AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning

Yilun Hao, Yongchao Chen, Chuchu Fan, Yang Zhang

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add prescreening (ablation)VLMFP · 6 grid worlds avg (seen appearance)success rate (%): 47.5 -> 70.0Improved
add simulation feedback (ablation)VLMFP · 6 grid worlds avg (seen appearance)success rate (%): 61.1 -> 70.0Improved
add PDDL updating (ablation)VLMFP · 6 grid worlds avg (seen appearance)success rate (%): 30.7 -> 70.0Improved
add prescreening on Frozenlake (ablation)VLMFP · Frozenlake (seen appearance)success rate (%): 94.3 -> 95.2No clear effect
add feedback on Frozenlake (ablation)VLMFP · Frozenlake (seen appearance)success rate (%): 95.5 -> 95.2Hurt
use VLMFP instead of CodePDDL (GPT-4o)GPT-4o · 6 grid worlds avg (seen appearance)success rate (%): 30.7 -> 70.0Improved
use VLMFP instead of CodePDDL on unseen appearanceGPT-4o · 6 grid worlds avg (unseen appearance)success rate (%): 32.3 -> 54.1Improved
use VLMFP instead of CodePDDL on SokobanGPT-4o · Sokoban (unseen appearance)success rate (%): 0.4 -> 25.1Improved
use GPT-5 instead of GPT-4o for direct planningDirect · 6 grid worlds avg (seen appearance)success rate (%): 1.3 -> 11.8Improved
use CoT instead of direct prompting with GPT-5GPT-5 · 6 grid worlds avg (seen appearance)success rate (%): 11.8 -> 12.7No clear effect
test SimVLM on unseen instead of seen appearance (task description)SimVLM · 6 grid worlds avgstring matching rate (%): 95.5 -> 82.6Hurt
test SimVLM on unseen instead of seen appearance (all outputs)SimVLM · 6 grid worlds avgstring matching rate (%): 87.3 -> 86.0No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy