-
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
Paper • 2411.17459 • Published • 12 -
MAGVIT: Masked Generative Video Transformer
Paper • 2212.05199 • Published -
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
Paper • 2310.05737 • Published • 6 -
Finite Scalar Quantization: VQ-VAE Made Simple
Paper • 2309.15505 • Published • 23
Inui
Norm
AI & ML interests
Video Diffusion; Large Language Model; Object Detection; OCR
Recent Activity
liked
a dataset
about 2 hours ago
wsdwJohn1231/DreamLIP_capion_csv_w_key
liked
a dataset
about 3 hours ago
Jyuhamdik/RealSyn15M
upvoted
a
paper
about 2 months ago
Revisiting Multimodal Positional Encoding in Vision-Language Models
Organizations
-
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
Paper • 2411.17459 • Published • 12 -
MAGVIT: Masked Generative Video Transformer
Paper • 2212.05199 • Published -
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
Paper • 2310.05737 • Published • 6 -
Finite Scalar Quantization: VQ-VAE Made Simple
Paper • 2309.15505 • Published • 23
datasets
0
None public yet