Mise à l'échelle des modèles de diffusion masquée sur le texte
52:46
Miika Aittala: Elucidating the Design Space of Diffusion-Based Generative Models
52:39
WARP: On the Benefits of Weight Averaged Rewarded Policies
40:14
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
44:29
Aprendizagem de transferência informada pela física para controle de processos
32:31
Round and Round We Go! What makes Rotary Positional Encodings useful?
24:07
AI can't cross this line and we don't know why.
1:02:30
Stable Diffusion 3: Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
35:52