Copertina

Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Boxu, Zheng, Ziwei, Yang, Le, Geng, Zeyu, Zhao, Zhengyu, Lin, Chenhao, Shen, Chao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Concept Unlearning by Modeling Key Steps of Diffusion Process
di: Zhang, Chaoshuo, et al.
Pubblicazione: (2025)

Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering
di: Lyu, Guangtao, et al.
Pubblicazione: (2026)

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
di: Jiang, Zhangqi, et al.
Pubblicazione: (2024)

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

Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
di: Tian, Qiwei, et al.
Pubblicazione: (2023)

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
di: Ren, Yuchen, et al.
Pubblicazione: (2025)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
di: Li, Qiming, et al.
Pubblicazione: (2025)

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

One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs
di: Shi, Youxu, et al.
Pubblicazione: (2026)

Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction
di: Zhang, Yuanhong, et al.
Pubblicazione: (2026)

Generalizable Targeted Data Poisoning against Varying Physical Objects
di: Chen, Zhizhen, et al.
Pubblicazione: (2024)

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

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
di: Zheng, Junhao, et al.
Pubblicazione: (2024)

Adversarial Example Soups: Improving Transferability and Stealthiness for Free
di: Yang, Bo, et al.
Pubblicazione: (2024)

Adversarial Video Promotion Against Text-to-Video Retrieval
di: Tian, Qiwei, et al.
Pubblicazione: (2025)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
di: Jiang, Nick, et al.
Pubblicazione: (2024)

Use as Many Surrogates as You Want: Selective Ensemble Attack to Unleash Transferability without Sacrificing Resource Efficiency
di: Yang, Bo, et al.
Pubblicazione: (2025)

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

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
di: He, Zhentao, et al.
Pubblicazione: (2025)

Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
di: Zheng, Junhao, et al.
Pubblicazione: (2025)

D3: Training-Free AI-Generated Video Detection Using Second-Order Features
di: Zheng, Chende, et al.
Pubblicazione: (2025)

Mitigating Object Hallucination via Robust Local Perception Search
di: Gao, Zixian, et al.
Pubblicazione: (2025)

Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
di: Lovenia, Holy, et al.
Pubblicazione: (2023)

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

Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
di: Jia, Kaidi, et al.
Pubblicazione: (2026)

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

A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication
di: Deng, Jingyi, et al.
Pubblicazione: (2024)

Reducing Hallucinations in Vision-Language Models via Latent Space Steering
di: Liu, Sheng, et al.
Pubblicazione: (2024)

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

Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models
di: Song, Jiale, et al.
Pubblicazione: (2026)

Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
di: Zou, Zhengtao, et al.
Pubblicazione: (2025)

Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering
di: Jana, Soumyadeep, et al.
Pubblicazione: (2026)

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

VORD: Visual Ordinal Calibration for Mitigating Object Hallucinations in Large Vision-Language Models
di: Neo, Dexter, et al.
Pubblicazione: (2024)

MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
di: Wang, Chao, et al.
Pubblicazione: (2025)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
di: Fazli, Mehrdad, et al.
Pubblicazione: (2025)

Mitigating Object Hallucinations via Sentence-Level Early Intervention
di: Peng, Shangpin, et al.
Pubblicazione: (2025)

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