{"total":58,"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":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"area":null},{"id":"2502.18461","title":"K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs","created":"2025-02-25","cited_by_count":48,"area":null},{"id":"2509.17786","title":"Accurate and Efficient Low-Rank Model Merging in Core Space","created":"2025-09-22","cited_by_count":29,"area":null},{"id":"2503.05683","title":"WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs","created":"2025-03-07","cited_by_count":26,"area":null},{"id":"2412.12153","title":"Revisiting Weight Averaging for Model Merging","created":"2024-12-11","cited_by_count":25,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"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":"2505.11883","title":"MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging","created":"2025-05-17","cited_by_count":14,"area":null},{"id":"2502.07274","title":"Forget Forgetting: Continual Learning in a World of Abundant Memory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2509.21413","title":"Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity","created":"2025-09-25","cited_by_count":8,"area":null},{"id":"2603.06242","title":"DC-Merge: Improving Model Merging with Directional Consistency","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2505.22389","title":"Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2503.06921","title":"Task Vector Quantization for Memory-Efficient Model Merging","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2511.21437","title":"A Systematic Study of In-the-Wild Model Merging for Large Language Models","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2602.05536","title":"When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2509.23592","title":"Toward a Holistic Approach to Continual Model Merging","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2411.02813","title":"Sparse Orthogonal Parameters Tuning for Continual Learning","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2412.13526","title":"MOMA: Masked Orthogonal Matrix Alignment for Zero-Additional-Parameter Model Merging","created":"2024-12-18","cited_by_count":2,"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":"2510.08016","title":"Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2512.19320","title":"MAGIC: Achieving Superior Model Merging via Magnitude Calibration","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2603.05768","title":"Bridging Domains through Subspace-Aware Model Merging","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2412.19098","title":"SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2502.01015","title":"Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2506.21260","title":"DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.13211","title":"GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging","created":"2025-09-16","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":"2602.20796","title":"Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.02633","title":"Analytic Drift Resister for Non-Exemplar Continual Graph Learning","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.07965","title":"DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.12960","title":"DiM\\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.14841","title":"GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2501.13584","title":"Towards Robust Incremental Learning under Ambiguous Supervision","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2503.01164","title":"Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2507.23311","title":"Forgetting of task-specific knowledge in model merging-based continual learning","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.05059","title":"Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.12643","title":"Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2509.21898","title":"Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2602.00144","title":"Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.09888","title":"LCA: Local Classifier Alignment for Continual Learning","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.09713","title":"Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.17822","title":"GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.08311","title":"Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.20803","title":"Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.19384","title":"SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.24465","title":"Rethinking Expert Training for Model Merging with Prompt Learning","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.01184","title":"SAFE-Merge: Data-Free Continual Model Merging with General Knowledge Preservation","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.31096","title":"One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.17026","title":"CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18560","title":"The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.24612","title":"Beyond Uniform Subspaces: Spectrum-Aware and Depth-Adaptive Fusion for Multi-Task Model Merging","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32332","title":"When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.40333","title":"I Have a Stream: Making Self-Supervised Learning Work on Continuous Video","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00431","title":"ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}