Analyzing and Improving the Training Dynamics of Diffusion Models
Paper
•
2312.02696
•
Published
•
31
Optimization
-
-
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
Paper • 2401.02994 • Published • 48 -
Rethinking Patch Dependence for Masked Autoencoders
Paper • 2401.14391 • Published • 23 -
In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss
Paper • 2402.10790 • Published • 41