Multimodal Pretraining and Scale Effects on Zero-Shot Reasoning in 13B vs 7B VLA Models

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: Do 13B VLA models with multimodal pretraining demonstrate better zero-shot reasoning capabilities on the MM-ReAct benchmark compared to 7B models when evaluated using Exact Match accuracy. Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the notion of "zero-shot" generalization. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

Do 13B VLA models with multimodal pretraining demonstrate better zero-shot reasoning capabilities on the MM-ReAct benchmark compared to 7B models when evaluated using Exact Match accuracy?

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