Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Yiwei, Zheng, Yi, Su, Huapeng, Lin, Jieyu, Ambrogio, Stefano, Jose, Cijo, Ramamonjisoa, Michael, Labatut, Patrick, De Salvo, Barbara, Liu, Chiao, Gibbons, Phillip B., Li, Ziyun
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.15622
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917456184868864
author Zhao, Yiwei
Zheng, Yi
Su, Huapeng
Lin, Jieyu
Ambrogio, Stefano
Jose, Cijo
Ramamonjisoa, Michael
Labatut, Patrick
De Salvo, Barbara
Liu, Chiao
Gibbons, Phillip B.
Li, Ziyun
author_facet Zhao, Yiwei
Zheng, Yi
Su, Huapeng
Lin, Jieyu
Ambrogio, Stefano
Jose, Cijo
Ramamonjisoa, Michael
Labatut, Patrick
De Salvo, Barbara
Liu, Chiao
Gibbons, Phillip B.
Li, Ziyun
contents Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive framework for efficient on-device inference of language-aligned VFMs that dynamically adjusts computation based on scene context and task complexity. Our key insight is that the effect of model size reduction on performance is task-dependent in vision applications, motivating a runtime-adaptive execution strategy. AdaVFM integrates neural architecture search (NAS) into the language-aligned VFM backbone to enable lightweight subnet execution during runtime. A multimodal large language model (LLM) deployed on the cloud enables runtime control with a context-aware agent. This synergy allows efficient model adaptation under diverse conditions while maintaining strong accuracy. Extensive experiments on zero-shot classification and open-vocabulary segmentation demonstrate that AdaVFM achieves state-of-the-art accuracy-efficiency trade-offs, surpassing prior baselines by up to $7.9\%$ in acc@1 on IN1K and $5.2\%$ mIoU on ADE20K over the best models of comparable VFM sizes. For models with similar accuracy, AdaVFM further reduces average FLOPs by up to $77.9\%$.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15622
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution
Zhao, Yiwei
Zheng, Yi
Su, Huapeng
Lin, Jieyu
Ambrogio, Stefano
Jose, Cijo
Ramamonjisoa, Michael
Labatut, Patrick
De Salvo, Barbara
Liu, Chiao
Gibbons, Phillip B.
Li, Ziyun
Computer Vision and Pattern Recognition
Machine Learning
Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive framework for efficient on-device inference of language-aligned VFMs that dynamically adjusts computation based on scene context and task complexity. Our key insight is that the effect of model size reduction on performance is task-dependent in vision applications, motivating a runtime-adaptive execution strategy. AdaVFM integrates neural architecture search (NAS) into the language-aligned VFM backbone to enable lightweight subnet execution during runtime. A multimodal large language model (LLM) deployed on the cloud enables runtime control with a context-aware agent. This synergy allows efficient model adaptation under diverse conditions while maintaining strong accuracy. Extensive experiments on zero-shot classification and open-vocabulary segmentation demonstrate that AdaVFM achieves state-of-the-art accuracy-efficiency trade-offs, surpassing prior baselines by up to $7.9\%$ in acc@1 on IN1K and $5.2\%$ mIoU on ADE20K over the best models of comparable VFM sizes. For models with similar accuracy, AdaVFM further reduces average FLOPs by up to $77.9\%$.
title AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2604.15622