# The Seriality Gap in Video Diffusion Models

arXiv: https://arxiv.org/abs/2607.13031 · HTML: https://mlsanity.com/paper/2607.13031/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 32)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [Benefits of depth in neural networks](https://mlsanity.com/paper/1602.04485/) (2016)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [The Parallelism Tradeoff: Limitations of Log-Precision Transformers](https://mlsanity.com/paper/2207.00729/) (2022)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [Training Very Deep Networks](https://mlsanity.com/paper/1507.06228/) (2015)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [PHYRE: A New Benchmark for Physical Reasoning](https://mlsanity.com/paper/1908.05656/) (2019)
- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [ARTboldsymbol·V: Auto-Regressive Text-to-Video Generation with Diffusion Models](https://mlsanity.com/paper/2311.18834/) (2023)
- [Progressive Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2410.08151/) (2024)
- [Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems](https://mlsanity.com/paper/2504.02918/) (2025)
- [Theoretical limitations of multi-layer Transformer](https://mlsanity.com/paper/2412.02975/) (2024)
- [T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation](https://mlsanity.com/paper/2505.00337/) (2025)
- [On the Scalability of Diffusion-based Text-to-Image Generation](https://mlsanity.com/paper/2404.02883/) (2024)
- [A Very Big Video Reasoning Suite](https://mlsanity.com/paper/2602.20159/) (2026)
- [Whole-Body Conditioned Egocentric Video Prediction](https://mlsanity.com/paper/2506.21552/) (2025)
- [Demystifying Video Reasoning](https://mlsanity.com/paper/2603.16870/) (2026)
- [Temporal Regularization Makes Your Video Generator Stronger](https://mlsanity.com/paper/2503.15417/) (2025)
- [Video Models Reason Early: Exploiting Plan Commitment for Maze Solving](https://mlsanity.com/paper/2603.30043/) (2026)

## Built on by (most cited first, 2 of 2)

- [How Does Geometry Enter Generated Motion?](https://mlsanity.com/paper/2610.05135/) (2026)
- [S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation](https://mlsanity.com/paper/2610.06847/) (2026)

## Abstract (arXiv)

When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard-sphere dynamics, we find that the performance of standard bidirectional video diffusion degrades as the causal chain lengthens, even when provided more denoising steps. In a length-matched single-ball control, where ball-ball interactions are absent, the degradation largely disappears, isolating dependent-event structure rather than video length as the cause. Across intervention studies, methods that increase effective serial computation improve performance disproportionately, including autoregressive/blockwise generation and architectural depth. We identify this pattern as the seriality gap: a mismatch between tasks requiring growing serial computation and video diffusion models whose denoising loop does not provide scalable serial compute. We then prove that, for deterministic video prediction, denoising steps do not add serial computation beyond the backbone, indicating a structural obstacle for video diffusion on serial reasoning and simulation tasks.