MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception

arXiv 2026 20.8 method

TLDR

MinkowskiPE introduces Lorentz-transformation-based positional encoding for spatiotemporal attention, improving molecular dynamics and video prediction with fewer parameters.

Reasoning

The paper's strength is an explicit relative spacetime bias in attention while preserving efficient dot-product interfaces, with strong empirical gains on molecular and KTH video tasks. Weaknesses include limited evidence of generalizability beyond the evaluated domains and no stated connection to world-model capabilities.

Read-first score

Read-first score 20.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 4.

Recency 5%

100

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

Methodology quality 15%

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

Reproducibility 15%

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

Topical relevance 25%

5.7

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

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Citation impact 15%

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

Citation velocity 10%

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 128.

Keyword Scores

world dynamics prediction

world model

video world model

world simulator

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper