Library

Research Library

Paper2026

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Mingqiao Ye, Zhaochong An, Zhitong Gao, Xian Liu et al. · ICML 2026 · 2026

Abstract

Any-to-any models predict any modality from any combination of the others. They are normally built from scratch on encoder-decoder or diffusion architectures, which rules out starting from a strong pretrained decoder-only model. This work builds one on a decoder-only backbone treating every modality symmetrically, with no per-modality heads or losses — so the same model can chain generation through an intermediate modality, or check its own answer by generating a second one.

Why it matters

The self-verification trick is the striking part: a model that can render its answer in another modality is able to grade itself. Accepted at ICML 2026.

multimodalarchitecturegenerative modelsany to any
Read the source

https://arxiv.org/abs/2607.25948