{"total":90,"rows":[{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"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":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248,"area":"moe"},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150,"area":"moe"},{"id":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111,"area":null},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"area":"moe"},{"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":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68,"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":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"area":"moe"},{"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":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2405.03133","title":"Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training","created":"2024-05-06","cited_by_count":37,"area":"moe"},{"id":"2401.02412","title":"LLM Augmented LLMs: Expanding Capabilities through Composition","created":"2024-01-04","cited_by_count":35,"area":null},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"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":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"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":"2501.15103","title":"Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task Learning","created":"2025-01-25","cited_by_count":13,"area":"moe"},{"id":"2310.02842","title":"Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","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":"2510.10977","title":"Revisiting Model Interpolation for Efficient Reasoning","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2604.04356","title":"REAM: Merging Improves Pruning of Experts in LLMs","created":"2026-04-06","cited_by_count":10,"area":"moe"},{"id":"2406.04801","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","created":"2024-06-07","cited_by_count":9,"area":"moe"},{"id":"2409.01483","title":"Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning","created":"2024-09-02","cited_by_count":8,"area":"moe"},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2506.05985","title":"Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2501.07890","title":"GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2502.00075","title":"BTS: Harmonizing Specialized Experts into a Generalist LLM","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2503.00634","title":"Efficiently Editing Mixture-of-Experts Models with Compressed Experts","created":"2025-03-01","cited_by_count":6,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","cited_by_count":6,"area":"moe"},{"id":"2310.15961","title":"Mixture of Tokens: Continuous MoE through Cross-Example Aggregation","created":"2023-10-24","cited_by_count":5,"area":"moe"},{"id":"2410.03440","title":"Exploring the Benefit of Activation Sparsity in Pre-training","created":"2024-10-04","cited_by_count":5,"area":"moe"},{"id":"2502.10743","title":"1bit-Merging: Dynamic Quantized Merging for Large Language Models","created":"2025-02-15","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":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"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":"2506.09919","title":"MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2508.01784","title":"RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model Merging","created":"2025-08-03","cited_by_count":4,"area":"moe"},{"id":"2601.09473","title":"SimMerge: Learning to Select Merge Operators from Similarity Signals","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2603.00573","title":"CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging","created":"2026-02-28","cited_by_count":4,"area":"moe"},{"id":"2603.08113","title":"SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2506.05928","title":"MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":3,"area":"moe"},{"id":"2509.10513","title":"Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning","created":"2025-09-03","cited_by_count":3,"area":"moe"},{"id":"2510.08987","title":"Towards Efficient Multimodal Unified Reasoning Model via Model Merging","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.16138","title":"Expert Merging in Sparse Mixture of Experts with Nash Bargaining","created":"2025-10-17","cited_by_count":3,"area":"moe"},{"id":"2512.18804","title":"Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation","created":"2025-12-21","cited_by_count":3,"area":null},{"id":"2603.04348","title":"RANGER: Sparsely-Gated Mixture-of-Experts with Adaptive Retrieval Re-ranking for Pathology Report Generation","created":"2026-03-04","cited_by_count":3,"area":"moe"},{"id":"2604.19048","title":"SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning","created":"2026-04-21","cited_by_count":3,"area":"moe"},{"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":"2410.09908","title":"Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2512.01461","title":"Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2602.17798","title":"Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds","created":"2026-02-19","cited_by_count":2,"area":"moe"},{"id":"2607.08601","title":"It Takes a MAESTRO To Prune Bad Experts","created":"2026-07-09","cited_by_count":2,"area":"moe"},{"id":"2405.13984","title":"Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2406.17935","title":"Sequential Editing for Lifelong Training of Speech Recognition Models","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2407.08176","title":"Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.18586","title":"Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing","created":"2025-05-24","cited_by_count":1,"area":"moe"},{"id":"2508.17250","title":"Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation","created":"2025-08-24","cited_by_count":1,"area":"distill"},{"id":"2510.01634","title":"CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2601.19451","title":"Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition","created":"2026-01-27","cited_by_count":1,"area":"moe"},{"id":"2603.00046","title":"REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2606.19036","title":"Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-Experts","created":"2026-06-17","cited_by_count":1,"area":"moe"},{"id":"2502.15483","title":"MoMa: A Modular Deep Learning Framework for Material Property Prediction","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2503.01268","title":"Multi-Level Collaboration in Model Merging","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.20446","title":"FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant Computing","created":"2025-04-29","cited_by_count":0,"area":"moe"},{"id":"2506.00002","title":"Advancing AI-assisted Hardware Design with Hierarchical Decentralized Training and Personalized Inference-Time Optimization","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2506.12597","title":"Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts","created":"2025-06-14","cited_by_count":0,"area":"moe"},{"id":"2509.19781","title":"Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference","created":"2025-09-24","cited_by_count":0,"area":"moe"},{"id":"2510.04286","title":"SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling","created":"2025-10-05","cited_by_count":0,"area":"moe"},{"id":"2604.21330","title":"Teacher-Guided Routing for Sparse Vision Mixture-of-Experts","created":"2026-04-23","cited_by_count":0,"area":"moe"},{"id":"2605.07837","title":"Approximation-Free Differentiable Oblique Decision Trees","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.26902","title":"Learning to Recover Task Experts from a Multi-Task Merged Model","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.26164","title":"Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.10605","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.28547","title":"DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.21346","title":"IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts","created":"2026-09-18","cited_by_count":0,"area":"moe"},{"id":"2610.02584","title":"Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute","created":"2026-10-01","cited_by_count":0,"area":"moe"},{"id":"2610.16171","title":"DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}