Saved in:
Bibliographic Details
Main Authors: Ziakas, Christos, Bar, Amir, Russo, Alessandra
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.01960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910053489967104
author Ziakas, Christos
Bar, Amir
Russo, Alessandra
author_facet Ziakas, Christos
Bar, Amir
Russo, Alessandra
contents Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal consistency and physical constraints, leading to failures when mapped to executable actions. To address this, we propose Grounding Video Plans with World Models (GVP-WM), a planning method that grounds video-generated plans into feasible action sequences using a learned action-conditioned world model. At test-time, GVP-WM first generates a video plan from initial and goal observations, then projects the video guidance onto the manifold of dynamically feasible latent trajectories via video-guided latent collocation. In particular, we formulate grounding as a goal-conditioned latent-space trajectory optimization problem that jointly optimizes latent states and actions under world-model dynamics, while preserving semantic alignment with the video-generated plan. Empirically, GVP-WM recovers feasible long-horizon plans from zero-shot image-to-video-generated and motion-blurred videos that violate physical constraints, across navigation and manipulation simulation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01960
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Grounding Generated Videos in Feasible Plans via World Models
Ziakas, Christos
Bar, Amir
Russo, Alessandra
Machine Learning
Large-scale video generative models have shown emerging capabilities as zero-shot visual planners, yet video-generated plans often violate temporal consistency and physical constraints, leading to failures when mapped to executable actions. To address this, we propose Grounding Video Plans with World Models (GVP-WM), a planning method that grounds video-generated plans into feasible action sequences using a learned action-conditioned world model. At test-time, GVP-WM first generates a video plan from initial and goal observations, then projects the video guidance onto the manifold of dynamically feasible latent trajectories via video-guided latent collocation. In particular, we formulate grounding as a goal-conditioned latent-space trajectory optimization problem that jointly optimizes latent states and actions under world-model dynamics, while preserving semantic alignment with the video-generated plan. Empirically, GVP-WM recovers feasible long-horizon plans from zero-shot image-to-video-generated and motion-blurred videos that violate physical constraints, across navigation and manipulation simulation tasks.
title Grounding Generated Videos in Feasible Plans via World Models
topic Machine Learning
url https://arxiv.org/abs/2602.01960