view article Article Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs allenai • about 13 hours ago • 18
dRAE: Representation Autoencoder with Hyper-Spherical Codes Paper • 2607.22148 • Published Jul 24 • 11
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models Paper • 2402.19427 • Published Feb 29, 2024 • 59