Looped World Models
- Published
- Source
- arXiv
- Paper number
- 437
- Field
- Machine Learning
- arXiv ID
- 2606.18208
Key points
- It is the first application of a looped transformer to a world model and proposes iterative latent depth as a new scaling axis.
- By repeating a shared transformer block, it achieves up to 100 times better parameter efficiency than prior designs.
- A spectrally constrained state-retention parameterization guarantees stability over arbitrary rollout lengths.
- Adaptive computation automatically assigns more loops to complex transitions such as collisions and contacts and fewer loops to simple dynamics.
- It achieves 66 to 88 percent EM and 72 to 98 percent F1 on scientific simulation tasks such as ScienceWorld.
- With only 1B parameters, it demonstrates better predictive performance on scientific simulation than Gemini and Qwen.
Paper links
External research summaries. These are not HDATF publications or measured product results.