Copertina

AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Haokun, Li, Jianing, Zhang, Yao, Bi, Jinhe, Xia, Yan, Gu, Jindong, Tresp, Volker
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
di: Bi, Jinhe, et al.
Pubblicazione: (2024)

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
di: Chen, Haokun, et al.
Pubblicazione: (2024)

Multi-event Video-Text Retrieval
di: Zhang, Gengyuan, et al.
Pubblicazione: (2023)

Visual Question Decomposition on Multimodal Large Language Models
di: Zhang, Haowei, et al.
Pubblicazione: (2024)

True Multimodal In-Context Learning Needs Attention to the Visual Context
di: Chen, Shuo, et al.
Pubblicazione: (2025)

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
di: Li, Hang, et al.
Pubblicazione: (2023)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
di: Chen, Shuo, et al.
Pubblicazione: (2023)

Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
di: Gu, Chenhe, et al.
Pubblicazione: (2025)

Provably Better Explanations with Optimized Aggregation of Feature Attributions
di: Decker, Thomas, et al.
Pubblicazione: (2024)

AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction
di: Zhang, Gengyuan, et al.
Pubblicazione: (2025)

Localizing Events in Videos with Multimodal Queries
di: Zhang, Gengyuan, et al.
Pubblicazione: (2024)

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
di: Luo, Haochen, et al.
Pubblicazione: (2024)

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
di: Zhou, Xingcheng, et al.
Pubblicazione: (2025)

Efficient Multi-modal Large Language Models via Visual Token Grouping
di: Huang, Minbin, et al.
Pubblicazione: (2024)

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
di: Wang, Zefeng, et al.
Pubblicazione: (2024)

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

LLMRA: Multi-modal Large Language Model based Restoration Assistant
di: Jin, Xiaoyu, et al.
Pubblicazione: (2024)

Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
di: Li, Jiaqi, et al.
Pubblicazione: (2024)

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
di: Jin, Hyundong, et al.
Pubblicazione: (2026)

Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards
di: Yang, Xiaoyu, et al.
Pubblicazione: (2024)

METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
di: Wang, Mengyue, et al.
Pubblicazione: (2025)

Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoning
di: Zhang, Gengyuan, et al.
Pubblicazione: (2023)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
di: Zhang, Yimeng, et al.
Pubblicazione: (2024)

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
di: Xu, Weiye, et al.
Pubblicazione: (2025)

Initialization Matters for Adversarial Transfer Learning
di: Hua, Andong, et al.
Pubblicazione: (2023)

From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
di: Jiang, Dongsheng, et al.
Pubblicazione: (2023)

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
di: Wei, Cong, et al.
Pubblicazione: (2024)

Efficient Large Multi-modal Models via Visual Context Compression
di: Chen, Jieneng, et al.
Pubblicazione: (2024)

Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs
di: Zhang, Gengyuan, et al.
Pubblicazione: (2025)

Visual Hallucinations of Multi-modal Large Language Models
di: Huang, Wen, et al.
Pubblicazione: (2024)

VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
di: Yang, Bufang, et al.
Pubblicazione: (2024)

MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models
di: Chen, Tianwei, et al.
Pubblicazione: (2026)

Empowering Segmentation Ability to Multi-modal Large Language Models
di: Yang, Yuqi, et al.
Pubblicazione: (2024)

EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing
di: Zhang, Wei, et al.
Pubblicazione: (2024)

Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
di: Peng, Tianfan, et al.
Pubblicazione: (2025)

Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
di: Cheng, Hao, et al.
Pubblicazione: (2024)

FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance
di: Wang, Haicheng, et al.
Pubblicazione: (2025)

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
di: Zou, Yong, et al.
Pubblicazione: (2026)

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
di: Chen, Junkai, et al.
Pubblicazione: (2026)