Imagen de Portada

Label-Free Cross-Task LoRA Merging with Null-Space Compression

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Wonyoung, Jeong, Wooseong, Yoon, Kuk-Jin
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
por: Jeong, Wooseong, et al.
Publicado: (2026)

Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
por: Jeong, Wooseong, et al.
Publicado: (2025)

Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training
por: Jeong, Wooseong, et al.
Publicado: (2025)

Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
por: Lee, Giwon, et al.
Publicado: (2025)

Quantifying Task Priority for Multi-Task Optimization
por: Jeong, Wooseong, et al.
Publicado: (2024)

LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
por: Liu, Xuan, et al.
Publicado: (2025)

LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
por: Shenaj, Donald, et al.
Publicado: (2024)

Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation
por: Singhal, Shubh, et al.
Publicado: (2024)

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
por: Zhang, Andi, et al.
Publicado: (2025)

Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
por: Yang, Minghao, et al.
Publicado: (2025)

Ortho-Hydra: Orthogonalized Experts for DiT LoRA
por: Ji, Seunghyun
Publicado: (2026)

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
por: Yang, Hunmin, et al.
Publicado: (2024)

FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning
por: Yu, Xiaobing, et al.
Publicado: (2025)

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
por: Smith, James Seale, et al.
Publicado: (2023)

Shared LoRA Subspaces for almost Strict Continual Learning
por: Kaushik, Prakhar, et al.
Publicado: (2026)

Vertical LoRA: Dense Expectation-Maximization Interpretation of Transformers
por: Fu, Zhuolin
Publicado: (2024)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
por: Zheng, Shenghe, et al.
Publicado: (2025)

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
por: Yang, Hunmin, et al.
Publicado: (2024)

DAC-LoRA: Dynamic Adversarial Curriculum for Efficient and Robust Few-Shot Adaptation
por: Umrajkar, Ved
Publicado: (2025)

Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
por: Choi, Joo Young, et al.
Publicado: (2024)

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction
por: Lin, Hsi-Che, et al.
Publicado: (2025)

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
por: Shenaj, Donald, et al.
Publicado: (2026)

Multi-LoRA Composition for Image Generation
por: Zhong, Ming, et al.
Publicado: (2024)

CoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection
por: Senadeera, Damith Chamalke, et al.
Publicado: (2026)

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
por: Chen, Chieh-Yun, et al.
Publicado: (2025)

Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
por: Zhang, Haojie, et al.
Publicado: (2025)

Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs
por: Thuau, Sébastien, et al.
Publicado: (2025)

DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
por: Liu, Jiaqi, et al.
Publicado: (2025)

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
por: Xu, Ziwen, et al.
Publicado: (2026)

Evolutionary Negative Module Pruning for Better LoRA Merging
por: Cao, Anda, et al.
Publicado: (2026)

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
por: Liang, Yan-Shuo, et al.
Publicado: (2024)

PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation
por: Hwang, Injoon, et al.
Publicado: (2024)

RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
por: Çelebi, Yusuf, et al.
Publicado: (2026)

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
por: Shah, Viraj, et al.
Publicado: (2023)

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
por: Chen, Chuheng, et al.
Publicado: (2025)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
por: Bian, Jieming, et al.
Publicado: (2024)

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
por: Lee, Seungeon, et al.
Publicado: (2025)

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
por: Che, Chang, et al.
Publicado: (2025)

Null-LoRA: Low-Rank Adaptation on Null Space
por: Zhang, Yi, et al.
Publicado: (2025)

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
por: Hu, Zixuan, et al.
Publicado: (2024)