Image de couverture de livre

ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Jianjiang, li, Yanshu, Huang, Ziyan
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation
par: Yang, Jianjiang, et autres
Publié: (2025)

TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration
par: Li, Yanshu, et autres
Publié: (2025)

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
par: Guo, Pinxue, et autres
Publié: (2025)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
par: Liu, Chengzhi, et autres
Publié: (2025)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
par: Zhang, Yu, et autres
Publié: (2026)

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
par: Wang, Shan, et autres
Publié: (2025)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
par: Xu, Haolei, et autres
Publié: (2026)

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations
par: Li, Yanshu
Publié: (2025)

See, Think, Learn: A Self-Taught Multimodal Reasoner
par: Sharma, Sourabh, et autres
Publié: (2025)

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning
par: Li, Yanshu, et autres
Publié: (2025)

Look Twice: Training-Free Evidence Highlighting in Multimodal Large Language Models
par: Morini, Marco, et autres
Publié: (2026)

Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
par: Tang, Fei, et autres
Publié: (2025)

Analyzing and Mitigating Object Hallucination: A Training Bias Perspective
par: Li, Yifan, et autres
Publié: (2025)

Watch Closely: Mitigating Object Hallucinations in Large Vision-Language Models with Disentangled Decoding
par: Ma, Ruiqi, et autres
Publié: (2025)

Mitigating Object Hallucination via Robust Local Perception Search
par: Gao, Zixian, et autres
Publié: (2025)

Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
par: Liu, Yi, et autres
Publié: (2026)

Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision
par: Lee, Seongyun, et autres
Publié: (2023)

Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
par: Yue, Zihao, et autres
Publié: (2024)

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
par: Wu, Jiulong, et autres
Publié: (2025)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
par: Fu, Yuhan, et autres
Publié: (2024)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
par: Zhu, Wenxin, et autres
Publié: (2025)

Mitigating Object Hallucination via Concentric Causal Attention
par: Xing, Yun, et autres
Publié: (2024)

Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data
par: Whitehead, Spencer, et autres
Publié: (2024)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
par: Chang, Kai-Po, et autres
Publié: (2025)

See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
par: Dai, Ziyun, et autres
Publié: (2025)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
par: Wu, Juncheng, et autres
Publié: (2026)

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
par: Deng, Haolin, et autres
Publié: (2026)

Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models
par: Zhong, Weihong, et autres
Publié: (2024)

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images
par: You, Liangliang, et autres
Publié: (2025)

Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
par: Compagnoni, Alberto, et autres
Publié: (2025)

Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback
par: Yuan, Jiakang, et autres
Publié: (2025)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
par: Kim, Junho, et autres
Publié: (2024)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
par: Li, Shuo, et autres
Publié: (2025)

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
par: Li, Yanshu, et autres
Publié: (2025)

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models
par: Xing, Shangyu, et autres
Publié: (2024)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
par: Lu, Yifan, et autres
Publié: (2025)

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
par: Deng, Ailin, et autres
Publié: (2024)

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
par: Zou, Xin, et autres
Publié: (2024)

Mitigating Hallucinations in Multimodal Spatial Relations through Constraint-Aware Prompting
par: Wu, Jiarui, et autres
Publié: (2025)

Do Vision Encoders Truly Explain Object Hallucination?: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
par: Oh, Hongseok, et autres
Publié: (2025)