Imagen de Portada

ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan, Bei, Min, Yuecong, Zhang, Jie, Shan, Shiguang, Chen, Xilin
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

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
por: Yang, Junqi, et al.
Publicado: (2026)

A Survey of Multimodal Hallucination Evaluation and Detection
por: Chen, Zhiyuan, et al.
Publicado: (2025)

SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs
por: Yan, Bei, et al.
Publicado: (2025)

Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models
por: Yan, Bei, et al.
Publicado: (2024)

T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models
por: Li, Changzhen, et al.
Publicado: (2025)

VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task
por: Long, Xingming, et al.
Publicado: (2025)

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
por: Yan, Bei, et al.
Publicado: (2024)

Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
por: Long, Xingming, et al.
Publicado: (2024)

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
por: Wang, Zhongqi, et al.
Publicado: (2025)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
por: Wang, Zhongqi, et al.
Publicado: (2024)

Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models
por: Wang, Zhongqi, et al.
Publicado: (2025)

FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers
por: Yuan, Zheng, et al.
Publicado: (2024)

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
por: Long, Xingming, et al.
Publicado: (2024)

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
por: Zhang, Jie, et al.
Publicado: (2024)

V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
por: Nie, Sen, et al.
Publicado: (2025)

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
por: Cao, Xiangkui, et al.
Publicado: (2026)

Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement
por: Yuan, Zheng, et al.
Publicado: (2024)

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

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
por: Wang, Tianyue, et al.
Publicado: (2025)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
por: Zhang, Jie, et al.
Publicado: (2025)

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
por: Nie, Sen, et al.
Publicado: (2026)

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

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models
por: Zhang, Jie, et al.
Publicado: (2025)

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
por: Xu, Yifeng, et al.
Publicado: (2024)

Dual Attention Guided Defense Against Malicious Edits
por: Zhang, Jie, et al.
Publicado: (2025)

Towards Transferable Defense Against Malicious Image Edits
por: Zhang, Jie, et al.
Publicado: (2025)

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
por: Nie, Sen, et al.
Publicado: (2026)

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

Generalized Face Liveness Detection via De-fake Face Generator
por: Long, Xingming, et al.
Publicado: (2024)

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

Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading
por: Luo, Songtao, et al.
Publicado: (2023)

Component-Based Out-of-Distribution Detection
por: Liu, Wenrui, et al.
Publicado: (2026)

EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
por: Cai, Yufei, et al.
Publicado: (2025)

Task-adaptive Q-Face
por: Sun, Haomiao, et al.
Publicado: (2024)

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
por: Li, Yinqi, et al.
Publicado: (2025)

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
por: Dastmalchi, Hamidreza, et al.
Publicado: (2026)

Adaptive Perturbation for Adversarial Attack
por: Yuan, Zheng, et al.
Publicado: (2021)

Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
por: Dong, Shuai, et al.
Publicado: (2025)

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
por: Li, Yinqi, et al.
Publicado: (2025)

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
por: Cheng, Ruoxi, et al.
Publicado: (2026)