CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
Paper • 2503.01874 • Published • 2
Favorite Merge Methods
Note cabs
Functionality-Oriented LLM Merging on the Fisher--Rao Manifold
Paper • 2603.04972 • Published • 3Note karcher
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
Paper • 2406.11617 • Published • 10Note della
FuseChat: Knowledge Fusion of Chat Models
Paper • 2408.07990 • Published • 15Note sce
Model Stock: All we need is just a few fine-tuned models
Paper • 2403.19522 • Published • 15Note model_stock
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper • 2311.03099 • Published • 33Note dare
Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 19Note ties
Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
Paper • 2312.06795 • Published • 2Note breadcrumbs
Editing Models with Task Arithmetic
Paper • 2212.04089 • Published • 8Note task_arithmetic
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 27Note ram, ramplus_tl
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
Paper • 2502.04959 • Published • 12Note iso-c
Accurate and Efficient Low-Rank Model Merging in Core Space
Paper • 2509.17786 • Published • 3Note core_space
Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification
Paper • 2506.01631 • Published • 1Note tensorguard
Fully Hyperbolic Neural Networks
Paper • 2105.14686 • Published • 1Note hyperbolic_karcher
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Paper • 2310.06824 • Published • 1Note mmt
Task Singular Vectors: Reducing Task Interference in Model Merging
Paper • 2412.00081 • PublishedNote tsv
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Paper • 2604.28109 • Published • 1Note t-switch
Parameter Competition Balancing for Model Merging
Paper • 2410.02396 • Published • 1Note pcb
Generalizing the Geometry of Model Merging Through Frechet Averages
Paper • 2604.27155 • Published • 1Note geomerge
DC-Merge: Improving Model Merging with Directional Consistency
Paper • 2603.06242 • Published • 1Note dc_merge
Model Merging in the Essential Subspace
Paper • 2602.20208 • Published • 1Note esd
Sparsity-Aware Evolution for Model Merging
Paper • 2602.08218 • Published • 1Note sae
Orthogonal Model Merging
Paper • 2602.05943 • Published • 1Note orthomerge
Bayesian Model Merging
Paper • 2605.12843 • Published • 1Note bmm
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
Paper • 2605.11679 • Published • 1Note mora, moramax
Cusp Formation in Merging Black Hole Horizons
Paper • 2605.10874 • Published • 1Note bh_cusp