Appears on
Articles2
Exploring the Power of Normalizing Flows in Generative Modeling
Normalizing Flows (NFs) are powerful generative models, demonstrated to be more capable than previously believed. TarFlow, a Transformer-based variant of Masked Autoregressive Flows (MAFs), enhances NF models' performance.
Insight
machinelearning.apple.com11mo agoIntroducing MiniMax-M1: The World's First Open-Weight Hybrid-Attention Reasoning Model
Introducing MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model powered by a hybrid Mixture-of-Experts architecture and lightning attention mechanism. Developed based on the MiniMax-Text-01 model, it contains 456 billion parameters with 45.9 billion parameters activated per token.
Code
github.com11mo ago