{"total":81,"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":"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":"2412.12497","title":"NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning","created":"2024-12-17","cited_by_count":37,"area":"alignment"},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"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":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2406.16330","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2411.16815","title":"FREE-Merging: Fourier Transform for Efficient Model Merging","created":"2024-11-25","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":"2602.06485","title":"AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents","created":"2026-02-06","cited_by_count":12,"area":"agents"},{"id":"2411.03055","title":"ATM: Improving Model Merging by Alternating Tuning and Merging","created":"2024-11-05","cited_by_count":11,"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":"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":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2409.18893","title":"HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2410.08604","title":"MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2505.16703","title":"Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs","created":"2025-05-22","cited_by_count":7,"area":"mllm"},{"id":"2505.23561","title":"Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2601.22285","title":"Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2412.19819","title":"ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation","created":"2024-12-15","cited_by_count":6,"area":null},{"id":"2506.12379","title":"Training-free LLM Merging for Multi-task Learning","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2510.04601","title":"FedSRD: Sparsify-Reconstruct-Decompose for Communication-Efficient Federated Large Language Models Fine-Tuning","created":"2025-10-06","cited_by_count":6,"area":null},{"id":"2603.02945","title":"ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2506.14436","title":"MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation","created":"2025-06-17","cited_by_count":5,"area":"moe"},{"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":"2509.22034","title":"The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging","created":"2025-09-26","cited_by_count":4,"area":"lr"},{"id":"2604.05502","title":"AttnDiff: Attention-based Differential Fingerprinting for Large Language Models","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2410.08371","title":"Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2503.03874","title":"LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2508.17926","title":"AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2605.09584","title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","created":"2026-05-10","cited_by_count":3,"area":"lr"},{"id":"2410.13841","title":"A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2502.12217","title":"Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.15434","title":"Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.21088","title":"ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging","created":"2025-03-27","cited_by_count":2,"area":"safety"},{"id":"2503.21657","title":"Model Assembly Learning with Heterogeneous Layer Weight Merging","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2509.03122","title":"From Construction to Injection: Edit-Based Fingerprints for Large Language Models","created":"2025-09-03","cited_by_count":2,"area":null},{"id":"2511.11851","title":"Defending Unauthorized Model Merging via Dual-Stage Weight Protection","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","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":"2604.01674","title":"Can Heterogeneous Language Models Be Fused?","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.16727","title":"PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2605.19373","title":"Conflict-Free Replicated Data Types for Neural Network Model Merging: A Two-Layer Architecture Enabling CRDT-Compliant Model Merging Across 26 Strategies","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2606.19549","title":"Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates","created":"2026-06-17","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":"2601.21115","title":"Multi-task Code LLMs: Data Mix or Model Merge?","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"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":"2606.03344","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03391","title":"When Model Merging Breaks Routing: Training-Free Calibration for MoE","created":"2026-06-02","cited_by_count":1,"area":"moe"},{"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":"2607.19971","title":"Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2412.05830","title":"Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2505.18548","title":"Composable Cross-prompt Essay Scoring by Merging Models","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2508.19839","title":"PSO-Merging: Merging Models Based on Particle Swarm Optimization","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.12951","title":"Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2512.02689","title":"An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.09972","title":"AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.00585","title":"Exploring Information Seeking Agent Consolidation","created":"2026-01-31","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":"2603.01416","title":"Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents","created":"2026-03-02","cited_by_count":0,"area":"mllm"},{"id":"2603.04972","title":"Functionality-Oriented LLM Merging on the Fisher--Rao Manifold","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.16826","title":"Crowded in B-Space: Calibrating Shared Directions for LoRA Merging","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.03914","title":"Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.19523","title":"Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2606.00511","title":"Saliency-Aware Model Merging","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.04378","title":"DLLG: Dynamic Logit-Level Gating of LLM Experts","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.10090","title":"CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.25354","title":"Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement","created":"2026-08-26","cited_by_count":0,"area":"mechinterp"},{"id":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.26506","title":"A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.02273","title":"CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.06406","title":"Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.32422","title":"MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging","created":"2026-09-26","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},{"id":"2610.03199","title":"Predicting and Repairing Merge Collapse in Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04272","title":"Rethinking Self-Distillation for Multi-Teacher Capability Merging","created":"2026-10-03","cited_by_count":0,"area":"distill"},{"id":"2610.14762","title":"CrossMean: Model Merging by Pairing Merged and Expert Activations","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}