AI RESEARCH
Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks
arXiv CS.LG
•
ArXi:2605.05358v1 Announce Type: new Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by incrementally adding them to a shared backbone; however, this sequential