Buchumschlag

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhu, Yingjie, Bai, Xuefeng, Chen, Kehai, Xiang, Yang, Pan, Youcheng, Hou, Yongshuai, Guan, Weili, Yu, Jun, Zhang, Min
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
von: Zhu, Yingjie, et al.
Veröffentlicht: (2024)

Evaluating and Steering Modality Preferences in Multimodal Large Language Model
von: Zhang, Yu, et al.
Veröffentlicht: (2025)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
von: Zhang, Hongbin, et al.
Veröffentlicht: (2026)

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
von: Zhang, Hongbin, et al.
Veröffentlicht: (2024)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
von: Zhang, Yu, et al.
Veröffentlicht: (2026)

Exploring the Translation Mechanism of Large Language Models
von: Zhang, Hongbin, et al.
Veröffentlicht: (2025)

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
von: Qu, Bingzheng, et al.
Veröffentlicht: (2026)

Beyond Rigid: Benchmarking Non-Rigid Video Editing
von: Qu, Bingzheng, et al.
Veröffentlicht: (2026)

Agentic Tool Use in Large Language Models
von: Hu, Jinchao, et al.
Veröffentlicht: (2026)

Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
von: Xu, Mufan, et al.
Veröffentlicht: (2026)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
von: Huang, Weiyang, et al.
Veröffentlicht: (2026)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
von: Wang, Yuchen, et al.
Veröffentlicht: (2025)

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
von: Zhang, Hongbin, et al.
Veröffentlicht: (2024)

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
von: Li, Zelin, et al.
Veröffentlicht: (2024)

Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
von: Tian, Xinyu, et al.
Veröffentlicht: (2025)

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent
von: Li, Xingzuo, et al.
Veröffentlicht: (2025)

Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
von: Tang, Yihong, et al.
Veröffentlicht: (2026)

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
von: Duan, Yifan, et al.
Veröffentlicht: (2025)

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

Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition
von: Ma, Jinlong, et al.
Veröffentlicht: (2026)

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling
von: Deng, Qiyuan, et al.
Veröffentlicht: (2025)

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
von: Zhang, Hongbin, et al.
Veröffentlicht: (2025)

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
von: Li, Jiaqi, et al.
Veröffentlicht: (2026)

Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
von: Chen, Andong, et al.
Veröffentlicht: (2024)

Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
von: An, Na Min, et al.
Veröffentlicht: (2025)

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
von: Chen, Andong, et al.
Veröffentlicht: (2024)

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
von: Atabuzzaman, Md., et al.
Veröffentlicht: (2025)

Investigating Spatial Attention Bias in Vision-Language Models
von: Chaudhary, Aryan, et al.
Veröffentlicht: (2025)

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
von: Sasse, Kuleen, et al.
Veröffentlicht: (2024)

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following
von: Li, Zhenyu, et al.
Veröffentlicht: (2025)

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
von: Zhang, Yu, et al.
Veröffentlicht: (2026)

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
von: Wei, Xuchen, et al.
Veröffentlicht: (2025)

Mitigating Multilingual Hallucination in Large Vision-Language Models
von: Qu, Xiaoye, et al.
Veröffentlicht: (2024)

YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models
von: Chen, Ting, et al.
Veröffentlicht: (2026)

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
von: Huang, Youcheng, et al.
Veröffentlicht: (2024)

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

Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
von: Zhang, Yu, et al.
Veröffentlicht: (2024)

A Survey on Human Preference Learning for Large Language Models
von: Jiang, Ruili, et al.
Veröffentlicht: (2024)

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
von: Qi, Jianing, et al.
Veröffentlicht: (2025)

Hierarchical Pre-Training of Vision Encoders with Large Language Models
von: Lee, Eugene, et al.
Veröffentlicht: (2026)