# Next Block Prediction: Video Generation via Semi-Autoregressive Modeling

arXiv: https://arxiv.org/abs/2502.07737 · HTML: https://mlsanity.com/paper/2502.07737/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 77 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 30 of 68)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (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)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)

## Built on by (most cited first, 26 of 26)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation](https://mlsanity.com/paper/2506.09350/) (2025)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [MotionStream: Real-Time Video Generation with Interactive Motion Controls](https://mlsanity.com/paper/2511.01266/) (2025)
- [VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory](https://mlsanity.com/paper/2512.04519/) (2025)
- [Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion](https://mlsanity.com/paper/2602.07775/) (2026)
- [INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling](https://mlsanity.com/paper/2604.07209/) (2026)
- [VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo](https://mlsanity.com/paper/2508.02317/) (2025)
- [Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation](https://mlsanity.com/paper/2512.18741/) (2025)
- [Streaming Autoregressive Video Generation via Diagonal Distillation](https://mlsanity.com/paper/2603.09488/) (2026)
- [Next Forcing: Causal World Modeling with Multi-Chunk Prediction](https://mlsanity.com/paper/2606.11187/) (2026)
- [VideoMAR: Autoregressive Video Generatio with Continuous Tokens](https://mlsanity.com/paper/2506.14168/) (2025)
- [BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2512.12080/) (2025)
- [MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines](https://mlsanity.com/paper/2603.06679/) (2026)
- [Toward Native Multimodal Modeling: A Roadmap](https://mlsanity.com/paper/2605.25343/) (2026)
- [WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion](https://mlsanity.com/paper/2512.19678/) (2025)
- [Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity](https://mlsanity.com/paper/2605.14487/) (2026)
- [Stream-T1: Test-Time Scaling for Streaming Video Generation](https://mlsanity.com/paper/2605.04461/) (2026)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation](https://mlsanity.com/paper/2606.04432/) (2026)
- [In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion](https://mlsanity.com/paper/2608.05237/) (2026)
- [Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity](https://mlsanity.com/paper/2604.07402/) (2026)
- [BlockGPT: Spatio-Temporal Modelling of Rainfall via Frame-Level Autoregression](https://mlsanity.com/paper/2510.06293/) (2025)
- [Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation](https://mlsanity.com/paper/2601.19488/) (2026)
- [Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation](https://mlsanity.com/paper/2606.24982/) (2026)
- [C3-UniMM: Causal Cycle-Consistent Unified Multimodal Modeling via Super Alignment and Shared Decoding Space](https://mlsanity.com/paper/2608.28603/) (2026)

## Abstract (arXiv)

Next-Token Prediction (NTP) is a de facto approach for autoregressive (AR) video generation, but it suffers from suboptimal unidirectional dependencies and slow inference speed. In this work, we propose a semi-autoregressive (semi-AR) framework, called Next-Block Prediction (NBP), for video generation. By uniformly decomposing video content into equal-sized blocks (e.g., rows or frames), we shift the generation unit from individual tokens to blocks, allowing each token in the current block to simultaneously predict the corresponding token in the next block. Unlike traditional AR modeling, our framework employs bidirectional attention within each block, enabling tokens to capture more robust spatial dependencies. By predicting multiple tokens in parallel, NBP models significantly reduce the number of generation steps, leading to faster and more efficient inference. Our model achieves FVD scores of 103.3 on UCF101 and 25.5 on K600, outperforming the vanilla NTP model by an average of 4.4. Furthermore, thanks to the reduced number of inference steps, the NBP model generates 8.89 frames (128x128 resolution) per second, achieving an 11x speedup. We also explored model scales ranging from 700M to 3B parameters, observing significant improvements in generation quality, with FVD scores dropping from 103.3 to 55.3 on UCF101 and from 25.5 to 19.5 on K600, demonstrating the scalability of our approach.