-
Chinese AI lab challenges Google, OpenAI with a model of 1.75 trillion parameters
-
GPT-3: Language Models are Few-Shot Learners
-
DALL·E 1: Creating Images from Text: We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language
-
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
-
https://scholar.google.com/citations?user=n1zDCkQAAAAJ&view_op=list_works&alert_preview_top_rm=2&sortby=pubdate
-
https://scholar.google.com/citations?user=GQWTo4MAAAAJ
-
China’s AI Advances Help Its Tech Industry, and State Security
-
https://scholar.google.com/citations?user=y5zkBeMAAAAJ
-
China’s GPT-3? BAAI Introduces Superscale Intelligence Model ‘Wu Dao 1.0’: The Beijing Academy of Artificial Intelligence (BAAI) releases Wu Dao 1.0, China’s first large-scale pretraining model.
-
ChinAI #141: The PanGu Origin Story: Notes from an informative Zhihu Thread on PanGu
-
Turing-NLG: A 17-billion-parameter language model by Microsoft
-
CPM: A Large-scale Generative Chinese Pre-trained Language Model
-
[Ali released PLUG: 27 billion parameters, the largest pre-trained language model in the Chinese community]
-
DeepSpeed: Extreme-scale model training for everyone
-
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
-
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning
-
ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
-
Microsoft announces new supercomputer, lays out vision for future AI work
-
Exploring Sparse Expert Models and Beyond
-