Open access
2026
DABO: Difficulty-Aware Binary Offloading for Collaborative Large-Small Model Inference
DABO is proposed, a calibration-aware binary offloading method for collaborative large–small model inference that maintains competitive end-to-end accuracy while processing an average of 83.72% of requests at the edge.
Chen Zhu, Yi-Ming Su, Chenwenjie Mao et al.
· IEEE Access · 0 citations