Model Merging

ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation CVPR 2026 BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning CVPR 2026 Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models CVPR 2026 Bridging Domains through Subspace-Aware Model Merging CVPR 2026 DC-Merge: Improving Model Merging with Directional Consistency CVPR 2026 Defending Unauthorized Model Merging via Dual-Stage Weight Protection CVPR 2026 DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation CVPR 2026 DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Merging CVPR 2026 Evolutionary Negative Module Pruning for Better LoRA Merging ACL 2026 Globscope: Toward a Global View of the Loss Landscape CVPR 2026 Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters ACL 2026 Label-Free Cross-Task LoRA Merging with Null-Space Compression CVPR 2026 MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models CVPR 2026 MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent CVPR 2026 Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space UAI 2026 Model Merging in the Essential Subspace CVPR 2026 Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning UAI 2026 Nature-Inspired Population-Based Evolution of Large Language Models ACL 2026 OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models CVPR 2026 Practical Guidelines for Model Merging in LLMs Pre-Training ACL 2026 Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy CVPR 2026 ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging ACL 2026 Understanding and Enforcing Weight Disentanglement in Task Arithmetic CVPR 2026 Why Do More Experts Fail? A Theoretical Analysis of Model Merging ACL 2026 A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment ACL 2025