WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Wenqiang Sun et al.
arXiv:2512.14614
In short
WorldPlay is a streaming video model you can steer with keyboard and mouse, generating 720p at 24 frames per second. It rebuilds its context from geometrically important past frames to stay consistent over long sessions, and a memory-aware distillation keeps it fast.
Why it matters
Interactive, consistent world simulation in real time edges generative video toward playable worlds.
Read first
The 3 Field Guide ideas this paper leans on.
Starting from scratch? The full route 12 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 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.
- Diffusion Model · read first ✓ understood
A generative model trained to remove noise a step at a time, so it can turn pure random noise into a new image, audio clip or other sample.
- Reinforcement Learning ✓ understood
Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.
- Agent ✓ understood
In reinforcement learning, the learner and decision-maker that observes an environment, takes actions and adjusts its behaviour to maximize cumulative reward.
- Environment ✓ understood
In RL, the world the agent interacts with, providing states, accepting actions, and returning rewards.
- World Model · read first ✓ understood
A learned model of environment dynamics that can predict future states, used in model-based RL.
- 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 · read first ✓ understood
Training a smaller 'student' model to mimic a larger 'teacher' model, transferring knowledge while reducing size.
In the frontier
- Rank
- #53 of 100
- Citations
- 97
- as of Aug 9, 2026
- Published
- Dec 2025
Topics: Video generation and world models , 3D and spatial intelligence , Efficiency and serving
Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026