SAEs used for layer selection with raw task vectors outperform subspace projection and raise math reasoning accuracy on Gemma-3-4B-IT.
Evolutionary optimization of model merging recipes
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Evolutionary merging with a 14-dimensional genome and MRI-Trust Fusion produces models that outperform their trained parents on reasoning benchmarks without any gradient updates.
OMEGA framework generates novel ML classifiers via meta-prompts and executable code that outperform scikit-learn baselines on 20 benchmark datasets.
HeteroFusion fuses heterogeneous LLMs via topology-based alignment and conflict-aware denoising, outperforming merging and ensemble baselines in cross-family and multi-source settings.
Tunable MAGMAX gives each task an element budget during model merging, letting users shift task-wise accuracy and auto-setting the budget from target-environment label/feature similarity.
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.
citing papers explorer
-
Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing
SAEs used for layer selection with raw task vectors outperform subspace projection and raise math reasoning accuracy on Gemma-3-4B-IT.
-
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning
Evolutionary merging with a 14-dimensional genome and MRI-Trust Fusion produces models that outperform their trained parents on reasoning benchmarks without any gradient updates.
-
OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms
OMEGA framework generates novel ML classifiers via meta-prompts and executable code that outperform scikit-learn baselines on 20 benchmark datasets.
-
Can Heterogeneous Language Models Be Fused?
HeteroFusion fuses heterogeneous LLMs via topology-based alignment and conflict-aware denoising, outperforming merging and ensemble baselines in cross-family and multi-source settings.
-
Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
Tunable MAGMAX gives each task an element budget during model merging, letting users shift task-wise accuracy and auto-setting the budget from target-environment label/feature similarity.
-
Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.