{"total":230,"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":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"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":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2403.19211","title":"Dual-Personalizing Adapter for Federated Foundation Models","created":"2024-03-28","cited_by_count":55,"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":"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":"2403.16073","title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","created":"2024-03-24","cited_by_count":41,"area":"agents"},{"id":"2404.09610","title":"LoRA Dropout as a Sparsity Regularizer for Overfitting Control","created":"2024-04-15","cited_by_count":35,"area":null},{"id":"2510.24795","title":"A Survey on Efficient Vision-Language-Action Models","created":"2025-10-27","cited_by_count":34,"area":"vla"},{"id":"2404.09957","title":"How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model","created":"2024-04-15","cited_by_count":32,"area":null},{"id":"2404.01322","title":"A Review of Multi-Modal Large Language and Vision Models","created":"2024-03-28","cited_by_count":30,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2406.02842","title":"DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut","created":"2024-06-05","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2402.02242","title":"Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2601.23286","title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","created":"2026-01-30","cited_by_count":23,"area":"diffusion"},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","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":"2402.06971","title":"In-Context Data Distillation with TabPFN","created":"2024-02-10","cited_by_count":19,"area":null},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2407.15793","title":"CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning","created":"2024-07-22","cited_by_count":17,"area":"mllm"},{"id":"2409.06214","title":"Towards Generalizable Scene Change Detection","created":"2024-09-10","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":"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":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.01631","title":"Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification","created":"2025-06-02","cited_by_count":14,"area":null},{"id":"2408.01119","title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer","created":"2024-08-02","cited_by_count":13,"area":null},{"id":"2410.08305","title":"Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12,"area":"mechinterp"},{"id":"2506.15606","title":"LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning","created":"2025-06-18","cited_by_count":12,"area":"safety"},{"id":"2501.16559","title":"LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation","created":"2025-01-27","cited_by_count":11,"area":"diffusion"},{"id":"2506.09958","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","created":"2025-06-11","cited_by_count":11,"area":"lr"},{"id":"2407.01873","title":"Automated Text Scoring in the Age of Generative AI for the GPU-poor","created":"2024-07-02","cited_by_count":10,"area":null},{"id":"2408.14572","title":"CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2410.15281","title":"LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends","created":"2024-10-20","cited_by_count":10,"area":"driving"},{"id":"2412.06289","title":"S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2410.09823","title":"Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models","created":"2024-10-13","cited_by_count":9,"area":null},{"id":"2503.23306","title":"Focus Directions Make Your Language Models Pay More Attention to Relevant Contexts","created":"2025-03-30","cited_by_count":9,"area":null},{"id":"2507.04599","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2409.10146","title":"LLMs4OL 2024 Overview: The 1st Large Language Models for Ontology Learning Challenge","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2410.10075","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2504.01919","title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2506.03189","title":"Continual Learning in Vision-Language Models via Aligned Model Merging","created":"2025-05-30","cited_by_count":8,"area":"mllm"},{"id":"2604.07765","title":"RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs","created":"2026-04-09","cited_by_count":8,"area":"agents"},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2409.15371","title":"MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2502.02069","title":"LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models","created":"2025-02-04","cited_by_count":7,"area":"mllm"},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2511.06202","title":"ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval","created":"2025-11-09","cited_by_count":7,"area":"vla"},{"id":"2410.06524","title":"Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA","created":"2024-10-09","cited_by_count":6,"area":"lr"},{"id":"2410.19230","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2601.13578","title":"FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning","created":"2026-01-20","cited_by_count":6,"area":"safety"},{"id":"2405.14446","title":"Worldwide Federated Training of Language Models","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2406.11047","title":"Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents","created":"2024-06-16","cited_by_count":5,"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":"2409.11393","title":"LLM-Agent-UMF: LLM-based Agent Unified Modeling Framework for Seamless Design of Multi Active/Passive Core-Agent Architectures","created":"2024-09-17","cited_by_count":5,"area":"agents"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2503.01936","title":"Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.11144","title":"MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling","created":"2025-03-14","cited_by_count":5,"area":"moe"},{"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":"2510.12178","title":"Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey","created":"2025-10-14","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":"2601.22905","title":"FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2605.05413","title":"From History to State: Constant-Context Skill Learning for LLM Agents","created":"2026-05-06","cited_by_count":5,"area":"agents"},{"id":"2409.01035","title":"Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning","created":"2024-09-02","cited_by_count":4,"area":null},{"id":"2412.18729","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","created":"2024-12-25","cited_by_count":4,"area":null},{"id":"2502.20527","title":"Supervised Fine-Tuning LLMs to Behave as Pedagogical Agents in Programming Education","created":"2025-02-27","cited_by_count":4,"area":"agents"},{"id":"2504.03563","title":"PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2504.03735","title":"Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots","created":"2025-04-01","cited_by_count":4,"area":"mllm"},{"id":"2504.21036","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2505.12871","title":"Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?","created":"2025-05-19","cited_by_count":4,"area":"safety"},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","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":"2509.09097","title":"DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2602.19534","title":"Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial","created":"2026-02-23","cited_by_count":4,"area":null},{"id":"2604.26934","title":"World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning","created":"2026-04-29","cited_by_count":4,"area":"wm"},{"id":"2406.04220","title":"BEADs: Bias Evaluation Across Domains","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2408.04910","title":"Unleashing Artificial Cognition: Integrating Multiple AI Systems","created":"2024-08-09","cited_by_count":3,"area":null},{"id":"2411.18412","title":"Adaptive Blind All-in-One Image Restoration","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2501.06836","title":"SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2504.16739","title":"Prompt-Tuning SAM: From Generalist to Specialist with only 2048 Parameters and 16 Training Images","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.00582","title":"Block Circulant Adapter for Large Language Models","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2506.04244","title":"Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models","created":"2025-05-29","cited_by_count":3,"area":"diffusion"},{"id":"2506.11103","title":"You Only Fine-tune Once: Many-Shot In-Context Fine-Tuning for Large Language Models","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2510.16985","title":"Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection","created":"2025-10-19","cited_by_count":3,"area":null},{"id":"2512.19297","title":"Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2601.09703","title":"ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation","created":"2026-01-14","cited_by_count":3,"area":"inference"},{"id":"2601.17921","title":"ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation","created":"2026-01-25","cited_by_count":3,"area":null}],"next_cursor":"100"}