Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.23993 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917541982502912 |
|---|---|
| author | Huang, Siqiao Kaushik, Partha Chen, Michael Pan, Hengkai Geng, Kaiwen Chehab, Omar Moreno-Pino, Fernando Simchowitz, Max |
| author_facet | Huang, Siqiao Kaushik, Partha Chen, Michael Pan, Hengkai Geng, Kaiwen Chehab, Omar Moreno-Pino, Fernando Simchowitz, Max |
| contents | World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research community still lacks compact, reproducible, and easily extensible implementations for studying the design choices underlying modern world models. We introduce Nano World Models, a minimalist codebase for future video prediction centered around diffusion forcing. Nano World Models provides a unified interface for generative objectives, model scales, action-conditioning mechanisms, latent observation spaces, datasets, evaluation protocols, and long-horizon rollout procedures. This design enables controlled studies of world-modeling components that are often entangled across separate implementations. Through experiments across simple control environments, game simulation, and real-robot data, we examine how prediction parameterization, architecture scale, action injection, sampling budget, and domain complexity affect video prediction quality and autoregressive rollout behavior. By releasing code, configurations, evaluation scripts, and pretrained checkpoints, Nano World Models aims to provide a compact yet extensible experimental substrate for open, reproducible, and scientific world-model research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23993 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Nano World Models: A Minimalist Implementation of Future Video Prediction Huang, Siqiao Kaushik, Partha Chen, Michael Pan, Hengkai Geng, Kaiwen Chehab, Omar Moreno-Pino, Fernando Simchowitz, Max Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research community still lacks compact, reproducible, and easily extensible implementations for studying the design choices underlying modern world models. We introduce Nano World Models, a minimalist codebase for future video prediction centered around diffusion forcing. Nano World Models provides a unified interface for generative objectives, model scales, action-conditioning mechanisms, latent observation spaces, datasets, evaluation protocols, and long-horizon rollout procedures. This design enables controlled studies of world-modeling components that are often entangled across separate implementations. Through experiments across simple control environments, game simulation, and real-robot data, we examine how prediction parameterization, architecture scale, action injection, sampling budget, and domain complexity affect video prediction quality and autoregressive rollout behavior. By releasing code, configurations, evaluation scripts, and pretrained checkpoints, Nano World Models aims to provide a compact yet extensible experimental substrate for open, reproducible, and scientific world-model research. |
| title | Nano World Models: A Minimalist Implementation of Future Video Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.23993 |