Rethinking Visual Information Processing in Multimodal LLMs

Dongwan Kim, Viresh Ranjan, Takashi Nagata, Arnab Dhua, Amit Kumar K C

Track: long paper (up to 8 pages)

Keywords: Vision-Language Models, Transformers

Abstract: Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this issue from a novel perspective in which the LLM not only serves as a language model but also a powerful vision encoder. To this end, we present LLaViT–Large Language Models as extended Vision Transformers—which enables the LLM to simultaneously function as a vision encoder through three key modifications: (1) learning separate QKV projections for vision modality, (2) enabling bidirectional attention on visual tokens, and (3) incorporating both global and local visual representations. Through extensive controlled experiments on a wide range of LLMs, we demonstrate that LLaViT significantly outperforms the baseline LLaVA method on a multitude of benchmarks, even surpassing models with double its parameter count, establishing a more effective approach to vision-language modeling.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 40