Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Justin Cui et al.
arXiv:2510.02283
In short
Video models distilled from short-clip teachers fall apart when asked to generate longer than the teacher ever did. Self-Forcing++ has the teacher correct segments of the student’s own long generations, extending coherent video up to 20× past the teacher’s horizon, to over four minutes.
Why it matters
It shows a way to long video without long training videos or long-video teachers.
Read first
The 4 Field Guide ideas this paper leans on.
Starting from scratch? The full route 15 ideas · basics first
- Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
- Neural Network ✓ understood
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.
- Diffusion Model · read first ✓ understood
A generative model that learns to denoise data, achieving state-of-the-art image generation (Stable Diffusion, DALL-E 2).
- Natural Language Processing ✓ understood
The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.
- Token ✓ understood
The basic unit of text that a language model processes, typically representing a word, subword, or character. Tokens are the fundamental building blocks for LLM input and output.
- Tokenization ✓ understood
Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.
- Language Modeling ✓ understood
Learning probability distributions over sequences of words to predict what comes next.
- Autoregressive Model · read first ✓ understood
A model that generates output one token at a time, using previously generated tokens as input for the next prediction.
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Training ✓ understood
The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.
- Activation Function ✓ understood
A non-linear function applied to neuron outputs that introduces non-linearity, enabling networks to learn complex patterns.
- Softmax ✓ understood
A function that turns a list of scores (logits) into probabilities that are all positive and sum to 1; the standard output of classifiers and language models.
- Knowledge Distillation ✓ understood
Training a smaller 'student' model to mimic a larger 'teacher' model, transferring knowledge while reducing size.
- Teacher Model · read first ✓ understood
The larger, more accurate model in knowledge distillation that guides student training.
- Student Model · read first ✓ understood
The smaller model in knowledge distillation learning to mimic the teacher's behavior.
In the frontier
- Rank
- #29 of 100
- Citations
- 156
- as of Aug 9, 2026
- Published
- Oct 2025
Topics: Video generation and world models , RL for reasoning , Efficiency and serving
Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026