Imagen de Portada

Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Yebo, Jin, Han, Guo, Zhijiang, Li, Li
Formato:	Preprint
Publicado:	2026
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

ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
por: Wang, Yujun, et al.
Publicado: (2025)

Energy-Guided Decoding for Object Hallucination Mitigation
por: Liu, Xixi, et al.
Publicado: (2025)

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
por: Jia, Sihang, et al.
Publicado: (2026)

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
por: Wang, Chenxi, et al.
Publicado: (2024)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
por: Yang, Chengxu, et al.
Publicado: (2026)

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

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
por: Huo, Fushuo, et al.
Publicado: (2024)

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
por: Tang, Lexiang, et al.
Publicado: (2025)

Regional Attention for Shadow Removal
por: Liu, Hengxing, et al.
Publicado: (2024)

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
por: Tang, Feilong, et al.
Publicado: (2025)

Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models
por: Liu, Zijian, et al.
Publicado: (2026)

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention
por: Zhao, Jianfei, et al.
Publicado: (2025)

Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
por: Chen, Xinlong, et al.
Publicado: (2025)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
por: Kolli, Govinda, et al.
Publicado: (2026)

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
por: Liu, Shuliang, et al.
Publicado: (2026)

Mitigating Object Hallucination via Concentric Causal Attention
por: Xing, Yun, et al.
Publicado: (2024)

CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
por: Li, Qiming, et al.
Publicado: (2026)

D2-Mamba: Dual-Scale Fusion and Dual-Path Scanning with SSMs for Shadow Removal
por: Li, Linhao, et al.
Publicado: (2025)

Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
por: Li, Jinlin, et al.
Publicado: (2025)

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
por: Tong, Bingkui, et al.
Publicado: (2025)

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

Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding
por: Cho, Yeongjae, et al.
Publicado: (2025)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
por: Li, Bin, et al.
Publicado: (2025)

ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer
por: Hu, Jin, et al.
Publicado: (2024)

VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
por: Wang, Zihu, et al.
Publicado: (2025)

Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
por: Liang, Xiao, et al.
Publicado: (2025)

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
por: Wang, Tianbo, et al.
Publicado: (2026)

SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation
por: Shukla, Tripti, et al.
Publicado: (2026)

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
por: Chen, Beitao, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
por: Min, Kyungmin, et al.
Publicado: (2024)

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

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

YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models
por: Chen, Ting, et al.
Publicado: (2026)

Mitigating Hallucinations in Diffusion Models through Adaptive Attention Modulation
por: Oorloff, Trevine, et al.
Publicado: (2025)

AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors
por: Zhang, Junyang, et al.
Publicado: (2025)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
por: Ma, Ruiqi, et al.
Publicado: (2025)

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
por: Li, Qiming, et al.
Publicado: (2025)

MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval
por: Cai, Weitong, et al.
Publicado: (2024)

See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
por: Dai, Ziyun, et al.
Publicado: (2025)