# Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance

arXiv: https://arxiv.org/abs/2609.08505 · HTML: https://mlsanity.com/paper/2609.08505/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 8 Sep 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [StableVideo: Text-driven Consistency-aware Diffusion Video Editing](https://mlsanity.com/paper/2308.09592/) (2023)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [Phantom: Subject-consistent video generation via cross-modal alignment](https://mlsanity.com/paper/2502.11079/) (2025)
- [Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance](https://mlsanity.com/paper/2306.00943/) (2023)
- [ID-Animator: Zero-Shot Identity-Preserving Human Video Generation](https://mlsanity.com/paper/2404.15275/) (2024)
- [FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention](https://mlsanity.com/paper/2407.19918/) (2024)
- [Describing Videos by Exploiting Temporal Structure](https://mlsanity.com/paper/1502.08029/) (2015)
- [Space-time Mixing Attention for Video Transformer](https://mlsanity.com/paper/2106.05968/) (2021)
- [VideoStudio: Generating Consistent-Content and Multi-Scene Videos](https://mlsanity.com/paper/2401.01256/) (2024)
- [Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation](https://mlsanity.com/paper/2312.04483/) (2023)
- [Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures](https://mlsanity.com/paper/1808.08946/) (2018)
- [Mask2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation](https://mlsanity.com/paper/2503.19881/) (2025)
- [Denoising Diffusion Step-aware Models](https://mlsanity.com/paper/2310.03337/) (2023)
- [Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation](https://mlsanity.com/paper/2501.03059/) (2025)
- [Training-Free Motion-Guided Video Generation with Enhanced Temporal Consistency Using Motion Consistency Loss](https://mlsanity.com/paper/2501.07563/) (2025)
- [Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy](https://mlsanity.com/paper/2510.09012/) (2025)
- [Enhance-A-Video: Better Generated Video for Free](https://mlsanity.com/paper/2502.07508/) (2025)
- [Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality](https://mlsanity.com/paper/2406.08845/) (2024)
- [Context Guided Transformer Entropy Modeling for Video Compression](https://mlsanity.com/paper/2508.01852/) (2025)

## Built on by (most cited first, 1 of 1)

- [GAD: Geometry Attention Distillation for Consistent Video Generation](https://mlsanity.com/paper/2610.18779/) (2026)

## Abstract (arXiv)

Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze local attention entropy, but these views do not reveal whether temporal interactions stay in a healthy transport regime. In this work, we study video generation through the perspective of Temporal State Transport. We introduce Spectral Tension, a signed diagnostic that compares local attention diffuseness with global spectral diversity, and use it to identify two opposite temporal failures: fragmented transport and over-mixing hotspots. Based on this diagnosis, we propose Spectral Transport Homeostasis, a training-free regulator that softly corrects pathological temporal states while largely preserving balanced ones. Experiments on pretrained video generation models show that the original model often occupies imbalanced temporal regimes, whereas our method selectively applies larger corrections to the worst temporal hotspots and improves temporal consistency and visual quality without finetuning. Code: https://github.com/lytang63/temporal-state-transport