Image de couverture de livre

Closed-Form Concept Erasure via Double Projections

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Chi, Cheng, Jingpu, Wang, Zhixian, Liu, Ping
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking the Vulnerability of Concept Erasure and a New Method
par: Richardson, Alex D., et autres
Publié: (2025)

MACE: Mass Concept Erasure in Diffusion Models
par: Lu, Shilin, et autres
Publié: (2024)

Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
par: Novello, Nicola, et autres
Publié: (2026)

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
par: Braun, Tobias, et autres
Publié: (2025)

Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
par: Chen, Hongxu, et autres
Publié: (2025)

TraSCE: Trajectory Steering for Concept Erasure
par: Jain, Anubhav, et autres
Publié: (2024)

Task-oriented Time Series Imputation Evaluation via Generalized Representers
par: Wang, Zhixian, et autres
Publié: (2024)

Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
par: Lazzati, Filippo, et autres
Publié: (2025)

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
par: Li, Fengpeng, et autres
Publié: (2026)

DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
par: Liu, Jiaqi, et autres
Publié: (2025)

EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning
par: Wang, Weiqi, et autres
Publié: (2026)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
par: Bui, Anh, et autres
Publié: (2025)

DiffLoad: Uncertainty Quantification in Electrical Load Forecasting with the Diffusion Model
par: Wang, Zhixian, et autres
Publié: (2023)

Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
par: Wetzel, Sebastian Johann
Publié: (2024)

Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
par: Peng, Bincheng, et autres
Publié: (2026)

Exact Stiefel Optimization for Probabilistic PLS: Closed-Form Updates, Error Bounds, and Calibrated Uncertainty
par: Hu, Haoran, et autres
Publié: (2026)

Continued AI Scaling Requires Repeated Efficiency Doublings
par: Lu, Chien-Ping
Publié: (2026)

Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
par: Grebe, Jonas Henry, et autres
Publié: (2026)

Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference
par: Lukashchuk, Mykola, et autres
Publié: (2026)

Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
par: Wetzel, Sebastian J., et autres
Publié: (2024)

Machine Unlearning under Retain-Forget Entanglement
par: Cheng, Jingpu, et autres
Publié: (2026)

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
par: Yang, Puning, et autres
Publié: (2026)

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
par: Hindupur, Sai Sumedh R., et autres
Publié: (2025)

Learning Discrete Concepts in Latent Hierarchical Models
par: Kong, Lingjing, et autres
Publié: (2024)

Derivation of Closed Form of Expected Improvement for Gaussian Process Trained on Log-Transformed Objective
par: Watanabe, Shuhei
Publié: (2024)

CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
par: Xue, Yuyang, et autres
Publié: (2025)

Palu: Compressing KV-Cache with Low-Rank Projection
par: Chang, Chi-Chih, et autres
Publié: (2024)

Asynchronous and Segmented Bidirectional Encoding for NMT
par: Yang, Jingpu, et autres
Publié: (2024)

SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
par: Zhang, Hanwei, et autres
Publié: (2026)

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset
par: Liu, Weijie, et autres
Publié: (2023)

Erasing with Precision: Evaluating Specific Concept Erasure from Text-to-Image Generative Models
par: Fuchi, Masane, et autres
Publié: (2025)

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
par: Hossain, Elias, et autres
Publié: (2026)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
par: Bu, Dake, et autres
Publié: (2025)

FL-TAC: Enhanced Fine-Tuning in Federated Learning via Low-Rank, Task-Specific Adapter Clustering
par: Ping, Siqi, et autres
Publié: (2024)

TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning
par: Li, Jiaxu, et autres
Publié: (2024)

Learning Equivariant Functions via Quadratic Forms
par: Karjol, Pavan, et autres
Publié: (2025)

Towards Better Generalization via Distributional Input Projection Network
par: Hao, Yifan, et autres
Publié: (2025)

Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
par: Dong, Zihan, et autres
Publié: (2026)

Many Ways to be Right: Rashomon Sets for Concept-Based Neural Networks
par: Feng, Shihan, et autres
Publié: (2025)

The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation
par: Jia, Hengrui, et autres
Publié: (2025)