Latent Action Model Architectures in Real-Time Robotic Control: Efficiency Benchmarks and Trade-offs

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How do different architectures for latent action models (e.g., transformers vs. RNNs) compare in terms of inference efficiency when deployed in real-time robotic control, and can this be benchmarked. 5 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How do different architectures for latent action models (e.g., transformers vs. RNNs) compare in terms of inference efficiency when deployed in real-time robotic control, and can this be benchmarked using metrics like latency or throughput on standardized robotic manipulation tasks?

Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.