Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.
Whoever started the interference should end it: Guiding data-free model merging via task vectors
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Memory Grafting improves language-model benchmarks by grafting offline hidden-state memory from a larger model into a recipient model using n-gram lookups and lightweight adapters, outperforming MoE and vanilla Engram baselines at 0.92B and 2.8B scales.
citing papers explorer
-
When Model Merging Breaks Routing: Training-Free Calibration for MoE
Merging breaks MoE routing via softmax sensitivity; HARC uses Hessian curvature for closed-form router calibration that improves merged model performance without retraining.
-
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Memory Grafting improves language-model benchmarks by grafting offline hidden-state memory from a larger model into a recipient model using n-gram lookups and lightweight adapters, outperforming MoE and vanilla Engram baselines at 0.92B and 2.8B scales.