“Classifier-FreeGuidance is a Predictor-Corrector”
【Diffusion勉強会】“Classifier-FreeGuidance is a Predictor-Corrector” by @DeepLearning2023
Author: risa.murata
Compositional Visual Generation with Composable Diffusion Models
【Diffusion勉強会】Compositional Visual Generation with Composable Diffusion Models by @De more
Foundation Models for 3D Scene Understanding
Foundation Models for 3D Scene Understanding by @DeepLearning2023
Lory: Fully Differentiable Mixture-of-Experts forAutoregressive Language Model Pre-training
Sorry, this entry is only available in Japanese. For the sake of viewer convenience, more
Guiding a Diffusion Model with a Bad Version of Itself
【Diffusion勉強会】Guiding a Diffusion Model with a Bad Version of Itself by @DeepLearning more
Prompt-guided PreciseAudio Editing with Diffusion Models [1]
【Diffusion勉強会】Prompt-guided PreciseAudio Editing with Diffusion Models [1] by @DeepLe more
Scaling Diffusion Transformers to 16 Billion Parameters
【Diffusion勉強会】Scaling Diffusion Transformers to 16 Billion Parameters by @DeepLearnin more
CADS: Unleashing the diversity of diffusion models through condition-annealed sampling
【Diffusion勉強会】CADS: Unleashing the diversity of diffusion models through condition-an more
Diffusion Forcing: Next-token Prediction Meets Full- Sequence Diffusion
【Diffusion勉強会】Diffusion Forcing: Next-token Prediction Meets Full- Sequence Diffusion more