Update README.md

README.md

@@ -1,3 +1,34 @@
----
-license: mit
----
+---
+license: mit
+---
+
+# Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
+
+
+Most existing video VAEs prioritize reconstruction fidelity, often overlooking the latent structure's impact on
+downstream diffusion training. Our research identifies properties of video VAE latent spaces that facilitate diffusion
+training through statistical analysis of VAE latents. Our key finding is that biased, rather than uniform, spectra lead
+to improved diffusability. Motivated by this, we introduce **SSVAE (Spectral-Structured VAE)**, which optimizes the *
+*spectral properties** of the latent space to enhance its **"Diffusability"**.
+
+<div align="center">
+<img src="https://raw.githubusercontent.com/zai-org/SSVAE/refs/heads/main/assets/figs/teaser.png" alt="Figure 1" width="400">
+</div>
+
+## 🔥 Key Highlights
+
+* **Spectral Analysis of Latents**: We identify two statistical properties essential for efficient diffusion training: a
+  **low-frequency biased spatio-temporal spectrum** and a **few-mode biased channel eigenspectrum**.
+* **Local Correlation Regularization (LCR)**: A lightweight regularizer that explicitly enhances local spatio-temporal
+  correlations to induce low-frequency bias.
+* **Latent Masked Reconstruction (LMR)**: A mechanism that simultaneously promotes few-mode bias and improves decoder
+  robustness against noise.
+* **Superior Performance**:
+    * 🚀 **3× Faster Convergence**: Accelerates text-to-video generation convergence by 3× compared to strong baselines.
+    * 📈 **Higher Quality**: Achieves a **10% gain** in video reward scores (UnifiedReward).
+    * 🏆 **Outperforms SOTA**: Surpasses open-source VAEs (e.g., Wan 2.2, CogVideoX) in generation quality with fewer
+      parameters.
+
+## Using Model
+
+Please View our [Github](https://github.com/zai-org/SSVAE).