Model Merging

Less is More: Efficient Model Merging with Binary Task Switch CVPR 2025 Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs ICLR 2025 Linear Mode Connectivity in Differentiable Tree Ensembles ICLR 2025 LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging ICLR 2025 LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs ACL 2025 Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs EMNLP 2025 LoRACLR: Contrastive Adaptation for Customization of Diffusion Models CVPR 2025 LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation ICCV 2025 LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs CVPR 2025 LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks COLING 2025 LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging EMNLP 2025 MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation ICLR 2025 Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement ICLR 2025 Measuring What Matters: Evaluating Ensemble LLMs with Label Refinement in Inductive Coding ACL 2025 MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs NAACL 2025 Mergenetic: a Simple Evolutionary Model Merging Library ACL 2025 MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities AAAI 2025 Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging EMNLP 2025 Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs EMNLP 2025 Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering ICLR 2025 MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality ACL 2025 Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models ICLR 2025 Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning ICLR 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents EMNLP 2025