English

MARVIS: Modality Adaptive Reasoning over VISualizations

Machine Learning 2026-04-30 v2

Abstract

Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. Such models often achieve excellent performance, but lack flexibility. LLMs and VLMs offer versatility, but typically underperform specialized predictors, especially on non-traditional modalities and long-tail domains. We propose MARVIS (Modality Adaptive Reasoning over VISualizations), a system that transforms latent embedding spaces into visual representations and then leverages the spatial and fine-grained reasoning skills of VLMs to interpret the visualizations and utilize them for predictions successfully. MARVIS achieves competitive performance across vision, audio, biological, and tabular domains using a single 3B parameter model, yielding results that beat Gemini 2.0 by 16% on average. MARVIS drastically reduces the gap between LLM/VLMs approaches and specialized domain-specific methods, without requiring any domain-specific training. Code and datasets are available at https://github.com/penfever/marvis.

Keywords

Cite

@article{arxiv.2507.01544,
  title  = {MARVIS: Modality Adaptive Reasoning over VISualizations},
  author = {Benjamin Feuer and Lennart Purucker and Oussama Elachqar and Chinmay Hegde},
  journal= {arXiv preprint arXiv:2507.01544},
  year   = {2026}
}
R2 v1 2026-07-01T03:42:57.711Z