Learning to Propagate Interaction Effects for Modeling Deformable Linear Objects Dynamics

arXiv 2021 28.8 method, application

TLDR

This paper proposes a recurrent interaction network to model full 3D dynamics of deformable linear objects from synthetic and real data, enabling accurate predictions and shape control.

Reasoning

The paper introduces a novel architecture for DLO dynamics and validates with synthetic and real-world experiments, which is a strength. However, the scope is narrowly focused on deformable linear objects and does not relate to general world models or simulators beyond that specific task.

Read-first score

Read-first score 28.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 5.

Citation impact 15%

98.8

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.98843142

Recency 5%

Uses a gentle age decay so recent papers surface without erasing older foundations. 2021

Citation velocity 10%

36.2

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=4.83

Methodology quality 15%

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

Graph prestige 15%

10.6

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0030

Topical relevance 25%

7.1

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

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=False; code=False; dataset=False; markers=none

Field roles

Foundation

Rank sensitivity

Stability: volatile; rank range: 658.

Keyword Scores

world dynamics prediction

world model

interactive world model

model-based reinforcement learning world model

world simulator

generative world model

video world model