Paper page - ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

Source: https://huggingface.co/papers/2608.14022 Authors:

,

,

,

,

,

,

,

,

,

Abstract

ForgeWM progressively distills bidirectional video generators into efficient few-step interactive world models with aligned discrete and continuous controls, supporting low-latency interaction and replay-time refinement.

Action-conditioned video world modelsrequire low-latency causal generation and reliable responses to game-native controls. Althoughcausal distillationenables one- orfew-step video synthesis, extending it to interactive world models remains challenging, as discrete keyboard states and continuous mouse motion must remain aligned with temporally compressedlatent chunksduring causal training andautoregressive 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, andon-policy distribution matchingwith abidirectional 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 optionalreplay-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 refinementmatches 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.

View arXiv pageView PDFProject pageGitHub76Add to collection

Get this paper in your agent:

hf papers read 2608\.14022

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

Models citing this paper1

#### ForgeWM/ForgeWM

Datasets citing this paper1

#### ForgeWM/ForgeWM-data

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.14022 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.