Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.02430 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915235364864000 |
|---|---|
| author | Wang, Haicheng Yu, Zhemeng Spadaro, Gabriele Ju, Chen Quétu, Victor Xiao, Shuai Tartaglione, Enzo |
| author_facet | Wang, Haicheng Yu, Zhemeng Spadaro, Gabriele Ju, Chen Quétu, Victor Xiao, Shuai Tartaglione, Enzo |
| contents | Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted from visual backbones poses a challenge for deployment in real-time applications. To address this issue, we introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence, mitigating both computational and memory demands during training and inference. Through a comprehensive analysis of the token reduction process, we analyze the information loss introduced by different reduction strategies and develop FOLDER to preserve key information while removing visual redundancy. We showcase the effectiveness of FOLDER by integrating it into the visual backbone of several MLLMs, significantly accelerating the inference phase. Furthermore, we evaluate its utility as a training accelerator or even performance booster for MLLMs. In both contexts, FOLDER achieves comparable or even better performance than the original models, while dramatically reducing complexity by removing up to 70% of visual tokens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance Wang, Haicheng Yu, Zhemeng Spadaro, Gabriele Ju, Chen Quétu, Victor Xiao, Shuai Tartaglione, Enzo Computer Vision and Pattern Recognition Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their abilities to generate and understand cross-modal data. However, processing long sequences of visual tokens extracted from visual backbones poses a challenge for deployment in real-time applications. To address this issue, we introduce FOLDER, a simple yet effective plug-and-play module designed to reduce the length of the visual token sequence, mitigating both computational and memory demands during training and inference. Through a comprehensive analysis of the token reduction process, we analyze the information loss introduced by different reduction strategies and develop FOLDER to preserve key information while removing visual redundancy. We showcase the effectiveness of FOLDER by integrating it into the visual backbone of several MLLMs, significantly accelerating the inference phase. Furthermore, we evaluate its utility as a training accelerator or even performance booster for MLLMs. In both contexts, FOLDER achieves comparable or even better performance than the original models, while dramatically reducing complexity by removing up to 70% of visual tokens. |
| title | FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.02430 |