Image de couverture de livre

CASteer: Cross-Attention Steering for Controllable Concept Erasure

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gaintseva, Tatiana, Oncescu, Andreea-Maria, Ma, Chengcheng, Liu, Ziquan, Benning, Martin, Slabaugh, Gregory, Deng, Jiankang, Elezi, Ismail
Format:	Preprint
Publié:	2025
Sujets:	Graphics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MidSteer: Optimal Affine Framework for Steering Generative Models
par: Gaintseva, Tatiana, et autres
Publié: (2026)

G3DR: Generative 3D Reconstruction in ImageNet
par: Reddy, Pradyumna, et autres
Publié: (2024)

RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement
par: Gaintseva, Tatiana, et autres
Publié: (2024)

SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing
par: Toker, Aysim, et autres
Publié: (2025)

From Attention to Activation: Unravelling the Enigmas of Large Language Models
par: Kaul, Prannay, et autres
Publié: (2024)

Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
par: Miles, Roy, et autres
Publié: (2026)

Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple View
par: Fu, Qifan, et autres
Publié: (2025)

CANRIG: Cross‐Attention Neural Face Rigging with Variable Local Control
par: Arad Mohammadi, et autres
Publié: (2026)

Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning
par: Ma, Chengcheng, et autres
Publié: (2023)

Improving Interpretability and Robustness for the Detection of AI-Generated Images
par: Gaintseva, Tatiana, et autres
Publié: (2024)

Deep Active Learning: A Reality Check
par: Gashi, Edrina, et autres
Publié: (2024)

$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections
par: Miles, Roy, et autres
Publié: (2024)

Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees
par: Ma, Zeyu, et autres
Publié: (2025)

ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting
par: Nishimura, Takuma, et autres
Publié: (2024)

Nested Attention: Semantic-aware Attention Values for Concept Personalization
par: Patashnik, Or, et autres
Publié: (2025)

CrossGen: Learning and Generating Cross Fields for Quad Meshing
par: Dong, Qiujie, et autres
Publié: (2025)

AvatarMMC: 3D Head Avatar Generation and Editing with Multi-Modal Conditioning
par: Para, Wamiq Reyaz, et autres
Publié: (2024)

Immersive Serious Games for Learning Physics Concepts: The Case of Density
par: Zhurakovskaia, Iuliia, et autres
Publié: (2024)

CAG-Avatar: Cross-Attention Guided Gaussian Avatars for High-Fidelity Head Reconstruction
par: Chang, Zhe, et autres
Publié: (2026)

How Historians Use Visualization: A Corpus-Backed Taxonomy and Analysis for Cross-Disciplinary Practice
par: Chen, Xinyue, et autres
Publié: (2026)

Double-Freeform Lens Design for Angular-Spatial Control of Light Fields
par: Sun, Yuou, et autres
Publié: (2026)

TopGen: Learning Structural Layouts and Cross-Fields for Quadrilateral Mesh Generation
par: Chen, Yuguang, et autres
Publié: (2026)

CAN: Concept‐Aligned Neurons for Visual Comparison of Deep Neural Network Models
par: M. Li, et autres
Publié: (2024)

LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
par: Sella, Etai, et autres
Publié: (2026)

Artistic Style Transfer Based on Attention with Knowledge Distillation
par: Hanadi Al‐Mekhlafi, et autres
Publié: (2024)

Winding Clearness for Differentiable Point Cloud Optimization
par: Xiao, Dong, et autres
Publié: (2024)

Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos
par: Jiang, Yuheng, et autres
Publié: (2025)

Investigating Crossing Perception in 3D Graph Visualisation
par: Zhang, Ying, et autres
Publié: (2025)

Controllable Layer Decomposition for Reversible Multi-Layer Image Generation
par: Liu, Zihao, et autres
Publié: (2025)

TransGI: Real-Time Dynamic Global Illumination With Object-Centric Neural Transfer Model
par: Deng, Yijie, et autres
Publié: (2025)

Anisotropic Green Coordinates
par: Xiao, Dong, et autres
Publié: (2025)

Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attention
par: Sella, Etai, et autres
Publié: (2023)

Creative Blends of Visual Concepts
par: Sun, Zhida, et autres
Publié: (2025)

From Cluster to Desktop: A Cache-Accelerated INR framework for Interactive Visualization of Tera-Scale Data
par: Zavorotny, Daniel, et autres
Publié: (2025)

Eulerian-Lagrangian Fluid Simulation on Particle Flow Maps
par: Zhou, Junwei, et autres
Publié: (2024)

COIVis: Eye-tracking-based Visual Exploration of Concept Learning in MOOC Videos
par: Zhou, Zhiguang, et autres
Publié: (2025)

CrossSet: Unveiling the Complex Interplay of Two Set-typed Dimensions in Multivariate Data
par: Matkovic, Kresimir, et autres
Publié: (2025)

Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation
par: Ng, Kam Woh, et autres
Publié: (2025)

Learning Conjugate Direction Fields for Planar Quadrilateral Mesh Generation
par: Tao, Jiong, et autres
Publié: (2025)

Data Visualization for Improving Financial Literacy: A Systematic Review
par: Du, Meng, et autres
Publié: (2025)