# ForgeWM：面向少步动作条件视频世界模型的渐进式因果训练

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-14 15:13
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmt2b5r5c0mjjroov51wpx2va
- 原文链接：https://arxiv.org/abs/2608.14022

## AI 摘要

ForgeWM 提出一种渐进式框架，将双向动作条件视频生成器转化为高效的少步世界模型，通过域适应、教师强制因果训练、因果一致性蒸馏及与双向教师模型的在线策略分布匹配，得到稳态去噪预算为 1、2、4 步的专用学生模型。

## 正文

Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillation enables one- or few-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressed latent chunks during causal training and autoregressive rollout. We introduce ForgeWM, a progressive framework that transforms a bidirectional action-conditioned video generator into efficient few-step world models through domain adaptation, teacher-forced causal training, causal consistency distillation, and on-policy distribution matching with a bidirectional teacher. The resulting budget-specialized students operate at steady-state denoising budgets of 1, 2, and 4 steps. ForgeWM further supports a dual-path deployment protocol combining latency-critical interaction with optional replay-time refinement, where the one-step student re-noises and refines its saved draft. On paired Minecraft trajectories, ForgeWM leads the evaluated systems in Imaging Quality, reference-aligned motion-profile agreement, action-sign accuracy, and mouse-control accuracy, while achieving the lowest reference LPIPS; the same four-stage recipe transfers to gamepad-controlled FPS gameplay. Replay-time refinement matches four-step reference quality while remaining roughly three times closer to the experienced trajectory than regeneration from noise. These results demonstrate ForgeWM's effectiveness for controllable few-step video generation.