Image de couverture de livre

Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Tan, Zhijie, Li, Yuzhi, Meng, Shengwei, Yuan, Xiang, Li, Weiping, Mo, Tong, Wang, Bingce, Chu, Xu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better
par: Chu, Xu, et autres
Publié: (2025)

Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning
par: Yang, Zexian, et autres
Publié: (2025)

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
par: Chu, Xu, et autres
Publié: (2025)

InstructAttribute: Fine-grained Object Attributes editing with Instruction
par: Yin, Xingxi, et autres
Publié: (2025)

Evaluating Multiview Object Consistency in Humans and Image Models
par: Bonnen, Tyler, et autres
Publié: (2024)

Mitigating Object Hallucinations via Sentence-Level Early Intervention
par: Peng, Shangpin, et autres
Publié: (2025)

Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
par: Chu, Xu, et autres
Publié: (2025)

Instruction Guided Multi Object Image Editing with Quantity and Layout Consistency
par: Tan, Jiaqi, et autres
Publié: (2025)

Mitigating Object Hallucination via Concentric Causal Attention
par: Xing, Yun, et autres
Publié: (2024)

Energy-Guided Decoding for Object Hallucination Mitigation
par: Liu, Xixi, et autres
Publié: (2025)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
par: Sun, Han, et autres
Publié: (2026)

HIME: Mitigating Object Hallucinations in LVLMs via Hallucination Insensitivity Model Editing
par: Akl, Ahmed, et autres
Publié: (2026)

Analyzing and Mitigating Object Hallucination: A Training Bias Perspective
par: Li, Yifan, et autres
Publié: (2025)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
par: Li, Shuo, et autres
Publié: (2025)

Mitigating Image Captioning Hallucinations in Vision-Language Models
par: Zhao, Fei, et autres
Publié: (2025)

Mitigating Object Hallucination via Robust Local Perception Search
par: Gao, Zixian, et autres
Publié: (2025)

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models
par: Yan, Qiao, et autres
Publié: (2025)

Extending Depth of Field for Varifocal Multiview Images
par: Li, Zhilong, et autres
Publié: (2024)

NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?
par: Li, Jiaxuan, et autres
Publié: (2024)

DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
par: Wang, JiYang, et autres
Publié: (2026)

Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models
par: Tan, Zhijie, et autres
Publié: (2024)

Multiview Image-Based Localization
par: Fiore, Cameron, et autres
Publié: (2025)

Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
par: Zhang, Jinrui, et autres
Publié: (2024)

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
par: Tong, Bingkui, et autres
Publié: (2025)

MVD$^2$: Efficient Multiview 3D Reconstruction for Multiview Diffusion
par: Zheng, Xin-Yang, et autres
Publié: (2024)

Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution
par: Ren, Weiming, et autres
Publié: (2025)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
par: Li, Bin, et autres
Publié: (2025)

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
par: Zhang, Kejia, et autres
Publié: (2025)

Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
par: Li, Peng, et autres
Publié: (2024)

Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation
par: Li, Shuwei, et autres
Publié: (2026)

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
par: Wang, Tianbo, et autres
Publié: (2026)

SGG-R$^{\rm 3}$: From Next-Token Prediction to End-to-End Unbiased Scene Graph Generation
par: Feng, Jiaye, et autres
Publié: (2026)

Multiview Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
par: Li, Xianju, et autres
Publié: (2024)

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
par: Wu, Yuanchen, et autres
Publié: (2025)

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
par: Li, Qiming, et autres
Publié: (2025)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
par: Dang, Tiantian, et autres
Publié: (2026)

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding
par: Yuan, Fan, et autres
Publié: (2024)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
par: Li, Qiming, et autres
Publié: (2025)

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
par: Gou, Yunhao, et autres
Publié: (2025)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
par: Lu, Yifan, et autres
Publié: (2025)