Imagen de Portada

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Tianbo, Ma, Yuqing, Liao, Kewei, Zhang, Zhange, Li, Simin, Guo, Jinyang, Liu, Xianglong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
por: Cheng, Ruoxi, et al.
Publicado: (2026)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
por: Li, Jiaming, et al.
Publicado: (2025)

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
por: Wu, Yuanchen, et al.
Publicado: (2025)

HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing
por: Akl, Ahmed, et al.
Publicado: (2026)

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
por: Dastmalchi, Hamidreza, et al.
Publicado: (2026)

ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration
por: Yan, Bei, et al.
Publicado: (2026)

Energy-Guided Decoding for Object Hallucination Mitigation
por: Liu, Xixi, et al.
Publicado: (2025)

Kestrel: Grounding Self-Refinement for LVLM Hallucination Mitigation
por: Mao, Jiawei, et al.
Publicado: (2026)

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination
por: Gong, Xuan, et al.
Publicado: (2024)

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM
por: Zhong, Li'an, et al.
Publicado: (2026)

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes
por: Gong, Ruihao, et al.
Publicado: (2024)

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
por: Qian, Jiaye, et al.
Publicado: (2025)

An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing
por: Liang, Zihan, et al.
Publicado: (2025)

Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
por: Chen, Cheng, et al.
Publicado: (2025)

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
por: Li, Qiming, et al.
Publicado: (2026)

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
por: Huang, Yiyang, et al.
Publicado: (2025)

Mitigating Object Hallucinations via Sentence-Level Early Intervention
por: Peng, Shangpin, et al.
Publicado: (2025)

MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
por: Deng, Jingyuan, et al.
Publicado: (2025)

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
por: Cai, Jianfeng, et al.
Publicado: (2025)

Mitigating Backdoor Attacks using Activation-Guided Model Editing
por: Hsieh, Felix, et al.
Publicado: (2024)

ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment
por: Chen, Yiyang, et al.
Publicado: (2025)

Factuality Matters: When Image Generation and Editing Meet Structured Visuals
por: Zhuo, Le, et al.
Publicado: (2025)

Mitigating Object Hallucination via Concentric Causal Attention
por: Xing, Yun, et al.
Publicado: (2024)

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
por: Zhang, Jiacheng, et al.
Publicado: (2026)

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
por: Sarkar, Pritam, et al.
Publicado: (2024)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
por: Jiang, Nick, et al.
Publicado: (2024)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
por: Sun, Han, et al.
Publicado: (2026)

Mitigating Object Hallucination via Robust Local Perception Search
por: Gao, Zixian, et al.
Publicado: (2025)

PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
por: Mei, Hefei, et al.
Publicado: (2026)

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
por: Wu, Yebo, et al.
Publicado: (2026)

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
por: Shi, Ziqiang, et al.
Publicado: (2026)

Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
por: Nguyen, Tuan Dung, et al.
Publicado: (2026)

CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
por: Kan, Zhehan, et al.
Publicado: (2024)

QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks
por: Qin, Haotong, et al.
Publicado: (2026)

Do Vision Encoders Truly Explain Object Hallucination?: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
por: Oh, Hongseok, et al.
Publicado: (2025)

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
por: Zhang, Kejia, et al.
Publicado: (2025)

Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
por: Li, Jinlin, et al.
Publicado: (2025)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
por: Li, Qiming, et al.
Publicado: (2025)

Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
por: Yang, Le, et al.
Publicado: (2024)

Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
por: Liang, Xiao, et al.
Publicado: (2025)