DreamX-World 1.0: A General-Purpose Interactive World Model

Published
Source
arXiv
Paper number
423
Field
Computer Vision
arXiv ID
2606.16993

Key points

  • E-PRoPE applies PRoPE's projection camera geometry to spatially reduced tokens, reducing inference latency by about 30%.
  • Memory-Conditioned Scene Persistence maintains scene consistency when revisiting previously observed areas through camera-geometry-based retrieval.
  • Causal forcing, DMD distillation, and long-rollout training reduce autoregressive chunk accumulation drift, including style and color drift.
  • On 8x RTX 5090, it streams at up to 16 FPS using mixed-precision DiT, residual reuse, 75% pruned VAE decoding, and asynchronous pipeline parallelism.

Paper links

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

Read original (opens in a new tab)