Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledged, a rigorous theoretical understanding of the contrastive pre-training framework remains limited. This paper develops a theoretical framework to explain the success of contrastive pre-training in downstream tasks, such as zero-shot classification, conditional diffusion models, and vision-language models. We introduce the concept of approximate sufficient statistics, a generalization of the classical sufficient statistics, and show that near-minimizers of the contrastive pre-training loss are approximately sufficient, making them adaptable to diverse downstream tasks. We further propose the Joint Generative Hierarchical Model for the joint distribution of images and text, showing that transformers can efficiently approximate relevant functions within this model via belief propagation. Building on this framework, we derive sample complexity guarantees for multi-modal learning based on contrastive pre-trained representations. Numerical simulations validate these theoretical findings, demonstrating the strong generalization performance of contrastively pre-trained transformers in various multi-modal tasks.
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Harvard T.H. Chan School of Public Health（哈佛T.H. 柏林公共卫生学院）；Harvard Medical School（哈佛医学院）；Rutgers University（罗格斯大学）；National University of Singapore（新加坡国立大学）
Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning
Berlin Institute of Health, Charité - Universitätsmedizin Berlin（柏林健康研究院，柏林夏里特大学医学中心）；Department of Mathematics and Computer Science, Freie Universität Berlin（柏林自由大学数学与计算机科学系）；Intelligent Medicine Institute, Fudan University（复旦大学智能医学研究院）
Prior-Fitted and Frozen Scorers for Multimodal Contrastive Learning
Berlin Institute of Health（柏林卫生研究所）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Intelligent Medicine Institute（智能医学研究所）；Fudan University（复旦大学）
Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；FZI Research Center for Information Technology（FZI信息技术研究中心）；Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Tübingen（蒂宾根大学）
Self-supervised Learning: Generative or Contrastive
Tsinghua University（清华大学）；Tsinghua National Laboratory for Information Science and Technology (TNList)（清华信息科学与技术国家实验室）；Anhui University（安徽大学）；Renmin University of China（中国人民大学）
Local-Global Multimodal Contrastive Learning for Molecular Property Prediction
School of Mathematical Sciences（数学科学学院）；University of Electronic Science and Technology of China（电子科技大学）；Department of Computer Science and Engineer（计算机科学与工程系）；Oakland University（奥克兰大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；College of Management Science（管理科学学院）；Chengdu University of Technology（成都理工大学）
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology（大数据知识工程重点实验室（教育部））
MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion
University of Shanghai for Science and TechnologyChina（上海科学技术大学中国）；Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesChina（深圳先进技术研究院，中国科学院中国）；University of Minnesota-Twin Cities, USA（明尼苏达大学双城分校，美国）；University of LeedsUK（利兹大学，英国）
Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations
Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School（图林根工业大学和汉诺威医学院医学信息学研究所）；Lower Saxony Center for AI and Causal Methods in Medicine (CAIMed)（下萨克森人工智能与因果医学中心（CAIMed））
Hidden in the Multiplicative Interaction: Uncovering Fragility in Multimodal Contrastive Learning
Berlin Institute of Health, Charité - Universitätsmedizin Berlin（柏林健康研究所，柏林查理医院）；Intelligent Medicine Institute, Fudan University（智能医学研究院，复旦大学）；Department of Mathematics and Computer Science, Freie Universität Berlin（数学与计算机科学系，柏林自由大学）
Multimodal Federated Learning via Contrastive Representation Ensemble
Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Waterloo（滑铁卢大学）；Carnegie Mellon University（卡内基梅隆大学）
