Chenghao Liu

2 months ago | nature.com | Chenghao Liu |Bo Xu

AbstractWhether working memory (WM) is encoded by persistent activity using attractors or by dynamic activity using transient trajectories has been debated for decades in both experimental and modeling studies, and a consensus has not been reached. Even though many recurrent neural networks (RNNs) have been proposed to simulate WM, most networks are designed to match respective experimental observations and show either transient or persistent activities.

Nov 8, 2024 | salesforce.com | Xu Liu |Juncheng Liu |Chenghao Liu |Taha Aksu

TL;DR: We propose Moirai-MoE, the first mixture-of-experts time series foundation model, achieving token-level model specialization in a data-driven manner. Extensive experiments on 39 datasets reveal that Moirai-MoE delivers up to 17% performance improvements over Moirai at the same level of model size and outperforms other time series foundation models, such as Chronos (from Amazon) and TimesFM (from Google) with up to 65 times fewer activated parameters.

Aug 23, 2024 | mdpi.com | Xiao Wang |Di Wang |Chenghao Liu |Mengmeng Zhang

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.