Image de couverture de livre

Why Instruction-Based Unlearning Fails in Diffusion Models?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Zeliang, Sun, Rui, Liu, Jiani, Wu, Qi, Xu, Chenliang
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language 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

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
par: Zhang, Zeliang, et autres
Publié: (2024)

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
par: Liu, Jiani, et autres
Publié: (2025)

Scaling Concept With Text-Guided Diffusion Models
par: Huang, Chao, et autres
Publié: (2024)

Targeted Forgetting of Image Subgroups in CLIP Models
par: Zhang, Zeliang, et autres
Publié: (2025)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
par: Tan, Zhangyun, et autres
Publié: (2026)

Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?
par: Zhang, Zeliang, et autres
Publié: (2024)

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
par: Zhang, Zeliang, et autres
Publié: (2025)

Video Understanding with Large Language Models: A Survey
par: Tang, Yolo Y., et autres
Publié: (2023)

Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
par: Feng, Mingqian, et autres
Publié: (2024)

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
par: Zhang, Zeliang, et autres
Publié: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
par: Gao, Hongcheng, et autres
Publié: (2024)

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
par: Yin, Hao, et autres
Publié: (2025)

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models
par: Xing, Shangyu, et autres
Publié: (2024)

Learning to Transform Dynamically for Better Adversarial Transferability
par: Zhu, Rongyi, et autres
Publié: (2024)

Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments
par: Hong, Haodong, et autres
Publié: (2024)

CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
par: Han, Insu, et autres
Publié: (2025)

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
par: Luo, Chuwei, et autres
Publié: (2024)

Otter: A Multi-Modal Model with In-Context Instruction Tuning
par: Li, Bo, et autres
Publié: (2023)

LLaVA-Video: Video Instruction Tuning With Synthetic Data
par: Zhang, Yuanhan, et autres
Publié: (2024)

Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding
par: Luo, Chuwei, et autres
Publié: (2022)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
par: Li, Yangfu, et autres
Publié: (2025)

Hierarchy-Aware Multimodal Unlearning for Medical AI
par: Wu, Fengli, et autres
Publié: (2025)

Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts
par: Hong, Haodong, et autres
Publié: (2024)

CLEAR: Character Unlearning in Textual and Visual Modalities
par: Dontsov, Alexey, et autres
Publié: (2024)

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
par: Miao, Daiye, et autres
Publié: (2025)

DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
par: Huang, Chao, et autres
Publié: (2025)

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
par: Nazir, Maham, et autres
Publié: (2026)

Maya: An Instruction Finetuned Multilingual Multimodal Model
par: Alam, Nahid, et autres
Publié: (2024)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
par: Zhang, Yihua, et autres
Publié: (2024)

Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models
par: Xu, Shilin, et autres
Publié: (2025)

Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
par: Liu, Zikang, et autres
Publié: (2025)

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
par: You, Zebin, et autres
Publié: (2025)

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
par: Zhang, Yanzhe, et autres
Publié: (2023)

ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation
par: Wu, Mengyang, et autres
Publié: (2024)

Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models
par: Huang, Yupan, et autres
Publié: (2023)

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
par: Fan, Zhiwen, et autres
Publié: (2025)

AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction
par: Xing, Zhen, et autres
Publié: (2024)

A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation
par: Zhou, Shijie, et autres
Publié: (2024)

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
par: Luo, Run, et autres
Publié: (2024)

Deciphering Oracle Bone Language with Diffusion Models
par: Guan, Haisu, et autres
Publié: (2024)