README.md

<div align="center">

<h1><a href="https://openreview.net/forum?id=PWhDUWRVhM&noteId=PWhDUWRVhM">Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification (ICLR 2026)</a></h1>

**[Siyi Du](https://scholar.google.com/citations?user=zsOt8MYAAAAJ&hl=en), [Xinzhe Luo](https://scholar.google.com/citations?user=l-oyIaAAAAAJ&hl=en&oi=ao), [Declan P. O'Regan](https://scholar.google.com/citations?user=85u-LbAAAAAJ&hl=en&oi=ao), and [Chen Qin](https://scholar.google.com/citations?view_op=list_works&hl=en&hl=en&user=mTWrOqHOqjoC&pagesize=80&sortby=pubdate)** 

[![](https://img.shields.io/badge/license-Apache--2.0-blue)](#License)
[![](https://img.shields.io/badge/arXiv-2503.06277-b31b1b.svg)](https://arxiv.org/abs/2601.22853)

</div>

![DyMo](./Images/overview.jpg)
<p align="center">(a-b) Evidence of the discarding-imputation dilemma: (a-1) vs. (a-2) recovery-free methods (e.g., ModDrop) learn less discriminative features because they ignore highly task-relevant missing modalities {M,T}; (b) recovery-based methods (e.g., MoPoE) generate unreliable reconstructions, e.g., low-fidelity (orange) or misaligned (yellow). (c) Our DyMo, which addresses the dilemma by dynamically fusing task-relevant recovered modalities, improving accuracy by 1.61% on PolyMNIST, 1.68% on MST, and 3.88% on CelebA (Tab 1).</p>


This repository provides **pretrained model checkpoints** for [Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification](https://openreview.net/forum?id=PWhDUWRVhM&noteId=PWhDUWRVhM). 

For the **training code, evaluation scripts, and usage instructions**, please refer to the official GitHub repository:  
👉 [https://github.com/siyi-wind/DyMo](https://github.com/siyi-wind/DyMo).