Cover Image

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Evelyn, Yu, Fufu, Wu, Aoqi, Wen, Zichen, Yan, Ke, Ding, Shouhong, Qi, Biqing, Zhang, Linfeng
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

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
by: Wen, Zichen, et al.
Published: (2025)

MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning
by: Ma, Hongxu, et al.
Published: (2025)

VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
by: Wu, Zhenkai, et al.
Published: (2025)

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs
by: Tan, Yifan, et al.
Published: (2026)

LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
by: Takezoe, Rinyoichi, et al.
Published: (2026)

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
by: Baek, Changwoo, et al.
Published: (2026)

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
by: Fang, Zhengyao, et al.
Published: (2026)

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
by: Ma, Shilin, et al.
Published: (2026)

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

IPCV: Information-Preserving Compression for MLLM Visual Encoders
by: Chen, Yuan, et al.
Published: (2025)

MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs
by: Li, Jiameng, et al.
Published: (2026)

Attention Debiasing for Token Pruning in Vision Language Models
by: Zhao, Kai, et al.
Published: (2025)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
by: Zhang, Evelyn, et al.
Published: (2024)

BiasPruner: Debiased Continual Learning for Medical Image Classification
by: Bayasi, Nourhan, et al.
Published: (2024)

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
by: Sun, Fengyuan, et al.
Published: (2025)

RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration
by: Wang, Boyao, et al.
Published: (2024)

VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
by: Han, Hui, et al.
Published: (2026)

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
by: Liu, Shengyuan, et al.
Published: (2026)

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
by: Zhang, Qizhe, et al.
Published: (2025)

Rethinking Clothes Changing Person ReID: Conflicts, Synthesis, and Optimization
by: Li, Junjie, et al.
Published: (2024)

ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
by: Yu, An, et al.
Published: (2026)

Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
by: Ding, Guanhua, et al.
Published: (2024)

Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models
by: Liu, Xuyang, et al.
Published: (2025)

SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering
by: Li, Wenli, et al.
Published: (2026)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
by: Wen, Zichen, et al.
Published: (2025)

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
by: Wu, Yuanchen, et al.
Published: (2025)

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
by: Wu, Yuanchen, et al.
Published: (2025)

SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
by: Zhao, Linglan, et al.
Published: (2024)

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
by: Han, Yuhang, et al.
Published: (2024)

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
by: Li, Duo, et al.
Published: (2025)

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
by: Alvar, Saeed Ranjbar, et al.
Published: (2025)

LaRE$^2$: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection
by: Luo, Yunpeng, et al.
Published: (2024)

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
by: Huang, Qihan, et al.
Published: (2025)

VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
by: Jiang, Pengfei, et al.
Published: (2025)

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
by: Chen, Sichen, et al.
Published: (2024)

LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
by: Castells, Thibault, et al.
Published: (2024)

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

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
by: Wu, Yuanchen, et al.
Published: (2025)

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
by: Xiong, Minhao, et al.
Published: (2025)

AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
by: Qi, Haozhe, et al.
Published: (2026)