Copertina

Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Quanjiang, Liu, Zhiming, Luo, Wei, Luo, Tingjin, Hou, Chenping
Natura:	Preprint
Pubblicazione:	2026
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

Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification
di: Li, Quanjiang, et al.
Pubblicazione: (2026)

CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
di: Huang, Xiaoyi, et al.
Pubblicazione: (2026)

Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
di: Liu, Zhining, et al.
Pubblicazione: (2025)

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
di: Xie, Yutong, et al.
Pubblicazione: (2026)

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
di: Chen, Cong, et al.
Pubblicazione: (2025)

Distracted Robot: How Visual Clutter Undermine Robotic Manipulation
di: Rasouli, Amir, et al.
Pubblicazione: (2025)

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
di: Zhao, Beidi, et al.
Pubblicazione: (2026)

When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
di: Cao, Fanpu, et al.
Pubblicazione: (2026)

BlurDM: A Blur Diffusion Model for Image Deblurring
di: He, Jin-Ting, et al.
Pubblicazione: (2025)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
di: Ghosh, Sreyan, et al.
Pubblicazione: (2024)

Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation
di: Gong, Boyang, et al.
Pubblicazione: (2026)

Object Isolated Attention for Consistent Story Visualization
di: Luo, Xiangyang, et al.
Pubblicazione: (2025)

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction
di: Tang, Hongyi, et al.
Pubblicazione: (2026)

Selective LoRA for Visual Tokens and Attention Heads
di: Luo, Tiange, et al.
Pubblicazione: (2025)

Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions
di: Ha, Jeongsoo, et al.
Pubblicazione: (2025)

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

Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment
di: Yin, Fan, et al.
Pubblicazione: (2026)

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
di: Jiang, Zhangqi, et al.
Pubblicazione: (2024)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
di: Ding, Wei, et al.
Pubblicazione: (2026)

What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
di: He, Yusheng, et al.
Pubblicazione: (2026)

ViRED: Prediction of Visual Relations in Engineering Drawings
di: Gu, Chao, et al.
Pubblicazione: (2024)

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
di: Li, Zhuowei, et al.
Pubblicazione: (2025)

TdAttenMix: Top-Down Attention Guided Mixup
di: Wang, Zhiming, et al.
Pubblicazione: (2025)

CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models
di: Chen, Kesheng, et al.
Pubblicazione: (2026)

CorrDetail: Visual Detail Enhanced Self-Correction for Face Forgery Detection
di: Zhou, Binjia, et al.
Pubblicazione: (2025)

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
di: Wang, Zhiqiang, et al.
Pubblicazione: (2026)

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection
di: Jiang, Lei, et al.
Pubblicazione: (2025)

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
di: Li, Yuanshuai, et al.
Pubblicazione: (2025)

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
di: Yu, Liu, et al.
Pubblicazione: (2025)

VIGC: Visual Instruction Generation and Correction
di: Wang, Bin, et al.
Pubblicazione: (2023)

Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction
di: Huang, Po-Hsuan, et al.
Pubblicazione: (2024)

3D WholeBody Pose Estimation based on Semantic Graph Attention Network and Distance Information
di: Wen, Sihan, et al.
Pubblicazione: (2024)

FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering
di: Tong, Chaodong, et al.
Pubblicazione: (2026)

Partial Convolution Meets Visual Attention
di: Huang, Haiduo, et al.
Pubblicazione: (2025)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
di: Xu, Haolei, et al.
Pubblicazione: (2026)

Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts
di: Sharma, Aditya, et al.
Pubblicazione: (2024)

LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models
di: Jiang, Zhiyuan, et al.
Pubblicazione: (2026)

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
di: Wu, Kai, et al.
Pubblicazione: (2024)

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing
di: Luo, Zhiming, et al.
Pubblicazione: (2026)