{"total":137,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"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":"2407.05000","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","created":"2024-07-06","cited_by_count":141,"area":null},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106,"area":"mllm"},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"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":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2311.11077","title":"Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning","created":"2023-11-18","cited_by_count":53,"area":null},{"id":"2403.18886","title":"Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning","created":"2024-03-27","cited_by_count":53,"area":null},{"id":"2412.12359","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","created":"2024-12-16","cited_by_count":51,"area":"mllm"},{"id":"2301.12132","title":"AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning","created":"2023-01-28","cited_by_count":49,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2309.09298","title":"OWL: A Large Language Model for IT Operations","created":"2023-09-17","cited_by_count":43,"area":null},{"id":"2402.11455","title":"LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks","created":"2024-02-18","cited_by_count":39,"area":null},{"id":"2407.09590","title":"Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts","created":"2024-07-12","cited_by_count":37,"area":"moe"},{"id":"2306.05406","title":"Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories","created":"2023-06-08","cited_by_count":34,"area":null},{"id":"2311.09179","title":"SiRA: Sparse Mixture of Low Rank Adaptation","created":"2023-11-15","cited_by_count":32,"area":"moe"},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32,"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":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26,"area":"mllm"},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2311.02684","title":"Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE","created":"2023-11-05","cited_by_count":25,"area":"moe"},{"id":"2402.08712","title":"BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation","created":"2024-02-13","cited_by_count":25,"area":null},{"id":"2403.11808","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","created":"2024-03-18","cited_by_count":25,"area":"moe"},{"id":"2406.00132","title":"QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2406.05130","title":"An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models","created":"2024-06-07","cited_by_count":22,"area":"mllm"},{"id":"2505.20809","title":"Improved Representation Steering for Language Models","created":"2025-05-27","cited_by_count":21,"area":"mechinterp"},{"id":"2402.18039","title":"ResLoRA: Identity Residual Mapping in Low-Rank Adaption","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2404.17245","title":"Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2412.05552","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","created":"2024-12-07","cited_by_count":16,"area":"moe"},{"id":"2505.23194","title":"Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2409.03659","title":"LLM-based multi-agent poetry generation in non-cooperative environments","created":"2024-09-05","cited_by_count":15,"area":"agents"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"area":"moe"},{"id":"2404.08417","title":"AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees","created":"2024-04-12","cited_by_count":14,"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":"2406.20030","title":"LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models","created":"2024-06-28","cited_by_count":14,"area":"moe"},{"id":"2305.13406","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2408.09053","title":"Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models","created":"2024-08-16","cited_by_count":11,"area":null},{"id":"2405.00557","title":"Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment","created":"2024-05-01","cited_by_count":10,"area":"lr"},{"id":"2503.23100","title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models","created":"2025-03-29","cited_by_count":10,"area":"moe"},{"id":"2509.16882","title":"Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation","created":"2025-09-21","cited_by_count":10,"area":"moe"},{"id":"2405.15007","title":"RE-Adapt: Reverse Engineered Adaptation of Large Language Models","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2407.03604","title":"Modality-Specialized Synergizers for Interleaved Vision-Language Generalists","created":"2024-07-04","cited_by_count":9,"area":"mllm"},{"id":"2502.15828","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","created":"2025-02-20","cited_by_count":9,"area":"moe"},{"id":"2305.16834","title":"Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging","created":"2023-05-26","cited_by_count":8,"area":null},{"id":"2306.14905","title":"PRISMA-DFLLM: An Extension of PRISMA for Systematic Literature Reviews using Domain-specific Finetuned Large Language Models","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2310.10094","title":"Decomposed Prompt Tuning via Low-Rank Reparameterization","created":"2023-10-16","cited_by_count":8,"area":null},{"id":"2411.00311","title":"C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning","created":"2024-11-01","cited_by_count":8,"area":null},{"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":"2507.05346","title":"LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2305.05901","title":"Text-guided High-definition Consistency Texture Model","created":"2023-05-10","cited_by_count":7,"area":"diffusion"},{"id":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2406.07007","title":"Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","cited_by_count":7,"area":"rag"},{"id":"2312.02923","title":"MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2407.11480","title":"AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2408.01505","title":"MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2411.00873","title":"CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2504.03454","title":"SpectR: Dynamically Composing LM Experts with Spectral Routing","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2504.21190","title":"TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-Experts","created":"2025-04-29","cited_by_count":6,"area":"moe"},{"id":"2603.13792","title":"IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring","created":"2026-03-14","cited_by_count":6,"area":null},{"id":"2402.00828","title":"Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters","created":"2024-02-01","cited_by_count":5,"area":"moe"},{"id":"2406.04984","title":"MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter","created":"2024-06-07","cited_by_count":5,"area":"moe"},{"id":"2406.17740","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2410.10589","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2412.02904","title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2505.23724","title":"SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.11265","title":"SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing","created":"2025-09-14","cited_by_count":5,"area":null},{"id":"2511.22880","title":"Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems","created":"2025-11-28","cited_by_count":5,"area":"inference"},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","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":"2403.09377","title":"Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2408.06610","title":"CROME: Cross-Modal Adapters for Efficient Multimodal LLM","created":"2024-08-13","cited_by_count":4,"area":"mllm"},{"id":"2411.01158","title":"Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction","created":"2024-11-02","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":"2412.11864","title":"Investigating Mixture of Experts in Dense Retrieval","created":"2024-12-16","cited_by_count":4,"area":"moe"},{"id":"2503.00572","title":"LoR2C : Low-Rank Residual Connection Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-03-01","cited_by_count":4,"area":null},{"id":"2505.22444","title":"On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2508.06953","title":"BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity","created":"2025-08-09","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":"2603.12378","title":"NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation","created":"2026-03-12","cited_by_count":4,"area":"moe"},{"id":"2305.08285","title":"Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2501.06892","title":"Language Fusion for Parameter-Efficient Cross-lingual Transfer","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2505.18451","title":"$\\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","created":"2025-05-24","cited_by_count":3,"area":"moe"},{"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":"2310.10532","title":"One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging For Cross-Lingual Transfer","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2311.13126","title":"Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper","created":"2023-11-22","cited_by_count":2,"area":null}],"next_cursor":"100"}