{"total":91,"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":"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":"2407.05000","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","created":"2024-07-06","cited_by_count":141,"area":null},{"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":"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":"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":"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":"2311.11501","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":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"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":"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":"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":"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":"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":"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":"2405.15007","title":"RE-Adapt: Reverse Engineered Adaptation of Large Language Models","created":"2024-05-23","cited_by_count":9,"area":null},{"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":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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},{"id":"2402.00913","title":"Institutional Platform for Secure Self-Service Large Language Model Exploration","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2407.01291","title":"Lightweight Zero-shot Text-to-Speech with Mixture of Adapters","created":"2024-07-01","cited_by_count":2,"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":"2411.15831","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2507.00502","title":"Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2511.00056","title":"MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2402.18145","title":"Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2506.02882","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.22467","title":"SegmentAnyMuscle: A universal muscle segmentation model across different locations in MRI","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2509.18093","title":"SEQR: Secure and Efficient QR-based LoRA Routing","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2509.19602","title":"Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2603.26929","title":"Live Interactive Training for Video Segmentation","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2608.07693","title":"CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2609.33548","title":"TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2401.04051","title":"Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2401.16137","title":"X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2407.03674","title":"Short-Long Policy Evaluation with Novel Actions","created":"2024-07-04","cited_by_count":0,"area":null},{"id":"2407.20557","title":"CELLM: An Efficient Communication in Large Language Models Training for Federated Learning","created":"2024-07-30","cited_by_count":0,"area":null},{"id":"2408.09568","title":"MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2501.06332","title":"Aggregating Low Rank Adapters in Federated Fine-tuning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2506.07587","title":"PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2601.17616","title":"Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.19739","title":"TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2605.07111","title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.11712","title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.24783","title":"Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}