Skip to content

Source paper

Solaris: Building a Multiplayer Video World Model in Minecraft

Georgy Savva, Oscar Michel, Daohan Lu and 6 more

Georgy Savva, Oscar Michel, Daohan Lu, Suppakit Waiwitlikhit, Timothy Meehan, Dhairya Mishra, Srivats Poddar, Jack Lu, Saining Xie

arXiv 2602.22208 · 202617 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper introduces Solaris, a multiplayer video world model for Minecraft capable of simulating consistent multi-view observations for two agents. To achieve this, the authors built a scalable data generation engine (SolarisEngine), collected a large synthetic dataset, and trained a modified Diffusion Transformer (DiT) using a novel "Checkpointed Self Forcing" technique to enable memory-efficient long-horizon autoregressive training.

How it works (AI summary)

The model is a Video Diffusion Transformer (DiT) based on Matrix Game 2.0, modified to process joint states of multiple players via a shared self-attention mechanism. Training follows a staged pipeline: single-player pretraining, bidirectional multiplayer finetuning, causal masking, and finally Checkpointed Self Forcing, which allows gradients to flow through long autoregressive chains by recomputing intermediate states to save memory.