithm with Small Treewidth Z Song, T Zhou arXiv preprint arXiv:2301.06741, 2023 | 1 | 2023 |
Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training L Qin, S Mitra, Z Song, Y Yang, T Zhou Bigdata, 2023 | | 2023 |