Cover Image

VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhuang, Xianwei, Zhu, Zhihong, Xie, Yuxin, Liang, Liming, Zou, Yuexian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model
by: Zhuang, Xianwei, et al.
Published: (2025)

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning
by: Zhuang, Xianwei, et al.
Published: (2025)

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation
by: Tang, Lexiang, et al.
Published: (2025)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
by: Zhang, Yuan, et al.
Published: (2024)

Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
by: Liang, Xiaoyu, et al.
Published: (2024)

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
by: Gu, Jihao, et al.
Published: (2024)

Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive Optimization
by: Deng, Haolin, et al.
Published: (2026)

Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation
by: Zhu, Xingyu, et al.
Published: (2026)

G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory
by: Li, Hongxiang, et al.
Published: (2023)

Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination
by: Yang, Dingchen, et al.
Published: (2024)

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
by: Li, Zhaoxu, et al.
Published: (2025)

FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression
by: Zhu, Yuke, et al.
Published: (2024)

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
by: Chang, Shuning, et al.
Published: (2024)

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
by: Yu, Xinlei, et al.
Published: (2025)

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

Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy
by: Sun, Yinan, et al.
Published: (2025)

Exploiting Auxiliary Caption for Video Grounding
by: Li, Hongxiang, et al.
Published: (2023)

Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving
by: Ma, Yunsheng, et al.
Published: (2024)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
by: Zhang, Kejia, et al.
Published: (2025)

TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
by: Zeng, Sen, et al.
Published: (2026)

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
by: Xie, Yutong, et al.
Published: (2026)

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification
by: Zhang, Jiacheng, et al.
Published: (2026)

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
by: Huang, Zhaohong, et al.
Published: (2026)

Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
by: Tong, Enwei, et al.
Published: (2026)

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
by: Yang, Chengxu, et al.
Published: (2026)

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

Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
by: Li, Yuanshuai, et al.
Published: (2025)

Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
by: Zhou, Jinxing, et al.
Published: (2025)

TokenPacker: Efficient Visual Projector for Multimodal LLM
by: Li, Wentong, et al.
Published: (2024)

Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens
by: Ma, Fan, et al.
Published: (2023)

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation
by: Jiang, Yubo, et al.
Published: (2026)

CAR: Controllable Autoregressive Modeling for Visual Generation
by: Yao, Ziyu, et al.
Published: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
by: Li, Jinlin, et al.
Published: (2025)

Principles of Visual Tokens for Efficient Video Understanding
by: Hao, Xinyue, et al.
Published: (2024)

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
by: Guo, Yiwei, et al.
Published: (2026)

Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
by: Yang, Nan, et al.
Published: (2025)

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
by: Zhu, Qihui, et al.
Published: (2026)

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs
by: Li, Qi, et al.
Published: (2026)