InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
This work addresses a bottleneck in developing robust MLLMs for high-resolution multimodal understanding, representing an incremental advancement in the field.
The paper tackles the challenge of accurate recognition and comprehension of intricate details in high-resolution images for Multimodal Large Language Models (MLLMs) by introducing InfiMM-HD, a novel architecture that processes images of different resolutions with low computational overhead, achieving improved visual perception efficiently and cost-effectively.
Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being indispensable for the development of robust MLLMs, this area remains underinvestigated. To tackle this challenge, our work introduces InfiMM-HD, a novel architecture specifically designed for processing images of different resolutions with low computational overhead. This innovation facilitates the enlargement of MLLMs to higher-resolution capabilities. InfiMM-HD incorporates a cross-attention module and visual windows to reduce computation costs. By integrating this architectural design with a four-stage training pipeline, our model attains improved visual perception efficiently and cost-effectively. Empirical study underscores the robustness and effectiveness of InfiMM-HD, opening new avenues for exploration in related areas. Codes and models can be found at https://huggingface.co/Infi-MM/infimm-hd