{"total":111,"rows":[{"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":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"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":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185,"area":null},{"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":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123,"area":null},{"id":"2502.09838","title":"HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation","created":"2025-02-14","cited_by_count":114,"area":"mllm"},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"id":"2401.16160","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","created":"2024-01-29","cited_by_count":84,"area":"mllm"},{"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":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2402.13717","title":"Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent","created":"2024-02-21","cited_by_count":52,"area":"agents"},{"id":"2405.20646","title":"LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation","created":"2024-05-31","cited_by_count":47,"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":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2406.13233","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models","created":"2024-06-19","cited_by_count":44,"area":"moe"},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2402.02803","title":"Large Language Model Distilling Medication Recommendation Model","created":"2024-02-05","cited_by_count":26,"area":null},{"id":"2605.27760","title":"SkillGrad: Optimizing Agent Skills Like Gradient Descent","created":"2026-05-26","cited_by_count":26,"area":"agents"},{"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":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"id":"2406.12529","title":"LLM4MSR: An LLM-Enhanced Paradigm for Multi-Scenario Recommendation","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2409.17508","title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","created":"2024-09-26","cited_by_count":19,"area":"mllm"},{"id":"2312.15450","title":"Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM","created":"2023-12-24","cited_by_count":18,"area":"agents"},{"id":"2405.17741","title":"LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design","created":"2024-05-28","cited_by_count":18,"area":"moe"},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2410.16038","title":"Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios","created":"2024-10-21","cited_by_count":17,"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":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2504.18383","title":"Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation","created":"2025-04-25","cited_by_count":15,"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":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2402.18099","title":"Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2411.08212","title":"PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model","created":"2024-11-12","cited_by_count":9,"area":"moe"},{"id":"2502.00089","title":"Ensembles of Low-Rank Expert Adapters","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2404.09027","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","created":"2024-04-13","cited_by_count":7,"area":"moe"},{"id":"2410.22782","title":"MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2504.07807","title":"Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models","created":"2025-04-10","cited_by_count":7,"area":"moe"},{"id":"2411.19064","title":"Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph","created":"2024-11-28","cited_by_count":6,"area":null},{"id":"2503.00908","title":"Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2506.12379","title":"Training-free LLM Merging for Multi-task Learning","created":"2025-06-14","cited_by_count":6,"area":null},{"id":"2410.15702","title":"Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2412.07405","title":"MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2503.06678","title":"Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2505.08542","title":"Guiding LLM-based Smart Contract Generation with Finite State Machine","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2505.15471","title":"CoLA: Collaborative Low-Rank Adaptation","created":"2025-05-21","cited_by_count":5,"area":"moe"},{"id":"2506.02827","title":"TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human Preference","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2506.11638","title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2506.14436","title":"MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation","created":"2025-06-17","cited_by_count":5,"area":"moe"},{"id":"2601.04823","title":"DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models","created":"2026-01-08","cited_by_count":5,"area":"moe"},{"id":"2605.05676","title":"Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2410.12926","title":"DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2410.16088","title":"Fine-Tuning LLMs for Reliable Medical Question-Answering Services","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2501.16125","title":"SampleLLM: Optimizing Tabular Data Synthesis in Recommendations","created":"2025-01-27","cited_by_count":4,"area":"synth"},{"id":"2506.09105","title":"MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2509.18942","title":"Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2509.21953","title":"MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment","created":"2025-09-26","cited_by_count":4,"area":"alignment"},{"id":"2501.06689","title":"TAPO: Task-Referenced Adaptation for Prompt Optimization","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2504.16394","title":"ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.00032","title":"MDD-LLM: Towards Accuracy Large Language Models for Major Depressive Disorder Diagnosis","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2505.18640","title":"ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2601.22828","title":"Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA","created":"2026-01-30","cited_by_count":3,"area":"mllm"},{"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":"2608.03275","title":"MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation","created":"2026-08-04","cited_by_count":3,"area":"moe"},{"id":"2410.21705","title":"AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2502.03884","title":"Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning","created":"2025-02-06","cited_by_count":2,"area":"moe"},{"id":"2502.15455","title":"R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-Task Learning","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.21227","title":"LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models","created":"2025-03-27","cited_by_count":2,"area":"mllm"},{"id":"2503.23362","title":"Mixture of Routers","created":"2025-03-30","cited_by_count":2,"area":"alignment"},{"id":"2504.05345","title":"ZeroED: Hybrid Zero-shot Error Detection through Large Language Model Reasoning","created":"2025-04-06","cited_by_count":2,"area":"lr"},{"id":"2510.00662","title":"Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2511.11460","title":"Rethinking Efficient Mixture-of-Experts for Remote Sensing Modality-Missing Classification","created":"2025-11-14","cited_by_count":2,"area":"moe"},{"id":"2402.01684","title":"A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs Using the CGC-LORA Algorithm","created":"2024-01-22","cited_by_count":1,"area":null},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2506.14235","title":"A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2507.11411","title":"Robust-Multi-Task Gradient Boosting","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2508.05078","title":"From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.11598","title":"MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.17705","title":"Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2511.13293","title":"Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval","created":"2025-11-17","cited_by_count":1,"area":"agents"},{"id":"2511.16147","title":"TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2601.10921","title":"RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2601.12460","title":"TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning","created":"2026-01-18","cited_by_count":1,"area":"safety"},{"id":"2601.17405","title":"HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2604.26340","title":"Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning","created":"2026-04-29","cited_by_count":1,"area":"moe"},{"id":"2605.25565","title":"RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism","created":"2026-05-25","cited_by_count":1,"area":"moe"},{"id":"2606.29425","title":"Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning","created":"2026-06-28","cited_by_count":1,"area":"agents"},{"id":"2608.16384","title":"Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation","created":"2026-08-17","cited_by_count":1,"area":"moe"},{"id":"2608.27338","title":"One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2501.06884","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","created":"2025-01-12","cited_by_count":0,"area":"moe"},{"id":"2502.08008","title":"An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2506.19702","title":"LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.01158","title":"Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA","created":"2025-09-01","cited_by_count":0,"area":"moe"},{"id":"2510.02194","title":"UpSafe$^\\circ$C: Upcycling for Controllable Safety in Large Language Models","created":"2025-10-02","cited_by_count":0,"area":"moe"},{"id":"2511.21733","title":"RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2601.19286","title":"ReToP: Learning to Rewrite Electronic Health Records for Clinical Prediction","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.12577","title":"Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation","created":"2026-03-13","cited_by_count":0,"area":"moe"}],"next_cursor":"100"}