Ampliando modelos de difusão mascarados em texto
48:21
MiniMax-01: Escalado de modelos de base con atención relámpago
25:22
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
52:46
Miika Aittala: Elucidating the Design Space of Diffusion-Based Generative Models
24:07
AI can't cross this line and we don't know why.
1:32:01
Diffusion and Score-Based Generative Models
45:05
Byte Latent Transformer: Patches Scale Better Than Tokens
30:07
LADD: Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
32:31