Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

arXiv 2026 22.3 system

TLDR

Embodied.cpp is a portable C++ inference runtime for embodied AI models, enabling multi-rate execution and latency-first inference on heterogeneous robots.

Reasoning

The paper addresses a practical deployment challenge with a modular five-layer architecture and demonstrates high task success rates on VLA models. However, the WAM evaluation is limited to a single block, and there is no comparison to existing runtimes, making the contribution primarily engineering.

Read-first score

Read-first score 22.3, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 2.

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=analysis,benchmark,result

Reproducibility 18%

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

Topical relevance 29%

2.9

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: 39.

Keyword Scores

world model

world simulator

generative world model

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper