相关论文: Behind the Scene: Revealing the Secrets of Pre-tra…

With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V\&L) tasks, scholars have introduced an abundance of deep learning models in this research domain. Furthermore, in recent years, transfer learning…

As transformer evolves, pre-trained models have advanced at a breakneck pace in recent years. They have dominated the mainstream techniques in natural language processing (NLP) and computer vision (CV). How to adapt pre-training to the…

In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream…

Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval,…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…

Large-scale pre-trained multimodal transformers, such as ViLBERT and UNITER, have propelled the state of the art in vision-and-language (V+L) research to a new level. Although achieving impressive performance on standard tasks, to date, it…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data,…

Large Language Models (LLMs), despite being trained on text alone, surprisingly develop rich visual priors. These priors allow latent visual capabilities to be unlocked for vision tasks with a relatively small amount of multimodal data, and…

Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets. There is now a plethora of…

Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…

We investigate the reasoning ability of pretrained vision and language (V&L) models in two tasks that require multimodal integration: (1) discriminating a correct image-sentence pair from an incorrect one, and (2) counting entities in an…

In-context learning (ICL) enables Large Language Models (LLMs) to learn tasks from demonstration examples without parameter updates. Although it has been extensively studied in LLMs, its effectiveness in Vision-Language Models (VLMs)…

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal…

Large-scale pretraining and task-specific fine-tuning is now the standard methodology for many tasks in computer vision and natural language processing. Recently, a multitude of methods have been proposed for pretraining vision and language…

The exploration of various vision-language tasks, such as visual captioning, visual question answering, and visual commonsense reasoning, is an important area in artificial intelligence and continuously attracts the research community's…

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder…

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…