Yang Liu, Peng Li, Code, Ming Yan, Maosong Sun, Fei Huang, Ji Zhang, Ziyue Wang, Chi Chen, Fuwen Luo, Yiqi Zhu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
With the bloom of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) that incorporate LLMs with pretrained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. A primary reason for this shortcoming is that the visual features for each images are encoded individually by frozen encoders before feeding into the LLM backbone, lacking awareness of other images and the multimodal instructions. We term this issue as prior-LLM modality isolation and propose a two phase paradigm, browse-and-concentrate 1 , to enable in-depth multimodal context fusion prior to feeding the features into LLMs. This paradigm initially "browses" through the inputs for essential insights, and then revisits the inputs to "concentrate" on crucial details, guided by these insights, to achieve a more comprehensive understanding of the multimodal inputs. Additionally, we develop training strategies specifically to enhance the understanding of multi-image inputs. Our method markedly boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.12195")
get_code_for_paper("2402.12195")
have("2402.12195")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.12195.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.12195)
Connect an agent — have() is free.