# STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

arXiv: https://arxiv.org/abs/2511.20462 · HTML: https://mlsanity.com/paper/2511.20462/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 73 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 30 of 62)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (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)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [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)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)

## Built on by (most cited first, 9 of 9)

- [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://mlsanity.com/paper/2512.15702/) (2025)
- [One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation](https://mlsanity.com/paper/2512.07829/) (2025)
- [SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows](https://mlsanity.com/paper/2512.04084/) (2025)
- [Latent Reasoning with Normalizing Flows](https://mlsanity.com/paper/2606.06447/) (2026)
- [Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation](https://mlsanity.com/paper/2607.27372/) (2026)
- [STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation](https://mlsanity.com/paper/2605.08029/) (2026)
- [Normalizing Trajectory Models](https://mlsanity.com/paper/2605.08078/) (2026)
- [Joint Flow Matching for Generator-Consistent Classification](https://mlsanity.com/paper/2607.23946/) (2026)
- [Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction](https://mlsanity.com/paper/2609.00610/) (2026)

## Abstract (arXiv)

Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation. Building upon the recently proposed STARFlow, STARFlow-V operates in the spatiotemporal latent space with a global-local architecture which restricts causal dependencies to a global latent space while preserving rich local within-frame interactions. This eases error accumulation over time, a common pitfall of standard autoregressive diffusion model generation. Additionally, we propose flow-score matching, which equips the model with a light-weight causal denoiser to improve the video generation consistency in an autoregressive fashion. To improve the sampling efficiency, STARFlow-V employs a video-aware Jacobi iteration scheme that recasts inner updates as parallelizable iterations without breaking causality. Thanks to the invertible structure, the same model can natively support text-to-video, image-to-video as well as video-to-video generation tasks. Empirically, STARFlow-V achieves strong visual fidelity and temporal consistency with practical sampling throughput relative to diffusion-based baselines. These results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation, establishing them as a promising research direction for building world models. Code and generated samples are available at https://github.com/apple/ml-starflow.