Multimodal large language models (MLLMs) enhance the capabilities of standard large
language models by integrating and processing data from multiple modalities, including text …

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training
vision encoders to generate image/text representations facilitating various applications …

Recent advancements in multimodal models highlight the value of rewritten captions for
improving performance, yet key challenges remain. For example, while synthetic captions …

Despite significant advancements in vision-language models (VLMs), there lacks effective
approaches to enhance response quality by scaling inference-time computation. This …

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-
training (CLIP) has made significant strides, becoming foundation for various downstream …

Visual Question Answering (VQA) with multiple choice questions enables a vision-centric
evaluation of Multimodal Large Language Models (MLLMs). Although it reliably checks the …

Recently, video-language understanding has achieved great success through large-scale
pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively …

Previous works show that noisy, web-crawled image-text pairs may limit vision-language
pretraining like CLIP and propose learning with synthetic captions as a promising …

The field of video generation has made remarkable advancements, yet there remains a
pressing need for a clear, systematic recipe that can guide the development of robust and …

While image-text representation learning has become very popular in recent years, existing
models tend to lack spatial awareness and have limited direct applicability for dense …