AI RESEARCH
EdgeFM: Efficient Edge Inference for Vision-Language Models
arXiv CS.CV
•
ArXi:2604.27476v1 Announce Type: new Vision-language models (VLMs) have nstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource limitations. Existing frameworks either rely on bloated general-purpose designs or force developers into opaque, hardware-specific closed-source ecosystems, leading to hardware lock-in limitation and poor cross-platform adaptability.