Image de couverture de livre

Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qin, Laiqiao, Zhu, Tianqing, Wang, Linlin, Zhou, Wanlei
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Safe and Reliable Diffusion Models via Subspace Projection
par: Chen, Huiqiang, et autres
Publié: (2025)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
par: Bian, Jieming, et autres
Publié: (2024)

OP-LoRA: The Blessing of Dimensionality
par: Teterwak, Piotr, et autres
Publié: (2024)

Feature Unlearning for Pre-trained GANs and VAEs
par: Moon, Saemi, et autres
Publié: (2023)

MOLM: Mixture of LoRA Markers
par: Fares, Samar, et autres
Publié: (2025)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
par: Zheng, Shenghe, et autres
Publié: (2025)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
par: Wang, Linlin, et autres
Publié: (2025)

MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality
par: Shi, Zhiyi, et autres
Publié: (2024)

Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation
par: Meral, Tuna Han Salih, et autres
Publié: (2024)

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
par: Zhong, Zihan, et autres
Publié: (2024)

KeepLoRA: Continual Learning with Residual Gradient Adaptation
par: Luo, Mao-Lin, et autres
Publié: (2026)

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
par: Ahn, Beomjin, et autres
Publié: (2026)

Ortho-Hydra: Orthogonalized Experts for DiT LoRA
par: Ji, Seunghyun
Publié: (2026)

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
par: He, Lingfeng, et autres
Publié: (2026)

ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
par: Shah, Viraj, et autres
Publié: (2023)

Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA
par: Abdal, Rameen, et autres
Publié: (2025)

Shared LoRA Subspaces for almost Strict Continual Learning
par: Kaushik, Prakhar, et autres
Publié: (2026)

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

Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
par: Yao, Dixi
Publié: (2024)

Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
par: Qin, Laiqiao, et autres
Publié: (2024)

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
par: Lu, Ziqi, et autres
Publié: (2024)

Multi-LoRA Composition for Image Generation
par: Zhong, Ming, et autres
Publié: (2024)

Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation
par: Wei, Xiwen, et autres
Publié: (2024)

Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
par: Choi, Joo Young, et autres
Publié: (2024)

Dual-Space Augmented Intrinsic-LoRA for Wind Turbine Segmentation
par: Singhal, Shubh, et autres
Publié: (2024)

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
par: Chen, Chieh-Yun, et autres
Publié: (2025)

Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models
par: Xuan, Hao, et autres
Publié: (2025)

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction
par: Lin, Hsi-Che, et autres
Publié: (2025)

Label-Free Cross-Task LoRA Merging with Null-Space Compression
par: Lee, Wonyoung, et autres
Publié: (2026)

Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
par: Smith, James Seale, et autres
Publié: (2023)

FM-LoRA: Factorized Low-Rank Meta-Prompting for Continual Learning
par: Yu, Xiaobing, et autres
Publié: (2025)

LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
par: Liu, Xuan, et autres
Publié: (2025)

CoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection
par: Senadeera, Damith Chamalke, et autres
Publié: (2026)

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

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
par: Jeong, Wooseong, et autres
Publié: (2026)

Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
par: Yang, Minghao, et autres
Publié: (2025)

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

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
par: Shenaj, Donald, et autres
Publié: (2026)

SR$^2$-LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning
par: Wan, Fengqiang, et autres
Publié: (2026)

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
par: Chen, Chuheng, et autres
Publié: (2025)