# M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining

arXiv: https://arxiv.org/abs/2401.15896 · HTML: https://mlsanity.com/paper/2401.15896/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 48 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [MultiModal-GPT: A Vision and Language Model for Dialogue with Humans](https://mlsanity.com/paper/2305.04790/) (2023)
- [Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark](https://mlsanity.com/paper/2202.06767/) (2022)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [Improving Multimodal Datasets with Image Captioning](https://mlsanity.com/paper/2307.10350/) (2023)
- [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://mlsanity.com/paper/2211.06679/) (2022)
- [WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training](https://mlsanity.com/paper/2103.06561/) (2021)
- [COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval](https://mlsanity.com/paper/1805.08661/) (2018)
- [Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2311.11608/) (2023)
- [Fluency-Guided Cross-Lingual Image Captioning](https://mlsanity.com/paper/1708.04390/) (2017)
- [M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining](https://mlsanity.com/paper/2110.03888/) (2021)
- [CCMB: A Large-scale Chinese Cross-modal Benchmark](https://mlsanity.com/paper/2205.03860/) (2022)
- [RECLIP: Resource-efficient CLIP by Training with Small Images](https://mlsanity.com/paper/2304.06028/) (2023)

## Built on by (most cited first, 4 of 4)

- [M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval](https://mlsanity.com/paper/2401.17797/) (2024)
- [LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Models](https://mlsanity.com/paper/2502.03950/) (2025)
- [Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization](https://mlsanity.com/paper/2505.07675/) (2025)
- [MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data](https://mlsanity.com/paper/2603.08202/) (2026)

## Abstract (arXiv)

Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss computation, which reduces the communication overhead and GPU memory demands significantly, facilitating a 60% increase in training speed. We pretrain a series of bilingual image-text foundation models with an enhanced fine-grained understanding ability on BM-6B, the resulting models, dubbed as M2-Encoders (pronounced "M-Square"), set new benchmarks in both languages for multimodal retrieval and classification tasks. Notably, Our largest M2-Encoder-10B model has achieved top-1 accuracies of 88.5% on ImageNet and 80.7% on ImageNet-CN under a zero-shot classification setting, surpassing previously reported SoTA methods by 2.2% and 21.1%, respectively. The M2-Encoder series represents one of the most comprehensive bilingual image-text foundation models to date, so we are making it available to the research community for further exploration and development.