Cover Image

Selective Fine-Tuning for Targeted and Robust Concept Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mansi, Kori, Avinash, Toni, Francesca, Demetriou, Soteris
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transparent Visual Reasoning via Object-Centric Agent Collaboration
by: Teoh, Benjamin, et al.
Published: (2025)

Grounded Object Centric Learning
by: Kori, Avinash, et al.
Published: (2023)

Identifiable Object Representations under Spatial Ambiguities
by: Kori, Avinash, et al.
Published: (2025)

Causal Representation Learning with Observational Grouping for CXR Classification
by: Rasal, Rajat, et al.
Published: (2025)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
by: Li, Qing, et al.
Published: (2025)

Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning
by: Devoto, Alessio, et al.
Published: (2024)

Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
by: Vasilescu, Vlad, et al.
Published: (2025)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
by: Oh, Changdae, et al.
Published: (2023)

Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
by: Xia, Tian, et al.
Published: (2025)

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
by: Elisha, Yehonatan, et al.
Published: (2026)

Adversarial 3D Virtual Patches using Integrated Gradients
by: You, Chengzeng, et al.
Published: (2024)

Factored Classifier-Free Guidance
by: Xia, Tian, et al.
Published: (2025)

ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]
by: Ayoobi, Hamed, et al.
Published: (2023)

Confounder-Aware Medical Data Selection for Fine-Tuning Pretrained Vision Models
by: Ji, Anyang, et al.
Published: (2025)

Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
by: Zeng, Hui, et al.
Published: (2024)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
by: Tan, Zhangyun, et al.
Published: (2026)

AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
by: Chen, Haokun, et al.
Published: (2025)

LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning
by: Zhang, Haotian, et al.
Published: (2025)

Large Pre-Training Datasets Don't Always Guarantee Robustness after Fine-Tuning
by: Hwang, Jaedong, et al.
Published: (2024)

Robust MLLM Unlearning via Visual Knowledge Distillation
by: Wang, Yuhang, et al.
Published: (2025)

Diffusion Counterfactual Generation with Semantic Abduction
by: Rasal, Rajat, et al.
Published: (2025)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
by: Lin, Shen, et al.
Published: (2026)

FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation
by: Woo, Young Beom, et al.
Published: (2025)

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
by: Kwon, Dahee, et al.
Published: (2025)

Visual Agentic Reinforcement Fine-Tuning
by: Liu, Ziyu, et al.
Published: (2025)

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
by: Kim, Hyeonjin, et al.
Published: (2026)

Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning
by: Tang, Ningyuan, et al.
Published: (2024)

RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
by: Ranjan, Ravi, et al.
Published: (2026)

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
by: Ramasubramanian, Shrinivas, et al.
Published: (2024)

BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning
by: Qian, Zekun, et al.
Published: (2026)

Flow Stochastic Segmentation Networks
by: Ribeiro, Fabio De Sousa, et al.
Published: (2025)

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
by: Balakrishnan, Ravikumar, et al.
Published: (2025)

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
by: Phute, Mansi, et al.
Published: (2025)

Fine-Tuning is Fine, if Calibrated
by: Mai, Zheda, et al.
Published: (2024)

Memory-Efficient Fine-Tuning for Quantized Diffusion Model
by: Ryu, Hyogon, et al.
Published: (2024)

Hierarchy-Aware Fine-Tuning of Vision-Language Models
by: Li, Jiayu, et al.
Published: (2025)

Remodeling Semantic Relationships in Vision-Language Fine-Tuning
by: Wu, Xiangyang, et al.
Published: (2025)

A Novel Adaptive Fine-Tuning Algorithm for Multimodal Models: Self-Optimizing Classification and Selection of High-Quality Datasets in Remote Sensing
by: Ren, Yi, et al.
Published: (2024)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
by: Moon, Saemi, et al.
Published: (2026)

Efficient Adversarial Training via Criticality-Aware Fine-Tuning
by: Li, Wenyun, et al.
Published: (2026)