AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning

Zhiwei Hao, Jianyuan Guo, Li Shen, Yong Luo, Han Hu, Yonggang Wen

IJCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add [cls] token to input (ablation)ADEM-VL baseline · ScienceQA ablation (LLaMA-7B)accuracy (%): 92.45 -> 92.61Improved
add SiLU parameter-free cross-attention (ablation)ADEM-VL · ScienceQA ablation (LLaMA-7B)accuracy (%): 92.61 -> 93.37Improved
add multiscale visual prompts (ablation)ADEM-VL · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.37 -> 93.47Improved
add adaptive fusion that drops unimportant visual features (ablation)ADEM-VL · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.47 -> 93.85Improved
use SiLU projection instead of identity (ablation)parameter-free cross-attention · ScienceQA ablation (LLaMA-7B)accuracy (%): 92.16 -> 93.85Improved
use softmax projection instead of SiLU (ablation)parameter-free cross-attention · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.85 -> 79.42Hurt
use ReLU projection instead of SiLU (ablation)parameter-free cross-attention · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.85 -> 91.99Hurt
shift SiLU to be positive (subtract min) (ablation)parameter-free cross-attention · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.85 -> 38.58Hurt
fuse from MLP input to MLP output instead of MHSA(in)->MHSA(out) (ablation)cross-attention placement · ScienceQA ablation (LLaMA-7B)accuracy (%): 92.19 -> 93.85Improved
use average pooling instead of max pooling for multiscale features (ablation)multiscale visual prompts · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.55 -> 93.85Improved
add 256 visual tokens at input stage alongside [cls] (ablation)ADEM-VL · ScienceQA ablation (LLaMA-7B)accuracy (%): 93.85 -> 90.17Hurt
use ADEM-VL instead of LaVIN (13B)LLaMA-13B captioning · COCO CaptionBLEU-4: 37.8 -> 38.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy