# Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective

arXiv: https://arxiv.org/abs/2507.08801 · HTML: https://mlsanity.com/paper/2507.08801/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 90 of its 101 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Placed in

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

## Builds on (most cited first, 30 of 90)

- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [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)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [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)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)

## Built on by (most cited first, 22 of 22)

- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation](https://mlsanity.com/paper/2512.04678/) (2025)
- [Code2Video: A Code-centric Paradigm for Educational Video Generation](https://mlsanity.com/paper/2510.01174/) (2025)
- [From Pixels to Words -- Towards Native Vision-Language Primitives at Scale](https://mlsanity.com/paper/2510.14979/) (2025)
- [PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache](https://mlsanity.com/paper/2601.04359/) (2026)
- [Uniform Discrete Diffusion with Metric Path for Video Generation](https://mlsanity.com/paper/2510.24717/) (2025)
- [VideoWorld 2: Learning Transferable Knowledge from Real-world Videos](https://mlsanity.com/paper/2602.10102/) (2026)
- [Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://mlsanity.com/paper/2512.09924/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL](https://mlsanity.com/paper/2512.03556/) (2025)
- [Endless World: Real-Time 3D-Aware Long Video Generation](https://mlsanity.com/paper/2512.12430/) (2025)
- [Stream-T1: Test-Time Scaling for Streaming Video Generation](https://mlsanity.com/paper/2605.04461/) (2026)
- [Next Tokens Denoising for Speech Synthesis](https://mlsanity.com/paper/2507.22746/) (2025)
- [TV2TV: A Unified Framework for Interleaved Language and Video Generation](https://mlsanity.com/paper/2512.05103/) (2025)
- [Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering](https://mlsanity.com/paper/2601.09697/) (2026)
- [OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens](https://mlsanity.com/paper/2603.02138/) (2026)
- [Generative Refinement Networks for Visual Synthesis](https://mlsanity.com/paper/2604.13030/) (2026)
- [FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis](https://mlsanity.com/paper/2603.07192/) (2026)
- [SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory](https://mlsanity.com/paper/2603.11746/) (2026)
- [RFDM: Residual Flow Diffusion Model for Efficient Causal Video Editing](https://mlsanity.com/paper/2602.06871/) (2026)
- [Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation](https://mlsanity.com/paper/2601.19488/) (2026)

## Abstract (arXiv)

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an LLM-based unified model for AR video generation with efficient discrete diffusion. Firstly, to fit videos with LLMs, we identify that 1D RoPE is ill-suited for visual spatiotemporal correlation modeling, and while demonstrated to be useful, naive 3D RoPE exhibits imbalanced frequency spectra. Therefore, we propose MM-RoPE, which preserves the original textual RoPE while seamlessly accommodating video data with comprehensive frequency spectra and scaled 3D positions. Secondly, to fit the video data's nature and overcome the inefficiency of next-token decoding, we adopt a parallel and mask-based discrete diffusion with the intra-frame bidirectional and inter-frame causal attention masks. Based on this attention mask, we uncover the frame-wise loss imbalance issue caused by spatial information redundancy and propose Autoregressive Discrete Diffusion Forcing, which introduces temporal tube masking during training with a compatible inference-time masking policy to avoid quality degradation. Despite using only 48 GPUs for pre-training and fine-tuning, limited data and a discrete tokenizer, Lumos-1 achieves results surpassing those of Show-o2 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code and models are available at https://github.com/alibaba-damo-academy/Lumos.