{"total":758,"rows":[{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216,"area":"mllm"},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147,"area":"moe"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"area":null},{"id":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80,"area":null},{"id":"2407.18242","title":"LoRA-Pro: Are Low-Rank Adapters Properly Optimized?","created":"2024-07-25","cited_by_count":77,"area":null},{"id":"2405.17604","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","created":"2024-05-27","cited_by_count":76,"area":null},{"id":"2404.14619","title":"OpenELM: An Efficient Language Model Family with Open Training and Inference Framework","created":"2024-04-22","cited_by_count":75,"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":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2501.13198","title":"SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning","created":"2025-01-22","cited_by_count":63,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2407.08674","title":"Still-Moving: Customized Video Generation without Customized Video Data","created":"2024-07-11","cited_by_count":50,"area":null},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2406.11909","title":"Mixture-of-Subspaces in Low-Rank Adaptation","created":"2024-06-16","cited_by_count":47,"area":"diffusion"},{"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":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2404.06369","title":"WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs","created":"2024-04-09","cited_by_count":44,"area":null},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2405.17357","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","created":"2024-05-27","cited_by_count":43,"area":null},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"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":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2502.00987","title":"RandLoRA: Full-rank parameter-efficient fine-tuning of large models","created":"2025-02-03","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":"2410.20625","title":"LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization","created":"2024-10-27","cited_by_count":32,"area":null},{"id":"2405.12130","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","created":"2024-05-20","cited_by_count":31,"area":null},{"id":"2406.03136","title":"Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2509.17786","title":"Accurate and Efficient Low-Rank Model Merging in Core Space","created":"2025-09-22","cited_by_count":29,"area":null},{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2410.04010","title":"Hyperbolic Fine-Tuning for Large Language Models","created":"2024-10-05","cited_by_count":27,"area":null},{"id":"2404.18848","title":"FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2407.01920","title":"To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models","created":"2024-07-02","cited_by_count":26,"area":"safety"},{"id":"2410.03190","title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","created":"2024-10-04","cited_by_count":26,"area":"diffusion"},{"id":"2411.05877","title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","created":"2024-11-08","cited_by_count":26,"area":null},{"id":"2502.17159","title":"RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness","created":"2025-02-24","cited_by_count":26,"area":null},{"id":"2412.04077","title":"SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning","created":"2024-12-05","cited_by_count":24,"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":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2412.03665","title":"Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis","created":"2024-12-04","cited_by_count":23,"area":"mllm"},{"id":"2505.18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping","created":"2025-05-24","cited_by_count":23,"area":null},{"id":"2403.19243","title":"Efficient Learning With Sine-Activated Low-rank Matrices","created":"2024-03-28","cited_by_count":22,"area":null},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2410.04207","title":"Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models","created":"2024-10-05","cited_by_count":22,"area":null},{"id":"2411.19557","title":"Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning","created":"2024-11-29","cited_by_count":22,"area":null},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21,"area":null},{"id":"2502.12913","title":"GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2505.16270","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","created":"2025-05-22","cited_by_count":21,"area":null},{"id":"2505.20809","title":"Improved Representation Steering for Language Models","created":"2025-05-27","cited_by_count":21,"area":"mechinterp"},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2410.01359","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","created":"2024-10-02","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2506.16406","title":"Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights","created":"2025-06-19","cited_by_count":20,"area":null},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2405.20339","title":"Visual Perception by Large Language Model's Weights","created":"2024-05-30","cited_by_count":19,"area":"mllm"},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19,"area":"moe"},{"id":"2410.18035","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"id":"2411.13949","title":"SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning","created":"2024-11-21","cited_by_count":19,"area":"mllm"},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2505.15875","title":"Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging","created":"2025-05-21","cited_by_count":18,"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":"2406.13175","title":"Sparse High Rank Adapters","created":"2024-06-19","cited_by_count":17,"area":null},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2504.21099","title":"A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning","created":"2025-04-29","cited_by_count":17,"area":null},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2406.12832","title":"LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation","created":"2024-06-18","cited_by_count":16,"area":null},{"id":"2410.10450","title":"KBLaM: Knowledge Base augmented Language Model","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.17206","title":"Soft-Masked Diffusion Language Models","created":"2025-10-20","cited_by_count":16,"area":"diffusion"},{"id":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2406.08798","title":"FouRA: Fourier Low Rank Adaptation","created":"2024-06-13","cited_by_count":15,"area":"diffusion"},{"id":"2410.11160","title":"A Unified Framework with Multimodal Fine-tuning for Remote Sensing Semantic Segmentation","created":"2024-10-15","cited_by_count":15,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2501.11587","title":"Recurrent Diffusion for Large-Scale Parameter Generation","created":"2025-01-20","cited_by_count":15,"area":null},{"id":"2510.03255","title":"SciTS: Scientific Time Series Understanding and Generation with LLMs","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2404.10292","title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2407.05417","title":"See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition","created":"2024-07-07","cited_by_count":14,"area":null},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2501.15361","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","created":"2025-01-26","cited_by_count":14,"area":null}],"next_cursor":"100"}