Cover Image

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Jiafei, Zhou, Fengwei, Qu, Jin, Li, Wenjin Jason, Wu, Tong, Xue, Gengjian, Zhao, Zhikang, Wei, Daomin, Lu, Yichao, Na, Bailin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores
by: Zhou, Fengwei, et al.
Published: (2025)

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking
by: Zhou, Sifan, et al.
Published: (2025)

EvoP: Robust LLM Inference via Evolutionary Pruning
by: Wu, Shangyu, et al.
Published: (2025)

EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models
by: Lu, Hongyu, et al.
Published: (2026)

EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
by: Xu, Tianyi, et al.
Published: (2026)

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
by: Sieberling, Oliver, et al.
Published: (2024)

EvoLen: Evolution-Guided Tokenization for DNA Language Model
by: Huang, Nan, et al.
Published: (2026)

ResiComp: Loss-Resilient Image Compression via Dual-Functional Masked Visual Token Modeling
by: Wang, Sixian, et al.
Published: (2025)

EvoMU: Evolutionary Machine Unlearning
by: Batorski, Pawel, et al.
Published: (2026)

Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
by: Peng, Tianfan, et al.
Published: (2025)

LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
by: Lu, Hongyu, et al.
Published: (2026)

EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
by: Chen, Yuhao, et al.
Published: (2026)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
by: Tan, Xudong, et al.
Published: (2025)

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
by: Li, Yan, et al.
Published: (2026)

TokenFLEX: Unified VLM Training for Flexible Visual Tokens Inference
by: Hu, Junshan, et al.
Published: (2025)

Lycopene intake and the risk of erectile dysfunction in US adults: The National Health and Nutrition Examination Survey 2001–2004
by: Jiafei Jin
Published: (2024)

EvoIF: Evolutionary Profiles for Protein Fitness Prediction
by: Jiao, Xiaoran, et al.
Published: (2026)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
by: Li, Na, et al.
Published: (2025)

EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation
by: Huang, Beichen, et al.
Published: (2023)

EvoMAS: Evolutionary Generation of Multi-Agent Systems
by: Hu, Yuntong, et al.
Published: (2026)

EvoVLMA: Evolutionary Vision-Language Model Adaptation
by: Ding, Kun, et al.
Published: (2025)

Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
by: Mao, Yu, et al.
Published: (2025)

QG-VTC: Question-Guided Visual Token Compression in MLLMs for Efficient VQA
by: Li, Shuai, et al.
Published: (2025)

QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression
by: Li, Zhongyang, et al.
Published: (2026)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
by: Gao, Juntao, et al.
Published: (2025)

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification
by: Jin, Xin, et al.
Published: (2026)

Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs
by: Lee, Jaehoon, et al.
Published: (2026)

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
by: Luo, Lvzhou, et al.
Published: (2025)

Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information
by: Chen, Yi, et al.
Published: (2024)

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
by: Feng, Kehua, et al.
Published: (2025)

EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning
by: Du, He, et al.
Published: (2025)

Expansion of Green's function and regularity of Robin's function for elliptic operators in divergence form
by: Cao, Daomin, et al.
Published: (2024)

Co-rotating nearly parallel helical vortices with small cross-section in 3D incompressible Euler equations
by: Cao, Daomin, et al.
Published: (2025)

On Arnold-type stability theorems for the Euler equation on a sphere
by: Cao, Daomin, et al.
Published: (2024)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
by: Zhu, Jiaying, et al.
Published: (2025)

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
by: Yao, Linli, et al.
Published: (2024)

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
by: Zhang, Hanrong, et al.
Published: (2026)

Modality Reliability Guided Multimodal Recommendation
by: Dong, Xue, et al.
Published: (2025)

SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization
by: Tan, Zhentao, et al.
Published: (2024)

Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning
by: Chen, Shiming, et al.
Published: (2024)