{"total":114,"rows":[{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2408.05517","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","created":"2024-08-10","cited_by_count":355,"area":"mllm"},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2405.19597","title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors","created":"2024-05-30","cited_by_count":58,"area":null},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"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":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","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":"2412.07775","title":"Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets","created":"2024-12-10","cited_by_count":32,"area":"diffusion"},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24,"area":"mllm"},{"id":"2412.17811","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models","created":"2024-12-23","cited_by_count":23,"area":"mllm"},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","cited_by_count":21,"area":null},{"id":"2502.13081","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey","created":"2025-02-18","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":"2401.13051","title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2406.10973","title":"ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts","created":"2024-06-16","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":"2409.17137","title":"PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization","created":"2024-09-25","cited_by_count":14,"area":null},{"id":"2512.05116","title":"Value Gradient Guidance for Flow Matching Alignment","created":"2025-12-04","cited_by_count":14,"area":"diffusion"},{"id":"2408.10280","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2507.12142","title":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2402.11417","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","created":"2024-02-18","cited_by_count":12,"area":null},{"id":"2502.04728","title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","created":"2025-02-07","cited_by_count":12,"area":"wm"},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2506.14530","title":"Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2506.15684","title":"Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards","created":"2025-06-18","cited_by_count":11,"area":"diffusion"},{"id":"2409.00119","title":"3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2410.08598","title":"Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2410.21759","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","created":"2024-10-29","cited_by_count":10,"area":"diffusion"},{"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":"2503.18225","title":"DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation","created":"2025-03-23","cited_by_count":10,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"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":"2606.13657","title":"Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation","created":"2026-06-11","cited_by_count":10,"area":"distill"},{"id":"2505.18877","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2401.16184","title":"Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2406.09384","title":"Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models","created":"2024-06-13","cited_by_count":8,"area":null},{"id":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2505.12532","title":"Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2505.20211","title":"PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2405.21050","title":"Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models","created":"2024-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2409.14836","title":"Orthogonal Finetuning for Direct Preference Optimization","created":"2024-09-23","cited_by_count":5,"area":"alignment"},{"id":"2502.06916","title":"QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2502.13533","title":"Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models","created":"2025-02-19","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":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2605.29843","title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2407.19342","title":"Parameter-Efficient Fine-Tuning via Circular Convolution","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2503.20282","title":"Faster Parameter-Efficient Tuning with Token Redundancy Reduction","created":"2025-03-26","cited_by_count":4,"area":"inference"},{"id":"2505.11235","title":"Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2511.06225","title":"MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition","created":"2025-11-09","cited_by_count":4,"area":"mllm"},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2410.06364","title":"Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2411.17426","title":"CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2412.08685","title":"ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2501.08727","title":"Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2505.12378","title":"Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2505.16531","title":"HOFT: Householder Orthogonal Fine-tuning","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2507.13260","title":"Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2605.31484","title":"Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2407.13427","title":"DeepClair: Utilizing Market Forecasts for Effective Portfolio Selection","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2408.17383","title":"MoRe Fine-Tuning with 10x Fewer Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2410.09692","title":"ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2502.01703","title":"QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2503.07399","title":"Exploring Representation Invariance in Finetuning","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2511.06859","title":"TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-Tuning","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2512.03056","title":"Delta Sampling: Data-Free Knowledge Transfer Across Diffusion Models","created":"2025-11-25","cited_by_count":2,"area":"diffusion"},{"id":"2605.28902","title":"Orthogonal Concept Erasure for Diffusion Models","created":"2026-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2408.13714","title":"TalkLoRA: Low-Rank Adaptation for Speech-Driven Animation","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2503.19530","title":"VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.00396","title":"SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2505.14367","title":"Dual Decomposition of Weights and Singular Value Low Rank Adaptation","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.17153","title":"Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2505.19888","title":"Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.06483","title":"Noise Consistency Regularization for Improved Subject-Driven Image Synthesis","created":"2025-06-06","cited_by_count":1,"area":"diffusion"},{"id":"2511.10707","title":"Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2511.18519","title":"CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2512.17344","title":"Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2607.00183","title":"DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation","created":"2026-06-30","cited_by_count":1,"area":"diffusion"},{"id":"2607.02576","title":"CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2501.06884","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","created":"2025-01-12","cited_by_count":0,"area":"moe"},{"id":"2505.15592","title":"VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.22105","title":"Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.17264","title":"OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2507.01806","title":"LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.07140","title":"Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2507.18076","title":"Hybrid and Unitary PEFT for Resource-Efficient Large Language Models","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2509.18629","title":"HyperAdapt: Simple High-Rank Adaptation","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.17734","title":"Efficient Tensor Completion Algorithms for Highly Oscillatory Operators","created":"2025-10-20","cited_by_count":0,"area":null},{"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":"2601.19739","title":"TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2603.27383","title":"Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.08368","title":"SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.21901","title":"GiVA: Gradient-Informed Bases for Vector-Based Adaptation","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.03252","title":"Ortho-Hydra: Orthogonalized Experts for DiT LoRA","created":"2026-05-05","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}