Command Palette
Search for a command to run...

Sakana AI and NYU Launch Dream-Cubed to Generate Playable Minecraft Worlds From Tens of Billions of Cubes

aiai-modelingai-research-evals 4 posts · 3 accounts

Sakana AI and NYU released Dream-Cubed, an artificial intelligence system trained on tens of billions of Minecraft cubes to generate playable, editable 3D environments. The project pairs a large-scale dataset with transformer models that treat discrete blocks as tokens, enabling users to mold terrain, structures and maps with block-level control.

The researchers applied discrete and continuous diffusion training objectives to the model, enabling targeted inpainting and large-scale outpainting. The dataset, code and research paper are publicly available to the research community.

From the sources (4 posts)

@sakanaailabs

We are excited to share our latest work, together with @nyuniversity: "Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes." Blog: Paper: Code: https:/

@hardmaru

Dreaming in Voxels: How AI is Generating Playable Minecraft Worlds Generative AI has conquered images, video, text. But what about interactive 3D environments? We trained models on billions of cubes to generate fully playable, structured w

@sakanaailabs

RT @hardmaru: Dreaming in Voxels: How AI is Generating Playable Minecraft Worlds Generative AI has conquered images, video, text. But what…

@togelius

Text and pixels are boring. How about cubes? In Dream-Cubed, a project in collaboration with @SakanaAILabs, we train large generative models on Minecraft maps, and achieve controllable generation. A new frontier for human-AI co-creativity!

Preview built on a synthetic news corpus (16 weeks, Apr–Jul 2026). Impact calls are model reads, not price data.

About Archive