minWM: 用于实时交互式视频世界模型的全栈开源框架
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
AI总结：
提出minWM全栈开源框架，通过因果强制/因果强制++流水线将双向视频扩散模型转化为可控制、低延迟的自回归世界模型，支持相机控制与多种骨干架构。
摘要：
最近的视频扩散基础模型在高品质视频生成方面取得了显著进展，但将其转化为实时交互式视频世界模型仍然具有挑战性。交互式世界模型需要可控、因果和低延迟的展开，这在实际中需要涵盖数据构建、可控微调、自回归训练、少步蒸馏和流式推理的完整流水线。在这项工作中，我们提出了minWM，一个用于构建实时交互式视频世界模型的全栈开源框架。minWM提供了一个端到端流水线，将现有的双向T2V/TI2V视频基础模型转化为相机可控的少步自回归世界模型。具体来说，minWM首先微调一个带有相机控制的双向视频扩散模型，然后应用因果强制/因果强制++流水线，包括AR扩散训练、因果ODE或因果一致性蒸馏以及非对称DMD，将其蒸馏为少步自回归生成器以实现低延迟展开。该框架是模块化和架构可扩展的：我们在代表性开源骨干上实例化它，包括Wan2.1-T2V-1.3B和HY1.5-TI2V-8B，覆盖了基于交叉注意力的条件注入和MMDiT风格架构。minWM还支持将现有的视频世界模型（如HY-WorldPlay）适应到新的数据分布、训练配方和延迟目标。除了发布可运行脚本、检查点、文档和推理代码外，我们还提供了关于相机轨迹质量、可控性训练步骤和最小批量大小要求的实际消融实验。我们希望minWM能够作为构建和适应实时交互式视频世界模型的可复现和可扩展的配方。
英文摘要：
Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-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 a bidirectional video diffusion model with camera control, and then applies the Causal Forcing / Causal Forcing++ pipeline, including AR diffusion training, causal ODE or causal consistency distillation, and asymmetric DMD, to distill it into a few-step autoregressive generator for low-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 both cross-attention-based condition injection and MMDiT-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)
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
