INSTADOC
/

Add pipeline tag

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: mit
 
3
  ---
4
 
5
  # Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
@@ -12,7 +13,7 @@ Most existing video VAEs prioritize reconstruction fidelity, often overlooking t
12
  downstream diffusion training. Our research identifies properties of video VAE latent spaces that facilitate diffusion
13
  training through statistical analysis of VAE latents. Our key finding is that biased, rather than uniform, spectra lead
14
  to improved diffusability. Motivated by this, we introduce **SSVAE (Spectral-Structured VAE)**, which optimizes the *
15
- *spectral properties** of the latent space to enhance its **"Diffusability"**.
16
 
17
  <div align="center">
18
  <img src="https://raw.githubusercontent.com/zai-org/SSVAE/refs/heads/main/assets/figs/teaser.png" alt="Figure 1" width="400">
 
1
  ---
2
  license: mit
3
+ pipeline_tag: other
4
  ---
5
 
6
  # Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
 
13
  downstream diffusion training. Our research identifies properties of video VAE latent spaces that facilitate diffusion
14
  training through statistical analysis of VAE latents. Our key finding is that biased, rather than uniform, spectra lead
15
  to improved diffusability. Motivated by this, we introduce **SSVAE (Spectral-Structured VAE)**, which optimizes the *
16
+ **spectral properties** of the latent space to enhance its **"Diffusability"**.
17
 
18
  <div align="center">
19
  <img src="https://raw.githubusercontent.com/zai-org/SSVAE/refs/heads/main/assets/figs/teaser.png" alt="Figure 1" width="400">