{"total":77,"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":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122,"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":"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":"2402.17641","title":"Variational Learning is Effective for Large Deep Networks","created":"2024-02-27","cited_by_count":65,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2501.01230","title":"Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent","created":"2025-01-02","cited_by_count":39,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2311.09344","title":"Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization","created":"2023-11-15","cited_by_count":28,"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":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"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":"2504.14662","title":"Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning","created":"2025-04-20","cited_by_count":16,"area":null},{"id":"2505.02874","title":"Uncertainty Quantification for Machine Learning in Healthcare: A Survey","created":"2025-05-04","cited_by_count":14,"area":null},{"id":"2506.02041","title":"Enhancing Multimodal Continual Instruction Tuning with BranchLoRA","created":"2025-05-31","cited_by_count":14,"area":"mllm"},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2508.12531","title":"Rethinking Safety in LLM Fine-tuning: An Optimization Perspective","created":"2025-08-17","cited_by_count":14,"area":"lr"},{"id":"2406.03280","title":"FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2410.14389","title":"SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery","created":"2024-10-18","cited_by_count":12,"area":null},{"id":"2503.04872","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2504.18992","title":"Dynamic Fisher-weighted Model Merging via Bayesian Optimization","created":"2025-04-26","cited_by_count":12,"area":null},{"id":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2411.03055","title":"ATM: Improving Model Merging by Alternating Tuning and Merging","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2502.10339","title":"STAR: Spectral Truncation and Rescale for Model Merging","created":"2025-02-14","cited_by_count":11,"area":null},{"id":"2508.03121","title":"RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging","created":"2025-08-05","cited_by_count":11,"area":null},{"id":"2407.00487","title":"It's Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-objective Optimization","created":"2024-06-29","cited_by_count":10,"area":null},{"id":"2505.14136","title":"Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging","created":"2025-05-20","cited_by_count":9,"area":"moe"},{"id":"2411.09263","title":"Rethinking Weight-Averaged Model-merging","created":"2024-11-14","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":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"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":"2508.16082","title":"On Task Vectors and Gradients","created":"2025-08-22","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":"2601.22285","title":"Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2506.14262","title":"Knowledge Adaptation as Posterior Correction","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2411.04421","title":"Variational Low-Rank Adaptation Using IVON","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2508.21421","title":"Rethinking Layer-wise Model Merging through Chain of Merges","created":"2025-08-29","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":"2605.13030","title":"FeatCal: Feature Calibration for Post-Merging Models","created":"2026-05-13","cited_by_count":5,"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":"2510.21223","title":"Model Merging with Functional Dual Anchors","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2603.26317","title":"Label-Free Cross-Task LoRA Merging with Null-Space Compression","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2403.13341","title":"FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis","created":"2024-03-20","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":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2601.19503","title":"GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2411.18385","title":"Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization","created":"2024-11-27","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":"2502.12776","title":"Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2504.16732","title":"Simplified Swarm Learning Framework for Robust and Scalable Diagnostic Services in Cancer Histopathology","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2510.17895","title":"Hierarchical Federated Unlearning for Large Language Models","created":"2025-10-19","cited_by_count":2,"area":"safety"},{"id":"2511.05171","title":"Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2603.26299","title":"Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2409.17994","title":"CRoP: Context-wise Robust Static Human-Sensing Personalization","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2412.08147","title":"Variational Model Merging for Pareto Front Estimation in Multitask Finetuning","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2503.03384","title":"GNNMerge: Merging of GNN Models Without Accessing Training Data","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2505.16524","title":"CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving","created":"2025-05-22","cited_by_count":1,"area":"driving"},{"id":"2509.02108","title":"DivMerge: A divergence-based model merging method for multi-tasking","created":"2025-09-02","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":"2605.19409","title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2402.15202","title":"Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2509.10132","title":"Cost-Free Personalization via Information-Geometric Projection in Bayesian Federated Learning","created":"2025-09-12","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":"2602.21372","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":"2602.23869","title":"Open-Vocabulary Semantic Segmentation in Remote Sensing via Hierarchical Attention Masking and Model Composition","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2606.24007","title":"Fast and Slow Variational Continual Learning","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.01689","title":"Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space","created":"2026-07-02","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}],"next_cursor":null}