AdaVFM integrates neural architecture search into vision foundation model backbones and uses a cloud multimodal LLM agent to enable runtime-adaptive lightweight subnet execution, delivering up to 7.9% higher accuracy and 77.9% lower FLOPs than fixed-size baselines on edge devices.
In: International conference on machine learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.
citing papers explorer
-
AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution
AdaVFM integrates neural architecture search into vision foundation model backbones and uses a cloud multimodal LLM agent to enable runtime-adaptive lightweight subnet execution, delivering up to 7.9% higher accuracy and 77.9% lower FLOPs than fixed-size baselines on edge devices.
-
T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification
T-DuMpRa fuses classifier outputs with cosine-matched multi-prototypes from a teacher model via conservative gating, yielding 0.21-2.69% gains on skin lesion datasets across five backbones.