:: Library Catalog

Omslagsbild

Sparad:

Bibliografiska uppgifter
Huvudupphovsmän:	Wang, Jingyi, Li, Fei, Liu, Rujie
Materialtyp:	Preprint
Publicerad:	2026
Ämnen:	Computer Vision and Pattern Recognition
Länkar:	https://arxiv.org/abs/2602.09521
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!

Liknande verk

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing
av: Huang, Yanbin, et al.
Publicerad: (2026)

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

Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models
av: Khan, Behraj, et al.
Publicerad: (2025)

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

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning
av: Li, Yanshu, et al.
Publicerad: (2025)

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
av: He, Jinghan, et al.
Publicerad: (2024)

Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs
av: Liu, Yuxin, et al.
Publicerad: (2026)

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

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

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
av: Shi, Ziqiang, et al.
Publicerad: (2026)

Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs
av: Liu, Shi, et al.
Publicerad: (2024)

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

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs
av: Lyu, Guangtao, et al.
Publicerad: (2026)

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

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

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

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

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

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
av: Ge, Xuanyu, et al.
Publicerad: (2026)

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection
av: Jiang, Lei, et al.
Publicerad: (2025)

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

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

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

Density-aware global-local attention network for point cloud segmentation
av: Li, Chade, et al.
Publicerad: (2024)

RTAT: A Robust Two-stage Association Tracker for Multi-Object Tracking
av: Guo, Song, et al.
Publicerad: (2024)

CoMemo: LVLMs Need Image Context with Image Memory
av: Liu, Shi, et al.
Publicerad: (2025)

Neuromorphic visual attention for Sign-language recognition on SpiNNaker
av: Liskova, Sarka, et al.
Publicerad: (2026)

Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation
av: Li, Wenhao, et al.
Publicerad: (2025)

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

Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
av: Wang, Chaoyang, et al.
Publicerad: (2025)

Self-Prophetic Decoding to Unlock Visual Search in LVLMs
av: He, Zhendong, et al.
Publicerad: (2026)

Attention to detail: inter-resolution knowledge distillation
av: del Amor, Rocío, et al.
Publicerad: (2024)

Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction
av: Liu, Yao, et al.
Publicerad: (2023)

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

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
av: Pan, Zihao, et al.
Publicerad: (2025)

Visual hallucination detection in large vision-language models via evidential conflict
av: Huang, Tao, et al.
Publicerad: (2025)

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

Getting to the Point: Pointing Improves LVLMs at Counting
av: Alghisi, Simone, et al.
Publicerad: (2026)

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

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