Cover Image

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Yanbin, Li, Yisen, Tie, Guiyao, Qu, Xiaoye, Zhou, Pan, Wang, Hongfei, Zou, Zhaofan, Sun, Hao, Li, Xuelong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attention to details, logits to truth: visual-aware attention and logits enhancement to mitigate hallucinations in LVLMs
by: Wang, Jingyi, et al.
Published: (2026)

Stop learning it all to mitigate visual hallucination, Focus on the hallucination target
by: Yoon, Dokyoon, et al.
Published: (2025)

Boosting Robust AIGI Detection with LoRA-based Pairwise Training
by: Xia, Ruiyang, et al.
Published: (2026)

Selective Volume Mixup for Video Action Recognition
by: Tan, Yi, et al.
Published: (2023)

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
by: Huang, Siyuan, et al.
Published: (2026)

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
by: Han, Feng, et al.
Published: (2025)

A Survey of AI Scientists
by: Tie, Guiyao, et al.
Published: (2025)

DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification
by: Saifullah, Saifullah, et al.
Published: (2025)

Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
by: Goel, Aman, et al.
Published: (2025)

LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
by: Zhou, Xueyang, et al.
Published: (2025)

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
by: Zhao, Wei, et al.
Published: (2025)

Optimizing Gastrointestinal Diagnostics: A CNN-Based Model for VCE Image Classification
by: Ahlawat, Vaneeta, et al.
Published: (2024)

Automated Safety Benchmarking: A Multi-agent Pipeline for LVLMs
by: Zhu, Xiangyang, et al.
Published: (2026)

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
by: Li, Yafu, et al.
Published: (2025)

GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?
by: Zou, Yueying, et al.
Published: (2026)

LVLMs and Humans Ground Differently in Referential Communication
by: Zeng, Peter, et al.
Published: (2026)

SEE: Continual Fine-tuning with Sequential Ensemble of Experts
by: Wang, Zhilin, et al.
Published: (2025)

LVLMs are Bad at Overhearing Human Referential Communication
by: Wang, Zhengxiang, et al.
Published: (2025)

A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT
by: Ganapathy, Nagarajan, et al.
Published: (2024)

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

GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
by: Park, Seongheon, et al.
Published: (2025)

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
by: Liu, Xuannan, et al.
Published: (2025)

Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling
by: Xiong, Shengwu., et al.
Published: (2025)

Unveiling contrasting impacts of heat mitigation and adaptation policies on U.S. internal migration
by: Li, Chao, et al.
Published: (2026)

Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation
by: Qu, Xiaoye, et al.
Published: (2024)

`Generalization is hallucination' through the lens of tensor completions
by: Wong, Liang Ze
Published: (2025)

A novel hallucination classification framework
by: Zavhorodnii, Maksym, et al.
Published: (2025)

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
by: Liu, Xuannan, et al.
Published: (2024)

From dots to faces: Individual differences in visual imagery capacity predict the content of Ganzflicker-induced hallucinations
by: Chkhaidze, Ana, et al.
Published: (2025)

Self-Improving Small Object Grounding in LVLMs
by: Yang, Tianze, et al.
Published: (2026)

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
by: Wang, Yuan, et al.
Published: (2024)

Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
by: Zhou, Xueyang, et al.
Published: (2025)

Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
by: Qu, Xiaoye, et al.
Published: (2024)

Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
by: Ding, Zhikai, et al.
Published: (2025)

VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection -- after competition results
by: Qiu, Bo-Cheng, et al.
Published: (2026)

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts
by: Sun, Weigao, et al.
Published: (2025)

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

PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset
by: Liu, Jiazhen, et al.
Published: (2024)

Benchmarking Corruption Robustness of LVLMs: A Discriminative Benchmark and Robustness Alignment Metric
by: Sui, Xiangjie, et al.
Published: (2025)

VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection
by: Qiu, Bo-Cheng, et al.
Published: (2026)