Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | Novello, Nicola, Tonello, Andrea M. |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy
by: Novello, Nicola, et al.
Published: (2024)
by: Novello, Nicola, et al.
Published: (2024)
Robust Classification with Noisy Labels Based on Posterior Maximization
by: Novello, Nicola, et al.
Published: (2025)
by: Novello, Nicola, et al.
Published: (2025)
MACE: Mass Concept Erasure in Diffusion Models
by: Lu, Shilin, et al.
Published: (2024)
by: Lu, Shilin, et al.
Published: (2024)
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
by: Kim, Kwanyoung, et al.
Published: (2025)
by: Kim, Kwanyoung, et al.
Published: (2025)
Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
by: Bui, Anh, et al.
Published: (2025)
by: Bui, Anh, et al.
Published: (2025)
Closed-Form Concept Erasure via Double Projections
by: Zhang, Chi, et al.
Published: (2026)
by: Zhang, Chi, et al.
Published: (2026)
AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
by: Li, Fengpeng, et al.
Published: (2026)
by: Li, Fengpeng, et al.
Published: (2026)
CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
by: Xue, Yuyang, et al.
Published: (2025)
by: Xue, Yuyang, et al.
Published: (2025)
SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
by: Cheng, Chih-Chuan, et al.
Published: (2025)
by: Cheng, Chih-Chuan, et al.
Published: (2025)
Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
by: Moon, Saemi, et al.
Published: (2026)
by: Moon, Saemi, et al.
Published: (2026)
Scaling Attention via Feature Sparsity
by: Xie, Yan, et al.
Published: (2026)
by: Xie, Yan, et al.
Published: (2026)
Rethinking the Vulnerability of Concept Erasure and a New Method
by: Richardson, Alex D., et al.
Published: (2025)
by: Richardson, Alex D., et al.
Published: (2025)
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
by: Braun, Tobias, et al.
Published: (2025)
by: Braun, Tobias, et al.
Published: (2025)
HashAttention: Semantic Sparsity for Faster Inference
by: Desai, Aditya, et al.
Published: (2024)
by: Desai, Aditya, et al.
Published: (2024)
A Unified Framework for Diffusion Model Unlearning with f-Divergence
by: Novello, Nicola, et al.
Published: (2025)
by: Novello, Nicola, et al.
Published: (2025)
Copula Density Neural Estimation
by: Letizia, Nunzio A., et al.
Published: (2022)
by: Letizia, Nunzio A., et al.
Published: (2022)
TraSCE: Trajectory Steering for Concept Erasure
by: Jain, Anubhav, et al.
Published: (2024)
by: Jain, Anubhav, et al.
Published: (2024)
DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
by: Liu, Jiaqi, et al.
Published: (2025)
by: Liu, Jiaqi, et al.
Published: (2025)
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
by: Hu, Junhao, et al.
Published: (2025)
by: Hu, Junhao, et al.
Published: (2025)
Hidden-State Privacy Has an Empty Middle
by: Bell, Alexander Okezue
Published: (2026)
by: Bell, Alexander Okezue
Published: (2026)
Mutual Information Estimation via $f$-Divergence and Data Derangements
by: Letizia, Nunzio A., et al.
Published: (2023)
by: Letizia, Nunzio A., et al.
Published: (2023)
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
by: Chen, Hongxu, et al.
Published: (2025)
by: Chen, Hongxu, et al.
Published: (2025)
Post-Training Sparse Attention with Double Sparsity
by: Yang, Shuo, et al.
Published: (2024)
by: Yang, Shuo, et al.
Published: (2024)
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
by: Ren, Yuxin, et al.
Published: (2026)
by: Ren, Yuxin, et al.
Published: (2026)
Sparsity-Aware Evolution for Model Merging
by: Zhang, Huan, et al.
Published: (2026)
by: Zhang, Huan, et al.
Published: (2026)
SCALEX: Scalable Concept and Latent Exploration for Diffusion Models
by: Zeng, E. Zhixuan, et al.
Published: (2025)
by: Zeng, E. Zhixuan, et al.
Published: (2025)
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
by: Yang, Puning, et al.
Published: (2026)
by: Yang, Puning, et al.
Published: (2026)
EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models
by: Heo, Jaehoon, et al.
Published: (2025)
by: Heo, Jaehoon, et al.
Published: (2025)
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
by: Zhang, Jintao, et al.
Published: (2025)
by: Zhang, Jintao, et al.
Published: (2025)
Orthogonal Concept Erasure for Diffusion Models
by: Sun, Yuhao, et al.
Published: (2026)
by: Sun, Yuhao, et al.
Published: (2026)
Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery
by: Varshney, Payal, et al.
Published: (2024)
by: Varshney, Payal, et al.
Published: (2024)
Inference Time Debiasing Concepts in Diffusion Models
by: Kupssinskü, Lucas S., et al.
Published: (2025)
by: Kupssinskü, Lucas S., et al.
Published: (2025)
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
by: Grebe, Jonas Henry, et al.
Published: (2026)
by: Grebe, Jonas Henry, et al.
Published: (2026)
Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence
by: Suwal, Sanish, et al.
Published: (2025)
by: Suwal, Sanish, et al.
Published: (2025)
Improving Decision Sparsity
by: Sun, Yiyang, et al.
Published: (2024)
by: Sun, Yiyang, et al.
Published: (2024)
Homeostasis and Sparsity in Transformer
by: Kotyuzanskiy, Leonid, et al.
Published: (2024)
by: Kotyuzanskiy, Leonid, et al.
Published: (2024)
An Efficient Training Algorithm for Models with Block-wise Sparsity
by: Zhu, Ding, et al.
Published: (2025)
by: Zhu, Ding, et al.
Published: (2025)
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
by: Cywiński, Bartosz, et al.
Published: (2025)
by: Cywiński, Bartosz, et al.
Published: (2025)
Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
by: Shrestha, Susav, et al.
Published: (2025)
by: Shrestha, Susav, et al.
Published: (2025)
Crossfusor: A Cross-Attention Transformer Enhanced Conditional Diffusion Model for Car-Following Trajectory Prediction
by: You, Junwei, et al.
Published: (2024)
by: You, Junwei, et al.
Published: (2024)
Similar Items
-
$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy
by: Novello, Nicola, et al.
Published: (2024) -
Robust Classification with Noisy Labels Based on Posterior Maximization
by: Novello, Nicola, et al.
Published: (2025) -
MACE: Mass Concept Erasure in Diffusion Models
by: Lu, Shilin, et al.
Published: (2024) -
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
by: Kim, Kwanyoung, et al.
Published: (2025) -
Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
by: Bui, Anh, et al.
Published: (2025)