In this paper, we introduce InternVL 1.5, an open-source multimodal large language model
(MLLM) to bridge the capability gap between open-source and proprietary commercial …

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding
the visual world. Conventional LMMs process images in fixed sizes and limited resolutions …

The ability to accurately interpret complex visual information is a crucial topic of multimodal
large language models (MLLMs). Recent work indicates that enhanced visual perception …

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

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and
tones, marks a milestone for omni-modal foundation models. However, empowering Large …

Multi-modal large language models (MLLMs) have demonstrated impressive performance in
vision-language tasks across a wide range of domains. However, the large model scale and …

Multi-modal large language models (MLLMs) have made significant strides in various visual
understanding tasks. However, the majority of these models are constrained to process low …

In this work, we propose a training-free method to inject visual referring into Multimodal
Large Language Models (MLLMs) through learnable visual token optimization. We observe …

Emerging multimodal large language models (MLLMs) exhibit great potential for chart
question answering (CQA). Recent efforts primarily focus on scaling up training datasets (ie …

High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer
visual details, enhancing their comprehension capabilities. To reduce the training and …