Visual AutoRegressive Modeling:Scalable Image Generation via Next-Scale Prediction
30:07
LADD: Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
1:52:44
Visual Autoregressive Modeling
45:48
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
1:21:39
DeepSeek-V3
41:33
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction [Lee Hyoseok]
21:44
Autoregressive Image Generation without Vector Quantization
25:22
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
17:40