How does SMoES-trained modality routing for multimodal LLMs generalize to out-of-distribution benchmarks like

Abstract

Abstract: Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA). Our approach is motivated by a few observations. First, VQA questions often require multiple steps of reasoning, which is still a capability that most PTMs lack. Second, different steps in VQA reasoning chains require different skills such as object detection and relational reasoning, but a single PTM may not possess all these skills. Third, recent work on zero-shot VQA does not explicitly consider multi-step reasoning chains, whic

Research Question

How does SMoES-trained modality routing for multimodal LLMs generalize to out-of-distribution benchmarks like DocVQA and InfographicVQA under domain shift, and what are the accuracy vs. latency trade-offs compared to chart-specific distribution shifts?

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