# DreamX-World 1.0 — Alibaba AMAP open-sources an interactive world model

> Open-source 5B world model that lets you steer the camera, revisit a scene, and stage events across photoreal, game, and stylized worlds.

- Org: AMAP-ML
- Date: 2026-06-15
- Category: paper, algorithm, model
- Source: https://arxiv.org/abs/2606.16993
- Canonical page: https://ai-tldr.dev/releases/amap-dreamx-world-1/

## In short

Alibaba's AMAP research team releases a 5B Apache-2.0 video world model with camera navigation, scene revisit, and event control across photoreal, game-style, and stylized domains. Code, paper, and two checkpoints are out.

## What it is

DreamX-World 1.0 is an interactive video world model from Alibaba's AMAP research group. You give it a starting image or prompt plus camera moves and event instructions, and it generates a coherent video the agent or player can navigate inside.

## How it works

The model uses a progressive training pipeline that adds camera-aware conditioning, geometry-guided memory for scene revisit, structured event instruction tuning, autoregressive long-video generation with distillation, and a reinforcement-learning quality pass. A technique the authors call Efficient PRoPE projects positional encodings to spatially reduced tokens, cutting inference latency by about 30% versus full PRoPE.

## Why it matters

World models that combine free camera control with memory across revisits and named events have mostly been closed (Project Genie, Decart Oasis). Shipping a 5B Apache-2.0 checkpoint that reaches 16 fps on eight RTX 5090s puts a comparable system in researchers' hands. AMAP reports a 57–62% human-preference win rate over HY-WorldPlay 1.5 and LingBot-World on the same evaluation.

## Who it's for

world-model researchers, robotics simulation teams, game engine experiments

## Try it

https://github.com/AMAP-ML/DreamX-World

## Quick facts

- Maker: AMAP-ML (Alibaba AMAP research team)
- License: Apache-2.0 (open source)
- Parameters: 5B
- Checkpoints: Two (5B and 5B-Cam) on Hugging Face
- Speed: Up to 16 FPS on eight RTX 5090 GPUs
- Overall score: 84.76 (vs 80.79 HY-WorldPlay 1.5, 80.45 LingBot-World)
- What it does: Interactive video world model with camera control, scene revisit, and event control

## FAQ

### Is DreamX-World open source?

Yes. DreamX-World 1.0 is released by Alibaba's AMAP research team under the Apache-2.0 license. The team published the code on GitHub, the paper on arXiv, a project page, and two model checkpoints (5B and 5B-Cam) on Hugging Face, so researchers can download and run the system directly.

### What does DreamX-World do?

DreamX-World is an interactive video world model. You give DreamX-World a starting image or prompt plus camera moves and event instructions, and DreamX-World generates a coherent video you can navigate inside. It supports free camera control, scene revisit with memory, and named event control across photoreal, game-style, and stylized worlds.

### How fast is DreamX-World?

DreamX-World reaches up to 16 FPS when running on eight RTX 5090 GPUs. The model uses optimizations such as mixed-precision DiT execution, residual reuse, 75%-pruned VAE decoding, and asynchronous pipeline parallelism. A technique the authors call Efficient PRoPE cuts inference latency by about 30 percent compared with full PRoPE.

### How does DreamX-World compare to other world models?

On its evaluation, DreamX-World scores 84.76 overall, ahead of HY-WorldPlay 1.5 at 80.79 and LingBot-World at 80.45, with a camera-control score of 73.75. AMAP reports a 57 to 62 percent human-preference win rate over HY-WorldPlay 1.5 and LingBot-World on the same evaluation. Earlier comparable systems, such as Project Genie and Decart Oasis, have mostly stayed closed.

## Links

- [Paper (arXiv)](https://arxiv.org/abs/2606.16993)
- [Project Page](https://amap-ml.github.io/DreamX_World)
- [Code](https://github.com/AMAP-ML/DreamX-World)
- [Model (5B)](https://huggingface.co/GD-ML/DreamX-World-5B)
- [Model (5B Cam)](https://huggingface.co/GD-ML/DreamX-World-5B-Cam)