No article text was recorded for this version.
generative model unlearning
Version 1 of 158 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Approximate Data Deletion in Generative Models
- Blog: Generative Adversarial Networks Unlearning
- Blog: Label Smoothing Improves Machine Unlearning
- Blog: A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services
- Blog: Soft Prompting for Unlearning in Large Language Models
- Blog: Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection
- Blog: ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
- Blog: Selective Fine-Tuning for Targeted and Robust Concept Unlearning
- Blog: Concept Forgetting via Label Annealing
- Blog: BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
- Blog: RRL: Recommendation Reverse Learning
- Blog: Label Smoothing Improves Machine Unlearning
- Blog: ESC: Erasing Space Concept for Knowledge Deletion
- Blog: Not All Wrong is Bad: Using Adversarial Examples for Unlearning
- Blog: Exploring Nonlinear Pathway in Parameter Space for Machine Unlearning
- Blog: Tackling Fake Forgetting through Uncertainty Quantification
- Blog: What makes unlearning hard and what to do about it
- Blog: SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
- Blog: Improved Localized Machine Unlearning Through the Lens of Memorization
- Blog: Deep Unlearning: Fast and Efficient Gradient-free Class Forgetting
- Blog: Fishers Harvest Parallel Unlearning in Inherited Model Networks
- Blog: Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning
- Blog: Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks
- Blog: Machine Unlearning for Image-to-Image Generative Models
- Blog: Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks
- Blog: AMUN: Adversarial Machine UNlearning
- Blog: Learning to Unlearn for Robust Machine Unlearning
- Blog: Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
- Blog: Siamese Machine Unlearning with Knowledge Vaporization and Concentration
- Blog: Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction
- Blog: Group-robust Machine Unlearning
- Blog: An Information Theoretic Evaluation Metric for Strong Unlearning
- Blog: Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
- Blog: Generative Unlearning for Any Identity
- Blog: Low Compute Unlearning via Sparse Representations
- Blog: Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
- Blog: Unlearning Isn’t Forgetting: Revealing Hidden Leakage in Class Unlearning Evaluations
- Blog: Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
- Blog: A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
- Blog: Machine Unlearning for Document Classification
- Blog: Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
- Blog: Revisiting Machine Unlearning with Dimensional Alignment
- Blog: Zero-shot CLIP Class Forgetting via Text-image Space Adaptation
- Blog: An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
- Blog: Black-Box Forgetting
- Blog: SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities
- Blog: Fine-Grained and Efficient Self-Unlearning with Layered Iteration
- Blog: Coded Machine Unlearning
- Blog: Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning
- Blog: Privacy Adhering Machine Un-learning in NLP
- Blog: RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator
- Blog: Machine Unlearning via Simulated Oracle Matching
- Blog: Machine Unlearning in Low-Dimensional Feature Subspace
- Blog: Not All Wrong is Bad: Using Adversarial Examples for Unlearning
- Blog: Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models
- Blog: Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
- Blog: Rethinking Evaluation Methods for Machine Unlearning
- Blog: DisCEdit: Model Editing by Identifying Discriminative Components
History & citation
Current · Permanent link
- This direction split from Selective Forgetting in Deep Neural Networks (93% overlap)
- This direction split from catastrophic forgetting in unlearning (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_generative_model_unlearning_2593ee91,
title = {generative model unlearning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generative-model-unlearning/rdr_2593ee91559248ec8de1925583d3e96f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_generative_model_unlearning_2593ee91_v1,
title = {generative model unlearning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generative-model-unlearning/rdr_2593ee91559248ec8de1925583d3e96f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}