AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

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

Mingqiao Ye, Zhaochong An, Zhitong Gao, Xian Liu, Oğuzhan Fatih Kar, Jesse Allardice, Roman Bachmann, David Mizrahi, François Fleuret, Chuan Li, Amir Zadeh, Serge Belongie and 2 more

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add VAE features to ViT-only conditioning (ablation)MODUS · NYUv2 surface normalangular error: 35.30 -> 19.92Improved
add ViT features to VAE-only conditioning (ablation)MODUS · NYUv2 depthdepth error: 6.9 -> 6.5Improved
use uniform instead of logit-normal timestep sampling (ablation)MODUS 2D experts · NYUv2 surface normalangular error: 50.54 -> 21.10Improved
use uniform instead of logit-normal timestep sampling (ablation)MODUS 2D experts · NYUv2 depthdepth error: 21.9 -> 8.4Improved
use uniform instead of mode timestep sampling (ablation)MODUS 2D experts · GenEvalGenEval score: 0.80 -> 0.81Improved
route surface normal estimation through canny edges (ablation)MODUS · NYUv2 surface normalangular error: 20.02 -> 19.87Improved
route surface normal estimation through DINOv2 features (ablation)MODUS · NYUv2 surface normalangular error: 20.02 -> 20.71Hurt
route surface normal estimation through depth (ablation)MODUS · NYUv2 surface normalangular error: 20.02 -> 20.06No clear effect
add VQA and grounding verifiers for self-verification (ablation)MODUS text-to-image · GenEvalGenEval score: 0.81 -> 0.84Improved
use unified sequence instead of decoupled per-modality heads (ablation)MODUS · NYUv2 surface normalangular error: 50.75 -> 19.92Improved
use unified sequence instead of decoupled per-modality heads (ablation)MODUS · DIODE depthdepth error: 0.322 -> 0.285Improved
use unified sequence instead of decoupled per-modality heads (ablation)MODUS · MMMUaccuracy: 50.4 -> 51.1No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy