LongLive: Real-time Interactive Long Video Generation
Shuai Yang et al.
arXiv:2509.22622
In short
LongLive generates long videos frame by frame in real time while the user changes the prompt mid-stream. It refreshes cached attention state on prompt switches, trains on long videos to match how it runs, and uses short-window attention with an anchor frame to stay consistent.
Why it matters
Minute-long, steerable video at 20 frames per second on one GPU makes interactive video generation real.
Read first
The 3 Field Guide ideas this paper leans on.
Starting from scratch? The full route 17 ideas · basics first
- 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 unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.
- 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
Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.
- 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.
- 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 model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Feature ✓ understood
A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.
- Deep Learning ✓ understood
A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.
- Representation Learning ✓ understood
Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand.
- Embedding ✓ understood
A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.
- Attention Mechanism ✓ understood
A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.
- Self-Attention · read first ✓ understood
An attention step in which every token in a sequence looks at every token in that same sequence and builds a new representation from a weighted mix of them.
- 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.
- Inference ✓ understood
Running a trained model on new inputs to get predictions, with its weights frozen: the stage of a model's life that users actually interact with.
- Inference Latency · read first ✓ understood
The time delay between submitting input and receiving output from a deployed model, critical for real-time applications.
In the frontier
- Rank
- #20 of 100
- Citations
- 189
- as of Aug 9, 2026
- Published
- Sep 2025
Topics: Video generation and world models , Efficiency and serving , Long context and attention
Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026