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

arXiv:2605.30263 · cs.CV · Submitted 2026-05-28 · Read on arXiv

cs.CV

Submitted: 2026-05-28

Updated: 2026-09-22

Code: https://github.com/shengshu-ai/minWM

Terminology

• World Model — 48× in this paper · explained in 7 episodes
• Distillation — 29× in this paper · explained in 2 episodes
• Diffusion Model — 28× in this paper · explained in 8 episodes
• Foundation Model — 11× in this paper · explained in 3 episodes
• Diffusion Models — 9× in this paper · explained in 6 episodes
• Foundation Models — 9× in this paper · explained in 7 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Consistency — 7× in this paper · explained in 3 episodes
• Consistency Distillation — 5× in this paper · explained in 2 episodes
• AR Diffusion Distillation — 3× in this paper · explained in 1 episode
• Ablation Studies — 2× in this paper · explained in 1 episode
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Closed-Loop Control — 1× in this paper · explained in 2 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes

Sources

• Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• Open-Sora Plan: Open-Source Large Video Generation Model
• Open-Sora: Democratizing Efficient Video Production for All
• Wan: Open and Advanced Large-Scale Video Generative Models
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model
• Yume-1.5: A Text-Controlled Interactive World Generation Model
• Vidarc: Embodied Video Diffusion Model for Closed-loop Control
• Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
• StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
• RELIC: Interactive Video World Model with Long-Horizon Memory
• Yan: Foundational Interactive Video Generation
• PAN: A World Model for General, Actionable, and Long-Horizon World Simulation
• Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
• MotionStream: Real-Time Video Generation with Interactive Motion Controls
• Diffusion Adversarial Post-Training for One-Step Video Generation
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models