# Diffusion for World Modeling: Visual Details Matter in Atari

*Source* · `src-alonso-2024-diamond` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, François Fleuret |
| venue | NeurIPS 2024 |
| date | 2024-05 |
| url | https://diamond-wm.github.io/ |
| arxiv | 2405.12399 |
| accessed | 2026-10-24 |

## Notes

DIAMOND: Atari 100k mean HNS 1.46. CS:GO world model from 87 h of human play, about 10 fps on an RTX 3090, trained 12 days on an RTX 4090; allows repeated jumps the real game forbids.

## Backlinks (computed)

**cited by:** [Diffusion and autoregressive neural game engines](../technique/diffusion-game-engines.md)

## Citation

Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, François Fleuret (2024-05). *Diffusion for World Modeling: Visual Details Matter in Atari*. NeurIPS 2024 https://diamond-wm.github.io/

---
Provenance: created in run `2026-10-24-techniques-world-models`.