# S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation

arXiv: https://arxiv.org/abs/2610.06847 · HTML: https://mlsanity.com/paper/2610.06847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

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

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

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Action-Conditional Video Prediction using Deep Networks in Atari Games](https://mlsanity.com/paper/1507.08750/) (2015)
- [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [On the Content Bias in Fr'echet Video Distance](https://mlsanity.com/paper/2404.12391/) (2024)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation](https://mlsanity.com/paper/2505.00337/) (2025)
- ["PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models](https://mlsanity.com/paper/2507.13428/) (2025)
- [Multiplayer Interactive World Models with Representation Autoencoders](https://mlsanity.com/paper/2607.05352/) (2026)
- [Back to Basics: Let Denoising Generative Models Denoise](https://mlsanity.com/paper/2511.13720/) (2025)
- [The Serial Scaling Hypothesis](https://mlsanity.com/paper/2507.12549/) (2025)
- [PhyGround: Benchmarking Physical Reasoning in Generative World Models](https://mlsanity.com/paper/2605.10806/) (2026)
- [Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model](https://mlsanity.com/paper/2607.03509/) (2026)
- [MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics](https://mlsanity.com/paper/2606.01538/) (2026)
- [VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation](https://mlsanity.com/paper/2512.11061/) (2025)
- [The Seriality Gap in Video Diffusion Models](https://mlsanity.com/paper/2607.13031/) (2026)

## Abstract (arXiv)

Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rules. We introduce Serial-to-Parallel Diffusion (S2PD), which performs autoregressive diffusion at high noise before switching to parallel diffusion at low noise. The autoregressive phase provides the serial computation needed to coordinate interdependent events and produce valid state transitions while the parallel phase jointly refines the entire video and reduces sampling time relative to fully serial generation. We implement S2PD with two architectures: a pixel-space diffusion transformer trained from scratch and a pretrained video model adapted through LoRA fine-tuning with causal attention. Across games, physical simulations, and real video, S2PD follows rules more reliably than matched bidirectional baselines and generates videos with greater temporal stability and sampling efficiency than other serial methods.