Paper page - minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Source: https://huggingface.co/papers/2605.30263 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

A comprehensive framework is presented for converting bidirectional video diffusion models into real-time interactive world models with controllable, causal, and low-latency capabilities through fine-tuning and distillation techniques.

Recentvideo diffusion foundation modelshave achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging.Interactive world modelsrequire controllable, causal, andlow-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipeline that converts existing bidirectional T2V/TI2V video foundation models into camera-controllable few-step autoregressive world models. Specifically, minWM first fine-tunes abidirectional video diffusion modelwith camera control, and then applies theCausal Forcing/Causal Forcing++ pipeline, including AR diffusion training,causal ODEorcausal consistency distillation, andasymmetric DMD, to distill it into afew-step autoregressive generatorforlow-latency rollout. The framework is modular and architecture-extensible: we instantiate it on representative open backbones, including Wan2.1-T2V-1.3B and HY1.5-TI2V-8B, covering bothcross-attention-based condition injectionandMMDiT-style architectures. minWM also supports adapting existing video world models, such as HY-WorldPlay, to new data distributions, training recipes, and latency targets. Beyond releasing runnable scripts, checkpoints, documentation, and inference code, we provide practical ablations on camera trajectory quality, controllability training steps, and minimal batch-size requirements. We hope minWM serves as a reproducible and extensible recipe for building and adapting real-time interactive video world models. Project Page: [https://github.com/shengshu-ai/minWM](https://github.com/shengshu-ai/minWM)

View arXiv pageView PDFGitHubAdd to collection

Get this paper in your agent:

hf papers read 2605\.30263

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.30263 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.30263 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.30263 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.