Imagen de Portada

EAR: Erasing Concepts from Unified Autoregressive Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fan, Haipeng, Zhang, Shiyuan, Baohunesitu, Guo, Zihang, Zhang, Huaiwen
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking
por: Qian, Shengsheng, et al.
Publicado: (2023)

Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
por: Zhang, Tong, et al.
Publicado: (2025)

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
por: Cassano, Enrico, et al.
Publicado: (2025)

ESC: Erasing Space Concept for Knowledge Deletion
por: Lee, Tae-Young, et al.
Publicado: (2025)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
por: Seo, Hoigi, et al.
Publicado: (2026)

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
por: Fan, Zhaoxin, et al.
Publicado: (2026)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
por: Tian, Zhihua, et al.
Publicado: (2025)

Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
por: Zhu, Yongxin, et al.
Publicado: (2024)

V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
por: Zhang, Guiwei, et al.
Publicado: (2025)

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
por: Yu, Hao, et al.
Publicado: (2025)

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
por: Lyu, Mengyao, et al.
Publicado: (2023)

Erasing with Precision: Evaluating Specific Concept Erasure from Text-to-Image Generative Models
por: Fuchi, Masane, et al.
Publicado: (2025)

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing
por: Zhu, Hongguang, et al.
Publicado: (2025)

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation
por: Chen, Yinda, et al.
Publicado: (2024)

Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space
por: Wang, Zihang, et al.
Publicado: (2026)

HRVVS: A High-resolution Video Vasculature Segmentation Network via Hierarchical Autoregressive Residual Priors
por: Yao, Xincheng, et al.
Publicado: (2025)

APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning
por: Cao, Guiming, et al.
Publicado: (2024)

Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective
por: Yuan, Hangjie, et al.
Publicado: (2025)

Nexus-Gen: Unified Image Understanding, Generation, and Editing via Prefilled Autoregression in Shared Embedding Space
por: Zhang, Hong, et al.
Publicado: (2025)

LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
por: Gu, Difei, et al.
Publicado: (2026)

Composing Concepts from Images and Videos via Concept-prompt Binding
por: Kong, Xianghao, et al.
Publicado: (2025)

Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
por: Kwon, JuneHyoung, et al.
Publicado: (2026)

Speculative Decoding for Autoregressive Video Generation
por: Hu, Yuezhou, et al.
Publicado: (2026)

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
por: Zheng, Anlin, et al.
Publicado: (2025)

Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways
por: Liu, Yi, et al.
Publicado: (2025)

Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
por: Koma, Arian Komaei, et al.
Publicado: (2026)

Unified Medical Image Segmentation with State Space Modeling Snake
por: Zhang, Ruicheng, et al.
Publicado: (2025)

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
por: Chen, Ruidong, et al.
Publicado: (2025)

Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation
por: Xiang, Xunzhi, et al.
Publicado: (2025)

BlindU: Blind Machine Unlearning without Revealing Erasing Data
por: Wang, Weiqi, et al.
Publicado: (2026)

Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label
por: Kang, Byeongkeun, et al.
Publicado: (2024)

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
por: Ma, Yiyang, et al.
Publicado: (2024)

FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery
por: Zhang, Xiaokun, et al.
Publicado: (2026)

GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs
por: Zheng, Guanghao, et al.
Publicado: (2025)

Training-Free Text-Guided Image Editing with Visual Autoregressive Model
por: Wang, Yufei, et al.
Publicado: (2025)

FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design
por: Wei, Renjie, et al.
Publicado: (2025)

VisualRWKV-HD and UHD: Advancing High-Resolution Processing for Visual Language Models
por: Li, Zihang, et al.
Publicado: (2024)

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
por: Zhang, Haifei, et al.
Publicado: (2025)

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning
por: Zhuang, Xianwei, et al.
Publicado: (2025)

StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling
por: Jing, Liqi, et al.
Publicado: (2026)