AI RESEARCH
AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution
arXiv CS.LG
•
ArXi:2604.15622v1 Announce Type: cross 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.