Image de couverture de livre

Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gao, Daiheng, Jiang, Nanxiang, Zhang, Andi, Lu, Shilin, Tang, Yufei, Zhou, Wenbo, Zhang, Weiming, Fan, Zhaoxin
Format:	Preprint
Publié:	2025
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

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
par: Fan, Zhaoxin, et autres
Publié: (2026)

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
par: Gao, Daiheng, et autres
Publié: (2024)

Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
par: Jiang, Nanxiang, et autres
Publié: (2025)

Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
par: Jiang, Nanxiang, et autres
Publié: (2026)

Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation
par: Tang, Yufei, et autres
Publié: (2025)

MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
par: Wu, Pingyu, et autres
Publié: (2025)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
par: Sun, Yi, et autres
Publié: (2026)

When Are Concepts Erased From Diffusion Models?
par: Lu, Kevin, et autres
Publié: (2025)

EAR: Erasing Concepts from Unified Autoregressive Models
par: Fan, Haipeng, et autres
Publié: (2025)

Pruning for Robust Concept Erasing in Diffusion Models
par: Yang, Tianyun, et autres
Publié: (2024)

Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
par: Zhou, Juexiao, et autres
Publié: (2023)

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
par: Xie, Yiwei, et autres
Publié: (2026)

Side Effects of Erasing Concepts from Diffusion Models
par: Saha, Shaswati, et autres
Publié: (2025)

Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
par: Bui, Anh, et autres
Publié: (2024)

MolFORM: Preference-Aligned Multimodal Flow Matching for Structure-Based Drug Design
par: Zhang, Daiheng, et autres
Publié: (2025)

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
par: Duan, Shiying, et autres
Publié: (2025)

Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression
par: Xie, Yiwei, et autres
Publié: (2025)

Erased or Dormant? Rethinking Concept Erasure Through Reversibility
par: Liu, Ping, et autres
Publié: (2025)

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
par: Cassano, Enrico, et autres
Publié: (2025)

Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
par: Ahmadi, Saba, et autres
Publié: (2026)

Revoke vs. Restart in Unweighted Throughput Scheduling
par: He, Changdao
Publié: (2025)

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
par: Hong, Feng, et autres
Publié: (2025)

OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person
par: Sun, Ke, et autres
Publié: (2024)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
par: Chen, Hao, et autres
Publié: (2025)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
par: Seo, Hoigi, et autres
Publié: (2026)

Achieve Medium-Range SST Forecast by Rolling 1-Day Deep Learning
par: Nanxiang, Huang
Publié: (2026)

Exponential stabilization of fractional-order continuous-time dynamic systems via event-triggered impulsive control
par: Yu Nanxiang
Publié: (2022)

Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
par: Zhang, Tong, et autres
Publié: (2025)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
par: Tian, Zhihua, et autres
Publié: (2025)

Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
par: Li, Leyang, et autres
Publié: (2025)

Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models
par: Sridhar, Deepak, et autres
Publié: (2024)

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models
par: Ye, Xiaoyu, et autres
Publié: (2025)

Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning
par: Fuchi, Masane, et autres
Publié: (2024)

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
par: Das, Anudeep, et autres
Publié: (2025)

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
par: Li, Haoran, et autres
Publié: (2024)

Can We Optimize Deep RL Policy Weights as Trajectory Modeling?
par: Tang, Hongyao
Publié: (2025)

ESC: Erasing Space Concept for Knowledge Deletion
par: Lee, Tae-Young, et autres
Publié: (2025)

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
par: Huang, Chi-Pin, et autres
Publié: (2023)

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
par: Lyu, Mengyao, et autres
Publié: (2023)

DCA: Dividing and Conquering Amnesia in Incremental Object Detection
par: Zhang, Aoting, et autres
Publié: (2025)