# Taming Teacher Forcing for Masked Autoregressive Video Generation

arXiv: https://arxiv.org/abs/2501.12389 · HTML: https://mlsanity.com/paper/2501.12389/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 58 references that are in the map.
- First posted on arXiv 21 Jan 2025.

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [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)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [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)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)

## Built on by (most cited first, 30 of 30)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025)
- [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025)
- [Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation](https://mlsanity.com/paper/2505.05472/) (2025)
- [RELIC: Interactive Video World Model with Long-Horizon Memory](https://mlsanity.com/paper/2512.04040/) (2025)
- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation](https://mlsanity.com/paper/2603.21366/) (2026)
- [Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective](https://mlsanity.com/paper/2507.08801/) (2025)
- [Generative Pre-trained Autoregressive Diffusion Transformer](https://mlsanity.com/paper/2505.07344/) (2025)
- [VideoMAR: Autoregressive Video Generatio with Continuous Tokens](https://mlsanity.com/paper/2506.14168/) (2025)
- [WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception](https://mlsanity.com/paper/2508.15720/) (2025)
- [MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation](https://mlsanity.com/paper/2502.11234/) (2025)
- [Video-GPT via Next Clip Diffusion](https://mlsanity.com/paper/2505.12489/) (2025)
- [Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation](https://mlsanity.com/paper/2605.30083/) (2026)
- [REAR: Rethinking Visual Autoregressive Models via Generator-Tokenizer Consistency Regularization](https://mlsanity.com/paper/2510.04450/) (2025)
- [SemanticGen: Video Generation in Semantic Space](https://mlsanity.com/paper/2512.20619/) (2025)
- [Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation](https://mlsanity.com/paper/2608.13391/) (2026)
- [SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models](https://mlsanity.com/paper/2509.15536/) (2025)
- [AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory](https://mlsanity.com/paper/2606.11751/) (2026)
- [Generative Augmented Reality: Paradigms, Technologies, and Future Applications](https://mlsanity.com/paper/2511.16783/) (2025)
- [CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas](https://mlsanity.com/paper/2510.13669/) (2025)
- [Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization](https://mlsanity.com/paper/2511.22169/) (2025)
- [Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation](https://mlsanity.com/paper/2601.19488/) (2026)
- [GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization](https://mlsanity.com/paper/2603.25020/) (2026)
- [Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs](https://mlsanity.com/paper/2606.01620/) (2026)
- [Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation](https://mlsanity.com/paper/2608.05648/) (2026)
- [SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation](https://mlsanity.com/paper/2608.28694/) (2026)
- [Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning](https://mlsanity.com/paper/2609.30258/) (2026)
- [Unveiling the Value of Motion for Cinematic Camera Trajectories](https://mlsanity.com/paper/2609.38683/) (2026)

## Abstract (arXiv)

We introduce MAGI, a hybrid video generation framework that combines masked modeling for intra-frame generation with causal modeling for next-frame generation. Our key innovation, Complete Teacher Forcing (CTF), conditions masked frames on complete observation frames rather than masked ones (namely Masked Teacher Forcing, MTF), enabling a smooth transition from token-level (patch-level) to frame-level autoregressive generation. CTF significantly outperforms MTF, achieving a +23% improvement in FVD scores on first-frame conditioned video prediction. To address issues like exposure bias, we employ targeted training strategies, setting a new benchmark in autoregressive video generation. Experiments show that MAGI can generate long, coherent video sequences exceeding 100 frames, even when trained on as few as 16 frames, highlighting its potential for scalable, high-quality video generation.