# Latent World Recovery for Multimodal Learning with Missing Modalities

arXiv: https://arxiv.org/abs/2606.12362 · HTML: https://mlsanity.com/paper/2606.12362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models](https://mlsanity.com/paper/1911.03393/) (2019)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [OmiEmbed: a unified multi-task deep learning framework for multi-omics data](https://mlsanity.com/paper/2102.02669/) (2021)
- [CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data](https://mlsanity.com/paper/2304.05542/) (2023)

## Abstract (arXiv)

We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made. We propose Latent World Recovery (LWR), a framework built on two key ideas: (i) modality-specific embeddings from different modalities are aligned in a shared latent space, and (ii) a unified representation is constructed by fusing only the embeddings of the modalities that are actually available at both training and inference time. Rather than imputing missing modalities or requiring a fixed modality set, LWR treats each modality as a partial perception of an underlying latent state and performs availability-aware representation learning directly from the observed modalities. This combination of neighbor-based latent alignment and availability-aware modality fusion enables robust multimodal prediction under partial observation, while avoiding error propagation from explicit reconstruction of missing modalities. We evaluate the proposed framework on real-world incomplete multi-omics benchmarks and demonstrate that it provides an effective approach to downstream tasks such as cancer phenotype classification and survival prediction.