Copertina

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Ziqiang, Liu, Rujie, Yu, Shanshan, Munakata, Satoshi, Shirahata, Koichi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SchröMind: Mitigating Hallucinations in Multimodal Large Language Models via Solving the Schrödinger Bridge Problem
di: Shi, Ziqiang, et al.
Pubblicazione: (2026)

Generative Modelling with High-Order Langevin Dynamics
di: Shi, Ziqiang, et al.
Pubblicazione: (2024)

Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
di: Yang, Tiancheng, et al.
Pubblicazione: (2025)

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
di: Deng, Haolin, et al.
Pubblicazione: (2026)

Do Vision Encoders Truly Explain Object Hallucination?: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
di: Oh, Hongseok, et al.
Pubblicazione: (2025)

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
di: Zhou, Guanyu, et al.
Pubblicazione: (2024)

MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation
di: Lu, Shuaiye, et al.
Pubblicazione: (2025)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
di: Chang, Kai-Po, et al.
Pubblicazione: (2025)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
di: Zhang, Yu, et al.
Pubblicazione: (2026)

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
di: Cai, Jianfeng, et al.
Pubblicazione: (2025)

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

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
di: Xiao, Wenyi, et al.
Pubblicazione: (2024)

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
di: Yin, Jianghao, et al.
Pubblicazione: (2026)

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning
di: Bai, Tianyi, et al.
Pubblicazione: (2025)

Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment
di: Sarkar, Pritam, et al.
Pubblicazione: (2024)

Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data
di: Kim, Shiwon, et al.
Pubblicazione: (2026)

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

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
di: Zhao, Haozhe, et al.
Pubblicazione: (2024)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
di: Ding, Wei, et al.
Pubblicazione: (2026)

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

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

Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
di: Tu, Chongjun, et al.
Pubblicazione: (2025)

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
di: Wang, Shan, et al.
Pubblicazione: (2025)

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

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

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
di: Ma, Ji, et al.
Pubblicazione: (2026)

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

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
di: Zhang, Jiacheng, et al.
Pubblicazione: (2026)

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models
di: Xing, Shangyu, et al.
Pubblicazione: (2024)

Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding
di: Kim, Namho, et al.
Pubblicazione: (2025)

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

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

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM
di: Zhong, Li'an, et al.
Pubblicazione: (2026)

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

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

Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration
di: Zhu, Younan, et al.
Pubblicazione: (2025)

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

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

ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval
di: Nguyen, Tien-Huy, et al.
Pubblicazione: (2026)

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