{"total":68,"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":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88,"area":null},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"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":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"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":"2409.16167","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","created":"2024-09-24","cited_by_count":59,"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":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2403.00108","title":"LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem","created":"2024-02-29","cited_by_count":24,"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":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2603.04445","title":"Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey","created":"2026-02-23","cited_by_count":19,"area":"inference"},{"id":"2404.18928","title":"Stylus: Automatic Adapter Selection for Diffusion Models","created":"2024-04-29","cited_by_count":18,"area":"diffusion"},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2503.01155","title":"Nature-Inspired Population-Based Evolution of Large Language Models","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"area":"moe"},{"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":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2412.04300","title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2505.11883","title":"MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging","created":"2025-05-17","cited_by_count":14,"area":null},{"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":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"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":"2509.21164","title":"Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say","created":"2025-09-25","cited_by_count":12,"area":"lr"},{"id":"2506.12551","title":"MEraser: An Effective Fingerprint Erasure Approach for Large Language Models","created":"2025-06-14","cited_by_count":11,"area":"safety"},{"id":"2408.09856","title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2502.12988","title":"Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2403.16854","title":"An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2503.21780","title":"Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation","created":"2025-03-27","cited_by_count":7,"area":null},{"id":"2601.21795","title":"Effective LoRA Adapter Routing using Task Representations","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","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":"2505.24174","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"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":"2504.21239","title":"Memorization and Knowledge Injection in Gated LLMs","created":"2025-04-30","cited_by_count":3,"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":"2511.07129","title":"LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2606.03723","title":"Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter","created":"2026-06-02","cited_by_count":3,"area":null},{"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":"2512.11366","title":"qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMs","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","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":"2404.04949","title":"SilverSight: A Multi-Task Chinese Financial Large Language Model Based on Adaptive Semantic Space Learning","created":"2024-04-07","cited_by_count":1,"area":null},{"id":"2410.22911","title":"CopRA: A Progressive LoRA Training Strategy","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2502.16055","title":"MedForge: Building Medical Foundation Models Like Open Source Software Development","created":"2025-02-22","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":"2605.28577","title":"Continual Model Routing in Evolving Model Hubs","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2606.10617","title":"SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models","created":"2026-06-09","cited_by_count":1,"area":"diffusion"},{"id":"2505.19128","title":"RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2506.13479","title":"Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness","created":"2025-06-16","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":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2511.08626","title":"SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images","created":"2025-11-09","cited_by_count":0,"area":null},{"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":"2602.21222","title":"Task-Aware LoRA Adapter Composition via Similarity Retrieval in Vector Databases","created":"2026-02-01","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":"2605.01429","title":"SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.01858","title":"Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.19079","title":"Semantic Adapter Routing with Fine-Tuning Task Embeddings","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.11949","title":"ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models","created":"2026-08-12","cited_by_count":0,"area":"agents"},{"id":"2609.11414","title":"SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.30922","title":"JevSoup: System-One Routing for Training-Free LoRA Composition","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.01934","title":"Learning to Predict Distributions over Weight Updates for Test-Time Adaptation","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}