{"total":65,"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":"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":"2403.03870","title":"Learning to Decode Collaboratively with Multiple Language Models","created":"2024-03-06","cited_by_count":62,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","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":"2501.01230","title":"Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent","created":"2025-01-02","cited_by_count":39,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2502.01976","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2407.00066","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"area":"moe"},{"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":"2411.18729","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","created":"2024-11-27","cited_by_count":22,"area":null},{"id":"2504.00762","title":"Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute","created":"2025-04-01","cited_by_count":20,"area":"lr"},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2406.16989","title":"Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning","created":"2024-06-24","cited_by_count":14,"area":"rag"},{"id":"2409.02685","title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","created":"2024-09-04","cited_by_count":12,"area":"moe"},{"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":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2408.15901","title":"Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts","created":"2024-08-28","cited_by_count":7,"area":"moe"},{"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":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2512.04695","title":"TRINITY: An Evolved LLM Coordinator","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2506.14126","title":"From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2510.12266","title":"HiLoRA: Adaptive Hierarchical LoRA Routing for Training-Free Domain Generalization","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2505.18867","title":"Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2410.01497","title":"DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language Models","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2508.06831","title":"Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2607.04118","title":"Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2410.10896","title":"AT-MoE: Adaptive Task-planning Mixture of Experts via LoRA Approach","created":"2024-10-12","cited_by_count":1,"area":"moe"},{"id":"2505.23846","title":"Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.15964","title":"MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts Framework","created":"2025-09-19","cited_by_count":1,"area":"moe"},{"id":"2512.00391","title":"From Coefficients to Directions: Rethinking Model Merging with Directional Alignment","created":"2025-11-29","cited_by_count":1,"area":null},{"id":"2601.22157","title":"Discovering Hidden Gems in Model Repositories","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.22849","title":"R$^3$AG: Retriever Routing for Retrieval-Augmented Generation","created":"2026-04-22","cited_by_count":1,"area":"rag"},{"id":"2605.00419","title":"Rethinking LLM Ensembling from the Perspective of Mixture Models","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2505.10939","title":"GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2507.07140","title":"Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2507.14959","title":"Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2507.21199","title":"Advancing Compositional LLM Reasoning with Structured Task Relations in Interactive Multimodal Communications","created":"2025-07-28","cited_by_count":0,"area":"lr"},{"id":"2511.01831","title":"Routing-Based Continual Learning for Multimodal Large Language Models","created":"2025-11-03","cited_by_count":0,"area":"mllm"},{"id":"2512.08826","title":"CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2603.03535","title":"Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.18448","title":"Seeking Universal Shot Language Understanding Solutions","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.22755","title":"KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.28304","title":"Compositional Generalization in Autoregressive Models via Logit Composition","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.31413","title":"Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs","created":"2026-06-30","cited_by_count":0,"area":"lr"},{"id":"2607.10985","title":"MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration","created":"2026-07-13","cited_by_count":0,"area":"mllm"},{"id":"2608.04215","title":"A Unified Model for Cross-Domain Clone Detection via Model Merging","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.31600","title":"New LoRA Skills Should Read but Never Write","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36770","title":"Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}