Cover Image

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Jinghan, Zhu, Kuan, Guo, Haiyun, Fang, Junfeng, Hua, Zhenglin, Jia, Yuheng, Tang, Ming, Chua, Tat-Seng, Wang, Jinqiao
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
by: Hua, Zhenglin, et al.
Published: (2025)

Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
by: He, Jinghan, et al.
Published: (2026)

MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
by: Guo, Haiyun, et al.
Published: (2025)

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
by: He, Jinghan, et al.
Published: (2024)

Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion
by: Zhou, Zhenglin, et al.
Published: (2025)

UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
by: Guo, Hongyu, et al.
Published: (2025)

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

Are Reasoning Models More Prone to Hallucination?
by: Yao, Zijun, et al.
Published: (2025)

ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval
by: Yang, Tianyu, et al.
Published: (2026)

FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition
by: An, Hongyan, et al.
Published: (2025)

AUHead: Realistic Emotional Talking Head Generation via Action Units Control
by: Lyu, Jiayi, et al.
Published: (2026)

ITS3D: Inference-Time Scaling for Text-Guided 3D Diffusion Models
by: Zhou, Zhenglin, et al.
Published: (2025)

Compose Your Aesthetics: Empowering Text-to-Image Models with the Principles of Art
by: Jin, Zhe, et al.
Published: (2025)

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
by: Zhou, Zhenglin, et al.
Published: (2025)

When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
by: Khayatan, Pegah, et al.
Published: (2026)

AAformer: Auto-Aligned Transformer for Person Re-Identification
by: Zhu, Kuan, et al.
Published: (2021)

Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval
by: Fang, Xiang, et al.
Published: (2026)

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
by: Zhao, Zhiyuan, et al.
Published: (2023)

Monocular Lane Detection Based on Deep Learning: A Survey
by: He, Xin, et al.
Published: (2024)

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
by: Fang, Hao, et al.
Published: (2025)

Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
by: Fei, Hao, et al.
Published: (2024)

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
by: Qin, Zhenxin, et al.
Published: (2026)

Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs
by: Fei, Hao, et al.
Published: (2023)

Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning
by: Wu, Shengqiong, et al.
Published: (2024)

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
by: Zhang, Xiaofeng, et al.
Published: (2024)

AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
by: Zhou, Zhenglin, et al.
Published: (2025)

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding
by: Yuan, Fan, et al.
Published: (2024)

Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
by: Zheng, Ge, et al.
Published: (2025)

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
by: Huang, Youcheng, et al.
Published: (2024)

Universal Scene Graph Generation
by: Wu, Shengqiong, et al.
Published: (2025)

Rethinking Representativeness and Diversity in Dynamic Data Selection
by: Zhou, Yuzhe, et al.
Published: (2026)

Referring Expression Instance Retrieval and A Strong End-to-End Baseline
by: Hao, Xiangzhao, et al.
Published: (2025)

Understanding Long Videos via LLM-Powered Entity Relation Graphs
by: Chu, Meng, et al.
Published: (2025)

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
by: Chen, Yangneng, et al.
Published: (2026)

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
by: Cui, Chenhang, et al.
Published: (2024)

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
by: Manevich, Avshalom, et al.
Published: (2024)

DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
by: Lu, Jinda, et al.
Published: (2025)

XNLP: An Interactive Demonstration System for Universal Structured NLP
by: Fei, Hao, et al.
Published: (2023)

PLUME: Latent Reasoning Based Universal Multimodal Embedding
by: He, Chenwei, et al.
Published: (2026)

CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
by: Ouali, Yassine, et al.
Published: (2024)