RISE: Adaptive Imagination for World Action Models

arXiv 2026 32.3 method, system, benchmark, application

TLDR

RISE adaptively decides when to stop imagination rollout in World Action Models, using a Latent Evaluator and Rollout Gate, with CounterDrive counterfactual data; outperforms on NAVSIM and nuScenes.

Reasoning

The paper introduces a novel adaptive computation mechanism for world action models, supported by a counterfactual dataset and strong empirical validation on driving benchmarks. Weaknesses include limited visible detail on the Latent Evaluator/Rollout Gate architecture and potential reliance on dataset-specific annotations.

Read-first score

Read-first score 32.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 26.

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=dataset,experiment,result

Reproducibility 18%

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

Topical relevance 29%

37.1

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

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: 133.

Keyword Scores

world model

world dynamics prediction

world simulator

generative world model

model-based reinforcement learning world model

interactive world model

video world model

Resources

Paper