Cover Image

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Qizhe, Liu, Mengzhen, Li, Lichen, Lu, Ming, Zhang, Yuan, Pan, Junwen, She, Qi, Zhang, Shanghang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
by: Ma, Junpeng, et al.
Published: (2025)

ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
by: Zhang, Yuan, et al.
Published: (2025)

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
by: Pan, Junwen, et al.
Published: (2025)

AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
by: Zhang, Yuan, et al.
Published: (2025)

TimeSearch: Hierarchical Video Search with Spotlight and Reflection for Human-like Long Video Understanding
by: Pan, Junwen, et al.
Published: (2025)

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

MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning
by: Zhang, Qizhe, et al.
Published: (2023)

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
by: Cao, Jiajun, et al.
Published: (2025)

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

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

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
by: Cao, Jiajun, et al.
Published: (2025)

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

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
by: Liu, Jiaming, et al.
Published: (2022)

LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling
by: Zhang, Zhihan, et al.
Published: (2025)

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
by: Zhang, Evelyn, et al.
Published: (2025)

Towards Joint Quantization and Token Pruning of Vision-Language Models
by: Li, Xinqing, et al.
Published: (2026)

GridPrune: From "Where to Look" to "What to Select" in Visual Token Pruning for MLLMs
by: Duan, Yuxiang, et al.
Published: (2025)

UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
by: Bai, Chengyu, et al.
Published: (2025)

On the Faithfulness of Visual Thinking: Measurement and Enhancement
by: Liu, Zujing, et al.
Published: (2025)

Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction
by: Guo, Ziyao, et al.
Published: (2025)

MammothModa: Multi-Modal Large Language Model
by: She, Qi, et al.
Published: (2024)

Gradient-based Parameter Selection for Efficient Fine-Tuning
by: Zhang, Zhi, et al.
Published: (2023)

Rényi Entropy: A New Token Pruning Metric for Vision Transformers
by: Su, Wei-Yuan, et al.
Published: (2026)

Similarity-Aware Token Pruning: Your VLM but Faster
by: Jeddi, Ahmadreza, et al.
Published: (2025)

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

Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs
by: Tan, Kaizhen
Published: (2026)

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
by: Yang, Senqiao, et al.
Published: (2023)

ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance
by: Li, Yuming, et al.
Published: (2024)

One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
by: Fa, Zhan, et al.
Published: (2026)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
by: Liu, Jizhihui, et al.
Published: (2025)

Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation
by: Chen, Ruoyu, et al.
Published: (2025)

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs
by: Su, Yongyi, et al.
Published: (2025)

Context Tokens are Anchors: Understanding the Repetition Curse in dMLLMs from an Information Flow Perspective
by: Zhao, Qiyan, et al.
Published: (2026)

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

OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection
by: Lu, Ziji
Published: (2025)

Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs
by: Zhang, Song, et al.
Published: (2026)

PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers
by: Li, Haotang, et al.
Published: (2026)

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
by: Li, Yuming, et al.
Published: (2025)