SparseGPT improves the speed and efficiency of large language models through parameter pruning.
Xiaoyu Li, Yingyu Liang, Zhenmei Shi
― 4 min read
Yingyu Liang
A new approach enhances gradient calculations, improving transformer efficiency in machine learning.
Yingyu Liang, Zhizhou Sha, Zhenmei Shi
― 4 min read
A method to enhance efficiency of language models with long text inputs.
Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen
― 5 min read
Exploring the capabilities and challenges of Transformer technology in understanding language.
Bo Chen, Xiaoyu Li, Yingyu Liang
― 6 min read
A closer look at how MHNs can enhance machine learning.
Xiaoyu Li, Yuanpeng Li, Yingyu Liang
― 6 min read
A look at Mamba and State-Space Models in AI capabilities.
Yifang Chen, Xiaoyu Li, Yingyu Liang
― 6 min read
Discover how tensor attention transforms AI language processing.
Xiaoyu Li, Yingyu Liang, Zhenmei Shi
― 7 min read
New methods improve RoPE attention, speeding up AI computations significantly.
Yifang Chen, Jiayan Huo, Xiaoyu Li
― 5 min read