# Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability

arXiv: https://arxiv.org/abs/2512.05394 · HTML: https://mlsanity.com/paper/2512.05394/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 27 of 27)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers](https://mlsanity.com/paper/2504.10483/) (2025)
- [Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models](https://mlsanity.com/paper/2410.10733/) (2024)
- [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025)
- [Masked Autoencoders Are Effective Tokenizers for Diffusion Models](https://mlsanity.com/paper/2502.03444/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling](https://mlsanity.com/paper/2502.09509/) (2025)
- [Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model](https://mlsanity.com/paper/2504.08685/) (2025)
- [Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training](https://mlsanity.com/paper/2505.17638/) (2025)
- [Improving the Diffusability of Autoencoders](https://mlsanity.com/paper/2502.14831/) (2025)
- [CV-VAE: A Compatible Video VAE for Latent Generative Video Models](https://mlsanity.com/paper/2405.20279/) (2024)
- [WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model](https://mlsanity.com/paper/2411.17459/) (2024)
- [On the Content Bias in Fr'echet Video Distance](https://mlsanity.com/paper/2404.12391/) (2024)
- [Improved Video VAE for Latent Video Diffusion Model](https://mlsanity.com/paper/2411.06449/) (2024)
- [DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space](https://mlsanity.com/paper/2508.00413/) (2025)
- [Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models](https://mlsanity.com/paper/2412.09645/) (2024)
- [OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model](https://mlsanity.com/paper/2409.01199/) (2024)

## Built on by (most cited first, 11 of 11)

- [Making Reconstruction FID Predictive of Diffusion Generation FID](https://mlsanity.com/paper/2603.05630/) (2026)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion](https://mlsanity.com/paper/2603.14645/) (2026)
- [Diffusing in the Right Space: A Systematic Study of Latent Diffusability](https://mlsanity.com/paper/2606.03578/) (2026)
- [Adaptive 1D Video Diffusion Autoencoder](https://mlsanity.com/paper/2602.04220/) (2026)
- [KVAE: Family of Tokenizers for Multimodal Generative Models](https://mlsanity.com/paper/2608.05798/) (2026)
- [Video Generation with Predictive Latents](https://mlsanity.com/paper/2605.02134/) (2026)
- [Latent-Frequency Validity: Fast Spectral Editing with Screened Video-VAE Transfer Operators](https://mlsanity.com/paper/2608.07569/) (2026)
- [AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer](https://mlsanity.com/paper/2608.23864/) (2026)
- [DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence](https://mlsanity.com/paper/2609.39222/) (2026)
- [VGGA: Geometry-Grounded Autoencoder for Video Generation](https://mlsanity.com/paper/2610.16204/) (2026)

## Abstract (arXiv)

Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs typically focus on reconstruction fidelity, overlooking latent structure. We present a statistical analysis of video VAE latent spaces and identify two spectral properties essential for diffusion training: a spatio-temporal frequency spectrum biased toward low frequencies, and a channel-wise eigenspectrum dominated by a few modes. To induce these properties, we propose two lightweight, backbone-agnostic regularizers: Local Correlation Regularization and Latent Masked Reconstruction. Experiments show that our Spectral-Structured VAE (SSVAE) achieves a 3× speedup in text-to-video generation convergence and a 10% gain in video reward, outperforming strong open-source VAEs. The code is available at https://github.com/zai-org/SSVAE.