# Buffer replay enhances the robustness of multimodal learning under missing-modality

arXiv: https://arxiv.org/abs/2511.23070 · HTML: https://mlsanity.com/paper/2511.23070/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos](https://mlsanity.com/paper/1606.06259/) (2016)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Multimodal Prompting with Missing Modalities for Visual Recognition](https://mlsanity.com/paper/2303.03369/) (2023)
- [UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2211.11256/) (2022)
- [Read-only Prompt Optimization for Vision-Language Few-shot Learning](https://mlsanity.com/paper/2308.14960/) (2023)
- [DePT: Decoupled Prompt Tuning](https://mlsanity.com/paper/2309.07439/) (2023)
- [TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2009.02902/) (2020)
- [FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space](https://mlsanity.com/paper/2310.20071/) (2023)
- [Towards Robust Multimodal Sentiment Analysis with Incomplete Data](https://mlsanity.com/paper/2409.20012/) (2024)
- [Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition](https://mlsanity.com/paper/2407.05374/) (2024)
- [Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models](https://mlsanity.com/paper/2407.12616/) (2024)
- [Deep Correlated Prompting for Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2410.06558/) (2024)
- [Towards Robust Multimodal Prompting With Missing Modalities](https://mlsanity.com/paper/2312.15890/) (2023)
- [I3-MRec: Invariant Learning with Information Bottleneck for Incomplete Modality Recommendation](https://mlsanity.com/paper/2508.04247/) (2025)
- [Hardness-Aware Dynamic Curriculum Learning for Robust Multimodal Emotion Recognition with Missing Modalities](https://mlsanity.com/paper/2508.06800/) (2025)

## Abstract (arXiv)

Missing modalities consistently lead to significant performance degradation in multimodal models. Existing approaches either synthesize missing modalities at high computational cost or apply prompt-based fine-tuning that relies only on adjacent-layer features and overlooks long-distance contextual information, which may offer additional tolerance to errors when one or more modalities are missing. To address this, we introduce REplay Prompting (REP): (1) construct modality-wise feature buffers via a residual bypass to cache early-layer representations and replay them in deeper layers, mitigating information loss as network depth increases; (2) employ a private-shared feature decoupling strategy, where private buffers preserve modality-specific signals and shared buffers encode cross-modal semantics; and (3) design a task-aware dynamic initialization mechanism to configure these buffers differently, improving stability and generalization under diverse missing-modality conditions. Experiments on vision-language, vision-language-audio, and temporal multimodal benchmarks demonstrate that REP consistently outperforms prior methods under both single- and multi-modality missing scenarios, while introducing only negligible parameter overhead. These results establish REP as a lightweight and effective paradigm for robust multimodal learning in challenging missing-modality environments.