Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
Model Merging Scaling Laws in Large Language Models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We study empirical scaling laws for language model merging measured by cross-entropy. Despite its wide practical use, merging lacks a quantitative rule that predicts returns as we add experts or scale the model size. We identify a compact power law that links model size and expert number: the size-dependent floor decreases with model capacity, while the merging tail exhibits clear diminishing returns in the number of experts. The law holds in-domain and cross-domain, tightly fits measured curves across diverse architectures and methods (Average, TA, TIES, DARE), and explains two robust regularities: most gains arrive early, and variability shrinks as more experts are included. Building on this, we present a simple theory that explains why gains fall roughly as 1/k and links the floor and tail to properties of the base model and the diversity across domains. This law enables predictive planning: estimate how many experts are needed to reach a target loss, decide when to stop adding experts, and trade off scaling the base model versus adding experts under a fixed budget--turning merging from heuristic practice into a computationally efficient, planable alternative to multitask training. This suggests a scaling principle for distributed generative AI: predictable gains can be achieved by composing specialists, offering a complementary path toward AGI-level systems.
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
FeatCal reduces feature drift in merged models via layer-wise closed-form calibration on a small dataset, outperforming prior post-merging methods on CLIP and GLUE benchmarks with high sample efficiency.
E-PMQ improves 4-bit quantization accuracy on merged models by 8-42 points across CLIP and GLUE tasks through expert-guided calibration and merged-weight anchoring.
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.
citing papers explorer
-
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
-
FeatCal: Feature Calibration for Post-Merging Models
FeatCal reduces feature drift in merged models via layer-wise closed-form calibration on a small dataset, outperforming prior post-merging methods on CLIP and GLUE benchmarks with high sample efficiency.
-
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
E-PMQ improves 4-bit quantization accuracy on merged models by 8-42 points across CLIP and GLUE tasks through expert-guided calibration and merged-weight anchoring.
-
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
-
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.