Buchumschlag

Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Xing, Wenbin, Zha, Quanxing, Zu, Lizheng, Li, Mengran, Li, Ming, Yan, Junchi
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
von: You, Liangliang, et al.
Veröffentlicht: (2025)

Causal Decoding for Hallucination-Resistant Multimodal Large Language Models
von: Tan, Shiwei, et al.
Veröffentlicht: (2026)

Mitigating Hallucinations in Video Large Language Models via Spatiotemporal-Semantic Contrastive Decoding
von: Gao, Yuansheng, et al.
Veröffentlicht: (2026)

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
von: Park, Yeji, et al.
Veröffentlicht: (2024)

SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
von: Xia, Yuxuan, et al.
Veröffentlicht: (2026)

Model Composition for Multimodal Large Language Models
von: Chen, Chi, et al.
Veröffentlicht: (2024)

Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models
von: Sun, Li, et al.
Veröffentlicht: (2024)

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

Woodpecker: Hallucination Correction for Multimodal Large Language Models
von: Yin, Shukang, et al.
Veröffentlicht: (2023)

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
von: Jiang, Chaoya, et al.
Veröffentlicht: (2023)

ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
von: Rawte, Vipula, et al.
Veröffentlicht: (2024)

Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition
von: Li, Meng-zhu, et al.
Veröffentlicht: (2025)

OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description
von: Xu, Quanxing, et al.
Veröffentlicht: (2025)

Speculative Decoding Reimagined for Multimodal Large Language Models
von: Lin, Luxi, et al.
Veröffentlicht: (2025)

Robust Multimodal Large Language Models Against Modality Conflict
von: Zhang, Zongmeng, et al.
Veröffentlicht: (2025)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
von: Fu, Yuhan, et al.
Veröffentlicht: (2024)

MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models
von: Yang, Garry, et al.
Veröffentlicht: (2025)

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
von: Zhong, Weihong, et al.
Veröffentlicht: (2024)

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

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
von: Wu, Kai, et al.
Veröffentlicht: (2024)

VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
von: Li, Chaoyu, et al.
Veröffentlicht: (2024)

VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models
von: Zhang, Zefan, et al.
Veröffentlicht: (2026)

TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning
von: Liu, Daixian, et al.
Veröffentlicht: (2026)

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
von: Chen, Xinrong, et al.
Veröffentlicht: (2026)

White-box Multimodal Jailbreaks Against Large Vision-Language Models
von: Wang, Ruofan, et al.
Veröffentlicht: (2024)

CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
von: Dang, Yunkai, et al.
Veröffentlicht: (2026)

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

Delve into Visual Contrastive Decoding for Hallucination Mitigation of Large Vision-Language Models
von: Lee, Yi-Lun, et al.
Veröffentlicht: (2024)

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

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
von: Gong, Ziyang, et al.
Veröffentlicht: (2025)

Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
von: Wang, Xintong, et al.
Veröffentlicht: (2024)

Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
von: Manevich, Avshalom, et al.
Veröffentlicht: (2024)

SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding
von: Wu, Chang-Hsun, et al.
Veröffentlicht: (2025)

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
von: Zhang, Chengsheng, et al.
Veröffentlicht: (2026)

CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
von: Li, Jingyao, et al.
Veröffentlicht: (2025)

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
von: Lee, Jihoon, et al.
Veröffentlicht: (2025)

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
von: Xing, Shuo, et al.
Veröffentlicht: (2025)

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
von: Zhang, Ruohong, et al.
Veröffentlicht: (2024)

Decoding Neighborhood Environments with Large Language Models
von: Cart, Andrew, et al.
Veröffentlicht: (2025)

CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis
von: Liang, Kaidi, et al.
Veröffentlicht: (2025)