LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving

arXiv 2026 32.8 method, application

TLDR

LWDrive refines VLM trajectories for autonomous driving using layer-wise world-model guidance and future-frame generation supervision.

Reasoning

The paper introduces a novel framework that integrates world-model supervision into VLM hidden states for coarse-to-fine trajectory refinement, which is a strength. However, the abstract lacks explicit real-world evaluation details and may have limited novelty beyond existing world-model approaches.

Read-first score

Read-first score 32.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 27.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,experiment,metric

Topical relevance 29%

38.6

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 118.

Keyword Scores

world model

world dynamics prediction

generative world model

video world model

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper