ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation
Visual prompting (VP) has emerged as a parameter-efficient method for adapting pre-trained models to downstream tasks. However, existing approaches encounter a trade-off between flexibility and efficiency. Some methods apply a fixed prompt to all images, ignoring individual image characteristics, while others introduce auxiliary networks to generate diverse prompts. Although the latter can improve performance, it also significantly increases parameter usage and the potential for overfitting to specific datasets. Furthermore, the auxiliary networks, combined with inherent biases in pre-trained
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%google-research/google-research →
“Shared author/contributor keys: sun”
- LinkedLinked via arxiv author · 85%Can Jin →
“ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation”
- LinkedLinked via arxiv author · 85%Xueying Liu →
“ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation”
- LinkedLinked via arxiv author · 85%Jingchen Sun →
“ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation”
- LinkedLinked via arxiv author · 85%Hongwu Peng →
“ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation”