Enzo Tartaglione, Chen Ju, Shuai Xiao, Haicheng Wang, Victor Quétu, Zhemeng Yu, Gabriele Spadaro
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.
Recently, Multi-modal Large Language Models (MLLMs) have shown remarkable effectiveness for multi-modal tasks due to their ability of cross-modal understanding. However, processing long sequences of visual tokens extracted from visual backbones poses challenges 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 computational and memory demands during both training and inference. Through a comprehensive analysis of the token reduction process in the vision encoder, we analyze the information loss introduced by different reduction strategies and develop FOLDER to preserve key information while removing visual redundancy. We show the effectiveness of FOLDER by integrating it into the visual backbone of various MLLMs, significantly accelerating the inference phase. Furthermore, we evaluate its utility as a training accelerator or even performance booster for MLLMs. FOLDER achieves comparable or even better performance than the original models, while dramatically reducing complexity by removing up to 70% of visual tokens. Our code is available at FOLDER Repository.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.02430")
get_code_for_paper("2501.02430")
have("2501.02430")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2501.02430.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2501.02430)
Connect an agent — have() is free.