EvoGM uses a dual-generator architecture with cycle-consistent learning on winner-loser pairs from search history to optimize LLM merging coefficients inside a multi-round evolutionary pipeline and reports outperformance over baselines on seen and unseen tasks.
Title resolution pending
3 Pith papers cite this work, alongside 8 external citations. Polarity classification is still indexing.
3
Pith papers citing it
8
external citations · OpenAlex
years
2026 3representative citing papers
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
Optimal layer-patching order for boomerang distillation is a shortest path on a KL-weighted Boolean lattice; greedy KLPatch and simple sequential orders often yield near-optimal interpolations.
citing papers explorer
-
EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
EvoGM uses a dual-generator architecture with cycle-consistent learning on winner-loser pairs from search history to optimize LLM merging coefficients inside a multi-round evolutionary pipeline and reports outperformance over baselines on seen and unseen tasks.
-
One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging
Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.
-
Understanding Layer Patching in Model Size Interpolation
Optimal layer-patching order for boomerang distillation is a shortest path on a KL-weighted Boolean lattice; greedy KLPatch and simple sequential orders often yield near-optimal interpolations.