Imagen de Portada

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qi, Zheng, Shang, Chao, Spiliopoulou, Evangelia, Pappas, Nikolaos
Formato:	Preprint
Publicado:	2025
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

When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
por: Cao, Jinjin, et al.
Publicado: (2025)

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
por: He, Lehan, et al.
Publicado: (2024)

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

Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detection
por: Mathew, Athul M., et al.
Publicado: (2025)

InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
por: Yang, Zhongyu, et al.
Publicado: (2025)

Ocular Authentication: Fusion of Gaze and Periocular Modalities
por: Lohr, Dillon, et al.
Publicado: (2025)

Mitigating Diffusion Model Hallucinations with Dynamic Guidance
por: Triaridis, Kostas, et al.
Publicado: (2025)

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens
por: Zheng, Haohan, et al.
Publicado: (2025)

Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
por: Wang, Hengfei, et al.
Publicado: (2026)

GazeShift: Unsupervised Gaze Estimation and Dataset for VR
por: Shapira, Gil, et al.
Publicado: (2026)

Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation
por: Zeng, Guanzhong, et al.
Publicado: (2024)

MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
por: Bae, Kyungho, et al.
Publicado: (2025)

VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Models
por: Wang, Chenyu, et al.
Publicado: (2026)

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
por: Dong, Xin, et al.
Publicado: (2025)

Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
por: Pani, Anupam, et al.
Publicado: (2025)

GazeVLM: A Vision-Language Model for Multi-Task Gaze Understanding
por: Mathew, Athul M., et al.
Publicado: (2025)

Integrating MedCLIP and Cross-Modal Fusion for Automatic Radiology Report Generation
por: Han, Qianhao, et al.
Publicado: (2024)

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

BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
por: Singha, Mainak, et al.
Publicado: (2026)

MMMamba: A Versatile Cross-Modal In Context Fusion Framework for Pan-Sharpening and Zero-Shot Image Enhancement
por: Wang, Yingying, et al.
Publicado: (2025)

CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
por: Zheng, Jinzhi, et al.
Publicado: (2024)

Cross-Modal Guidance for Fast Diffusion-Based Computed Tomography
por: Efimov, Timofey, et al.
Publicado: (2026)

CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization
por: Kritikos, Antonios, et al.
Publicado: (2026)

A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
por: Yang, Hao-Ran, et al.
Publicado: (2025)

Cross-Dataset Gaze Estimation by Evidential Inter-intra Fusion
por: Wang, Shijing, et al.
Publicado: (2024)

Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation
por: Chung, Tien-Dat, et al.
Publicado: (2025)

Multi-Modal Gaze Following in Conversational Scenarios
por: Hou, Yuqi, et al.
Publicado: (2023)

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

CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learning
por: Qi, Chao, et al.
Publicado: (2025)

Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification
por: Yang, Xi, et al.
Publicado: (2024)

Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
por: Lin, Chenchen, et al.
Publicado: (2026)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
por: Lu, Yifan, et al.
Publicado: (2025)

Enriching Knowledge Distillation with Cross-Modal Teacher Fusion
por: Mansourian, Amir M., et al.
Publicado: (2025)

GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection
por: Wang, Yu, et al.
Publicado: (2025)

Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
por: Jo, Yujin, et al.
Publicado: (2026)

Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs
por: Chen, Qinyu, et al.
Publicado: (2025)

Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate
por: Lin, Zheng, et al.
Publicado: (2024)

Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance
por: Li, Jun, et al.
Publicado: (2024)

MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification
por: Zhao, Yujian, et al.
Publicado: (2025)

CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild
por: Cătrună, Andy, et al.
Publicado: (2024)