{"total":83,"rows":[{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"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":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194,"area":null},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133,"area":null},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"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":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2410.01335","title":"Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models","created":"2024-10-02","cited_by_count":21,"area":null},{"id":"2305.15253","title":"Rethinking the Evaluation Protocol of Domain Generalization","created":"2023-05-24","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":"2311.13171","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","created":"2023-11-22","cited_by_count":18,"area":null},{"id":"2312.16240","title":"Merging Vision Transformers from Different Tasks and Domains","created":"2023-12-25","cited_by_count":17,"area":null},{"id":"2505.22697","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","created":"2025-05-28","cited_by_count":17,"area":null},{"id":"2410.00911","title":"Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning","created":"2024-10-01","cited_by_count":16,"area":null},{"id":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2501.05559","title":"Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2402.07785","title":"HYPO: Hyperspherical Out-of-Distribution Generalization","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2408.01119","title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer","created":"2024-08-02","cited_by_count":13,"area":null},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2402.15414","title":"Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2312.15681","title":"Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2410.08000","title":"AHA: Human-Assisted Out-of-Distribution Generalization and Detection","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2510.21453","title":"Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP","created":"2025-10-24","cited_by_count":7,"area":null},{"id":"2403.16697","title":"DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization","created":"2024-03-25","cited_by_count":6,"area":null},{"id":"2502.05784","title":"Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble","created":"2025-02-09","cited_by_count":5,"area":null},{"id":"2502.18821","title":"CAMEx: Curvature-aware Merging of Experts","created":"2025-02-26","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":"2311.10291","title":"Leveraging Function Space Aggregation for Federated Learning at Scale","created":"2023-11-17","cited_by_count":4,"area":null},{"id":"2402.04644","title":"LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views","created":"2024-02-07","cited_by_count":4,"area":null},{"id":"2504.10902","title":"Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2505.21571","title":"FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2510.18052","title":"Measure-Theoretic Anti-Causal Representation Learning","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2406.15570","title":"DEM: Distribution Edited Model for Training with Mixed Data Distributions","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2412.17023","title":"Parameter-Efficient Interventions for Enhanced Model Merging","created":"2024-12-22","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2504.10231","title":"A Model Zoo of Vision Transformers","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2504.18072","title":"A Model Zoo on Phase Transitions in Neural Networks","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2410.05980","title":"Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.09446","title":"Harmonizing and Merging Source Models for CLIP-based Domain Generalization","created":"2025-06-11","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":"2605.26484","title":"Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2401.17790","title":"RADIN: Souping on a Budget","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2406.13025","title":"ABNet: Attention BarrierNet for Safe and Scalable Robot Learning","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2410.23883","title":"'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2504.10141","title":"The Impact of Model Zoo Size and Composition on Weight Space Learning","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2602.02890","title":"Self-Soupervision: Cooking Model Soups without Labels","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.09689","title":"Model soups need only one ingredient","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2610.00968","title":"Structure-agnostic Causal Representation Learning","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2411.00406","title":"MoD: A Distribution-Based Approach for Merging Large Language Models","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2411.13073","title":"Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2501.03782","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2503.06158","title":"Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2507.22576","title":"COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2508.02039","title":"Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.09223","title":"Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.19353","title":"Efficient Multi-Source Knowledge Transfer by Model Merging","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.06955","title":"High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.06982","title":"Revisiting Mixout: An Overlooked Path to Robust Finetuning","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2512.10818","title":"Self-Ensemble Post Learning for Noisy Domain Generalization","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.06552","title":"Fine-Grained Model Merging via Modular Expert Recombination","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.21372","title":"The Mean is the Mirage: Entropy-Adaptive Model Merging under Heterogeneous Domain Shifts in Medical Imaging","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.15421","title":"U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable exploration","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.17664","title":"Temporal Preference Optimization for Unsupervised Retrieval","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.09054","title":"Training-Free Task Vectors for LLM Behavioral Control","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.33437","title":"SMAT: Simple and Efficient Merge-Aware Training","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}