# CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning

arXiv: https://arxiv.org/abs/2512.00496 · HTML: https://mlsanity.com/paper/2512.00496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Self-Supervised MultiModal Versatile Networks](https://mlsanity.com/paper/2006.16228/) (2020)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [MAE-AST: Masked Autoencoding Audio Spectrogram Transformer](https://mlsanity.com/paper/2203.16691/) (2022)
- [Natural Language Supervision for General-Purpose Audio Representations](https://mlsanity.com/paper/2309.05767/) (2023)
- [Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning](https://mlsanity.com/paper/2309.11500/) (2023)

## Abstract (arXiv)

As deep learning models evolve, new applications and challenges are rapidly emerging. Tasks that once relied on a single modality, such as text, images, or audio, are now enriched by seamless interactions between multimodal data. These connections bridge information gaps: an image can visually materialize a text, while audio can add context to an image. Researchers have developed numerous multimodal models, but most rely on resource-intensive training across multiple modalities. Similarly, extending these models to new languages often follows the same resource-heavy training strategy. In this work, we propose a multimodal and multilingual architecture, CACARA, trained through emergent alignment learning, enabling the seamless integration of new modalities into an existing bimodal/multimodal model without requiring full retraining. This work breaks new ground by demonstrating that this emergent alignment paradigm can unlock multilingual capabilities from monolingual training. By fine-tuning the newly incorporated modality only on data aligned with the English language, our model develops support for over 100 languages without explicit multilingual pretraining or tuning of the text encoder. Such emergent multimodal and multilingual properties are gained efficiently, preserving previously learned knowledge at a training cost comparable to that of a monolingual model. Our strategy achieves up to a 14.24 percentage points improvement in R@1 audio-to-text retrieval, outperforming state-of-the-art multimodal models -- all without the heavy computational cost of retraining across every modality and language.