Continuous Latent Action Models Outperform Discrete Tokens in RT-2 Multimodal Policy Robustness

Abstract

Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How do continuous latent action models perform relative to discrete token methods in terms of robustness to observation noise and action jitter within the RT-2 multimodal policy benchmarks. 14 claims were extracted from source literature; 1 was independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do continuous latent action models perform relative to discrete token methods in terms of robustness to observation noise and action jitter within the RT-2 multimodal policy benchmarks?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance