view article Article Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand 22 days ago • 62
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19 • 226
Train Sparse Autoencoders Efficiently by Utilizing Features Correlation Paper • 2505.22255 • Published May 28 • 24
You Do Not Fully Utilize Transformer's Representation Capacity Paper • 2502.09245 • Published Feb 13 • 37
FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline Paper • 2311.13073 • Published Nov 22, 2023 • 58
Runtime error Featured 5.07k MusicGen 🎵 5.07k Generate music from text descriptions and optional melodies