Son T. Ly

The authors propose SEA-PEFT, which treats adapter configuration as an online allocation problem solved during fine-tuning through a search–audit–allocate loop that trains active adapters, estimates each adapter's Dice utility by momentarily toggling it off, and reselects the active set under a parameter budget with a greedy knapsack allocator, stabilized by EMA+IQR smoothing and a finite-state machine; on TotalSegmentator and FLARE'22 it improves mean Dice by 2.4–2.8 points over the strongest fixed-topology PEFT baselines across 1/5/10-shot settings while training under 1% of parameters.

The authors propose SEA-PEFT, which treats adapter configuration as an online allocation problem solved during fine-tuning through a search–audit–allocate loop that trains active adapters, estimates each adapter's Dice utility by momentarily toggling it off, and reselects the active set under a parameter budget with a greedy knapsack allocator, stabilized by EMA+IQR smoothing and a finite-state machine; on TotalSegmentator and FLARE'22 it improves mean Dice by 2.4–2.8 points over the strongest fixed-topology PEFT baselines across 1/5/10-shot settings while training under 1% of parameters.