{"total":47,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25,"area":null},{"id":"2405.17897","title":"$C^2M^3$: Cycle-Consistent Multi-Model Merging","created":"2024-05-28","cited_by_count":20,"area":null},{"id":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2502.00264","title":"Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion","created":"2025-02-01","cited_by_count":16,"area":null},{"id":"2506.22712","title":"Generalized Linear Mode Connectivity for Transformers","created":"2025-06-28","cited_by_count":16,"area":null},{"id":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2505.23681","title":"Understanding Mode Connectivity via Parameter Space Symmetry","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2506.13234","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2312.09832","title":"Disentangling Linear Mode-Connectivity","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2406.16300","title":"Landscaping Linear Mode Connectivity","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2501.00061","title":"Training-free Heterogeneous Model Merging","created":"2024-12-29","cited_by_count":6,"area":null},{"id":"2402.05966","title":"Vanishing Feature: Diagnosing Model Merging and Beyond","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2505.02604","title":"Connecting Independently Trained Modes via Layer-Wise Connectivity","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2505.13900","title":"New Evidence of the Two-Phase Learning Dynamics of Neural Networks","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2502.12672","title":"Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.06001","title":"Analyzing the Role of Permutation Invariance in Linear Mode Connectivity","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2503.16316","title":"On the Cone Effect in the Learning Dynamics","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2509.23689","title":"Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.08023","title":"Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.08564","title":"M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2606.23607","title":"Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2405.14596","title":"Linear Mode Connectivity in Differentiable Tree Ensembles","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2410.22911","title":"CopRA: A Progressive LoRA Training Strategy","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2506.18135","title":"SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2510.09174","title":"Robustness and Regularization in Hierarchical Re-Basin","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.11268","title":"Exploring and Leveraging Class Vectors for Classifier Editing","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.13921","title":"Weight Weaving: Parameter Pooling for Data-Free Model Merging","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2511.04514","title":"Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2512.06297","title":"Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2602.23360","title":"Model Agreement via Anchoring","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2606.12498","title":"From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2405.15895","title":"Manifold Metric: A Loss Landscape Approach for Predicting Model Performance","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2410.12927","title":"Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2502.15483","title":"MoMa: A Modular Deep Learning Framework for Material Property Prediction","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2503.17905","title":"Finding Stable Subnetworks at Initialization with Dataset Distillation","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2506.02478","title":"FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2602.18658","title":"Communication-Efficient Personalized Adaptation via Federated-Local Model Merging","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2606.04754","title":"Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2610.00620","title":"Misalignment of Low-Loss Regions Causes Grokking","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}