SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Key points

It converted 1.43 million clips from 10 datasets, totaling at least 25TB, into a unified format containing frame alignment, camera geometry, captions, and quality metadata, enabling experiments with different training mixtures without rerunning preprocessing.
It applied backbone-native adaptations that preserve the original representations and objectives of the structurally different Wan2.2 (5B/14B), LTX-2.5 (22B), and MiniMax-H3 (33B) backbones, producing 4 directly comparable model families.
A simple 3-stage process of bidirectional training, autoregressive adaptation, and distribution matching distillation (DMD, a technique that compresses a large model into a smaller one by training it to imitate the large model's output distribution) achieved leading performance without special initialization.
Despite training only on 5-second sequences, it maintained scene identity and camera responsiveness throughout continuous 60-minute rollouts without fine-tuning on long videos or using attention-sink mechanisms.
Even when initialized with externally generated images from GPT Image 2 or Krea in styles absent from the training data, it generalized by imagining unseen regions and expanding them into explorable worlds.
It released all data, processing pipelines, training recipes, and weights, establishing a reference point for reproducible video world-model research.

External research summaries. These are not HDATF publications or measured product results.