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

Hugging Face Daily Papers Papers

Summary

Modus is a decoder-only model that predicts any modality from any combination of others, achieving strong performance across diverse benchmarks without modality-specific heads or losses.

Any-to-any models predict any modality from any combination of others within a single network, a formulation used in multimodal vision and vision-language models, and increasingly in scientific domains such as ecology and astronomy. Existing any-to-any models are typically trained from scratch using encoder-decoder or diffusion architectures, impacting their performance and preventing them from using strong pre-trained decoder-only models as a prior. In this work, we investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modalities as inputs and outputs without modality-specific heads, losses, or task pipelines. Because every modality is both an input and an output of the same model, the resulting model, named Modus, can support a range of applications, such as chained generation through intermediate modalities or cross-modal self-verification by scoring the model's own outputs with another generated modality. Modus demonstrates strong out-of-the-box performance and is competitive with specialist and multitask baselines using a single model across various benchmarks. All materials are open-sourced at https://modus-multimodal.epfl.ch/.
Original Article
View Cached Full Text

Cached at: 07/29/26, 11:52 AM

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

Source: https://huggingface.co/papers/2607.25948 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Any-to-anymodelspredictanymodalityfromanycombinationofotherswithinasinglenetwork,aformulationusedinmultimodalvisionandvision-languagemodels,andincreasinglyinscientificdomainssuchasecologyandastronomy.Existingany-to-anymodelsaretypicallytrainedfromscratchusingencoder-decoderordiffusionarchitectures,impactingtheirperformanceandpreventingthemfromusingstrongpre-traineddecoder-onlymodelsasaprior.Inthiswork,weinvestigatedecoder-onlyany-to-anymultimodalmodeling,whichtreatsallmodalitiessymmetricallyandsupportsarbitrarymodalitiesasinputsandoutputswithoutmodality-specificheads,losses,ortaskpipelines.Becauseeverymodalityisbothaninputandanoutputofthesamemodel,theresultingmodel,namedModus,cansupportarangeofapplications,suchaschainedgenerationthroughintermediatemodalitiesorcross-modalself-verificationbyscoringthemodel’sownoutputswithanothergeneratedmodality.Modusdemonstratesstrongout-of-the-boxperformanceandiscompetitivewithspecialistandmultitaskbaselinesusingasinglemodelacrossvariousbenchmarks.Allmaterialsareopen-sourcedathttps://modus-multimodal.epfl.ch/.

View arXiv pageView PDFProject pageGitHub16Add to collection

Get this paper in your agent:

hf papers read 2607\.25948

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.25948 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.25948 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.25948 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

How Modalities Learn Together (49 minute read)

TLDR AI

A systematic study from Meta FAIR, Reality Labs, and Oxford on multimodal pretraining, revealing asymmetric knowledge flow between modalities, synergy vs. competition dynamics, the benefits of early unification, and efficient training recipes validated with 13.5B MoE models.

Generalized Multimodal Foundation Model

arXiv cs.LG

This paper introduces a generalized multimodal foundation model capable of handling arbitrary modality combinations and prediction tasks, achieving competitive performance through training on large-scale synthetic datasets with diverse causal structures.