跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25243 · v1

Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans

首次提交 2026-11-19 06:22
版本更新 2026-11-19 06:22
雷达观测 2026-11-21 12:18
arXiv ↗PDF ↗

摘要

Vision-Language Models (VLMs) can propose multi-step manipulation plans, but they have no grounded model of how a scene will change, and the pixel-level world models that could check those plans are slow and drift over long horizons. We present Verify2Act, a modular verification framework that separates semantic action proposal from latent physical verification. A VLM proposes candidate plans, a latent world model (V2A-WM) imagines each of them in the DINOv2 feature space, and a dual-head critic checks the imagined rollouts for temporal consistency and goal satisfaction before anything is executed. V2A-WM extends recent flow-matching world models with cross-attention action grounding and a causal temporal history window. We deploy the full system on a low-cost robot arm, training the world model and critic only on data generated in a digital twin. Across six language-conditioned tasks, Verify2Act reaches 83.3\% task success, compared with 61.7\% for a latent world model without our architectural changes, 53.3\% for the VLM alone, and 46.7\% for a pixel-diffusion world model. It verified every plan it executed and incurred no planning-induced failures: all of its failed episodes were caused by low-level grasp or placement slips. In simulation, Verify2Act obtains the highest five-task chain success on CALVIN among the compared baselines with 30×\times fewer reflective VLM calls than pixel-diffusion verification, and the highest success on cluttered nut assembly.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 06:22 · 最新观测版本

Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans

Vision-Language Models (VLMs) can propose multi-step manipulation plans, but they have no grounded model of how a scene will change, and the pixel-level world models that could check those plans are slow and drift over long horizons. We present Verify2Act, a modular verification framework that separates semantic action proposal from latent physical verification. A VLM proposes candidate plans, a latent world model (V2A-WM) imagines each of them in the DINOv2 feature space, and a dual-head critic checks the imagined rollouts for temporal consistency and goal satisfaction before anything is executed. V2A-WM extends recent flow-matching world models with cross-attention action grounding and a causal temporal history window. We deploy the full system on a low-cost robot arm, training the world model and critic only on data generated in a digital twin. Across six language-conditioned tasks, Verify2Act reaches 83.3\% task success, compared with 61.7\% for a latent world model without our architectural changes, 53.3\% for the VLM alone, and 46.7\% for a pixel-diffusion world model. It verified every plan it executed and incurred no planning-induced failures: all of its failed episodes were caused by low-level grasp or placement slips. In simulation, Verify2Act obtains the highest five-task chain success on CALVIN among the compared baselines with 30×\times fewer reflective VLM calls than pixel-diffusion verification, and the highest success on cluttered nut assembly.

查看此版本解读 →查看此版本原文 ↗