{"total":127,"rows":[{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387,"area":null},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301,"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":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2309.14888","title":"Nearest Neighbor Guidance for Out-of-Distribution Detection","created":"2023-09-26","cited_by_count":64,"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":"2208.08914","title":"Prompt Vision Transformer for Domain Generalization","created":"2022-08-18","cited_by_count":52,"area":null},{"id":"2410.13025","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","created":"2024-10-16","cited_by_count":52,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2210.00912","title":"Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer","created":"2022-10-03","cited_by_count":40,"area":null},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35,"area":null},{"id":"2203.04600","title":"Domain Generalization using Pretrained Models without Fine-tuning","created":"2022-03-09","cited_by_count":29,"area":null},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2303.11674","title":"ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization","created":"2023-03-21","cited_by_count":28,"area":null},{"id":"2306.02879","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2409.15250","title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","created":"2024-09-23","cited_by_count":27,"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":"2505.06977","title":"CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging","created":"2025-05-11","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"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":"2404.00710","title":"Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2304.01973","title":"ERM++: An Improved Baseline for Domain Generalization","created":"2023-04-04","cited_by_count":18,"area":null},{"id":"2210.06807","title":"Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors","created":"2022-10-13","cited_by_count":17,"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":"2306.02595","title":"Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2407.15085","title":"Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization","created":"2024-07-21","cited_by_count":14,"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":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13,"area":null},{"id":"2303.07527","title":"Domain Generalization via Nuclear Norm Regularization","created":"2023-03-13","cited_by_count":12,"area":null},{"id":"2403.12029","title":"Align and Distill: Unifying and Improving Domain Adaptive Object Detection","created":"2024-03-18","cited_by_count":12,"area":null},{"id":"2209.01610","title":"Generalization in Neural Networks: A Broad Survey","created":"2022-09-04","cited_by_count":11,"area":null},{"id":"2310.11031","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2302.01497","title":"Gradient Estimation for Unseen Domain Risk Minimization with Pre-Trained Models","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2310.07361","title":"Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters","created":"2023-10-11","cited_by_count":9,"area":null},{"id":"2412.02856","title":"Is Large-Scale Pretraining the Secret to Good Domain Generalization?","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2506.01901","title":"Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2305.13046","title":"POEM: Polarization of Embeddings for Domain-Invariant Representations","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2404.07815","title":"Post-Hoc Reversal: Are We Selecting Models Prematurely?","created":"2024-04-11","cited_by_count":8,"area":null},{"id":"2502.06761","title":"When, Where and Why to Average Weights?","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2507.02288","title":"Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization","created":"2025-07-03","cited_by_count":8,"area":null},{"id":"2403.17592","title":"On the Benefits of Over-parameterization for Out-of-Distribution Generalization","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2405.11337","title":"A Unified Approach Towards Active Learning and Out-of-Distribution Detection","created":"2024-05-18","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":"2502.10749","title":"LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging","created":"2025-02-15","cited_by_count":7,"area":null},{"id":"2502.16770","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2503.02491","title":"Joint Out-of-Distribution Filtering and Data Discovery Active Learning","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2505.12745","title":"PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2511.20258","title":"Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2307.08187","title":"An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2310.06670","title":"Domain Generalization by Rejecting Extreme Augmentations","created":"2023-10-10","cited_by_count":5,"area":null},{"id":"2412.09006","title":"Motor Imagery Classification for Asynchronous EEG-Based Brain-Computer Interfaces","created":"2024-12-12","cited_by_count":5,"area":null},{"id":"2412.12830","title":"Differential Alignment for Domain Adaptive Object Detection","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2503.14897","title":"When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2503.18987","title":"Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2506.17718","title":"Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2507.04790","title":"Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning","created":"2025-07-07","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":"2307.08163","title":"Boundary-weighted logit consistency improves calibration of segmentation networks","created":"2023-07-16","cited_by_count":4,"area":null},{"id":"2309.04063","title":"INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2309.06337","title":"Exploring Flat Minima for Domain Generalization with Large Learning Rates","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2403.05523","title":"Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2403.09891","title":"Fisher Mask Nodes for Language Model Merging","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2410.22228","title":"Subgraph Aggregation for Out-of-Distribution Generalization on Graphs","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2507.03004","title":"CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2203.17067","title":"CADG: A Model Based on Cross Attention for Domain Generalization","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2205.09891","title":"Interpolating Compressed Parameter Subspaces","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2210.01360","title":"Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2307.06825","title":"A Causal Framework to Unify Common Domain Generalization Approaches","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2403.00946","title":"Fine-tuning with Very Large Dropout","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2403.11792","title":"SETA: Semantic-Aware Token Augmentation for Domain Generalization","created":"2024-03-18","cited_by_count":3,"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":"2407.12996","title":"Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2407.21028","title":"Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design","created":"2024-07-15","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":"2206.05912","title":"INDIGO: Intrinsic Multimodality for Domain Generalization","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2209.14742","title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2304.00629","title":"A principled approach to model validation in domain generalization","created":"2023-04-02","cited_by_count":2,"area":null},{"id":"2307.07181","title":"DISPEL: Domain Generalization via Domain-Specific Liberating","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2409.07796","title":"WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systems","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2502.10716","title":"Why Domain Generalization Fail? A View of Necessity and Sufficiency","created":"2025-02-15","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":"2509.00311","title":"MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2512.00940","title":"Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2305.16820","title":"Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2308.04515","title":"Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2406.01825","title":"Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2505.23844","title":"Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2511.19561","title":"Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2605.05136","title":"CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.17575","title":"UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts","created":"2026-05-17","cited_by_count":1,"area":null}],"next_cursor":"100"}