Model merging is cast as PoE inference with EBM experts, revealing Gaussian assumptions in prior work and proposing convergent Cauchy experts that improve empirical performance.
The 2011 international joint conference on neural networks , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.
citing papers explorer
-
Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space
Model merging is cast as PoE inference with EBM experts, revealing Gaussian assumptions in prior work and proposing convergent Cauchy experts that improve empirical performance.
-
Evolutionary Negative Module Pruning for Better LoRA Merging
ENMP prunes negative LoRA modules via evolutionary search to boost merging performance to new state-of-the-art levels across language and vision tasks.