Cover Image

Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Zhaoqi, Zhang, Yingying, Li, Jian, Guo, Jianwei, Zhu, Qiannan, Huang, Hua
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Information Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework
by: Zafari, Ali, et al.
Published: (2025)

Adaptive Rate Control for Deep Video Compression with Rate-Distortion Prediction
by: Gu, Bowen, et al.
Published: (2024)

Histogram Driven Amplitude Embedding for Qubit Efficient Quantum Image Compression
by: Tomar, Sahil, et al.
Published: (2025)

Leveraging Perceptual Scores for Dataset Pruning in Computer Vision Tasks
by: Singh, Raghavendra
Published: (2024)

Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
by: Shen, Ruiqi, et al.
Published: (2025)

DeCompress: Denoising via Neural Compression
by: Zafari, Ali, et al.
Published: (2025)

VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
by: Gondkar, Aryan, et al.
Published: (2026)

Communication-Efficient Collaborative Perception via Information Filling with Codebook
by: Hu, Yue, et al.
Published: (2024)

Adaptive Transform Coding for Semantic Compression
by: Enttsel, Andriy, et al.
Published: (2026)

Challenges and Solutions in Selecting Optimal Lossless Data Compression Algorithms
by: Rahman, Md. Atiqur, et al.
Published: (2025)

Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
by: Zhao, Mengyu, et al.
Published: (2024)

Spatial Channel State Information Prediction with Generative AI: Towards Holographic Communication and Digital Radio Twin
by: Zhang, Lihao, et al.
Published: (2024)

Efficient Semantic Communication Through Transformer-Aided Compression
by: Mortaheb, Matin, et al.
Published: (2024)

Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization
by: Bach, Duong
Published: (2025)

Information Entropy-Based Framework for Quantifying Tortuosity in Meibomian Gland Uneven Atrophy
by: Wang, Kesheng, et al.
Published: (2025)

Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval
by: Liu, Zhuchenyang, et al.
Published: (2026)

Universal Representations for Classification-enhanced Lossy Compression
by: Nguyen, Nam
Published: (2025)

Scaling Training Data with Lossy Image Compression
by: Mentzer, Katherine L., et al.
Published: (2024)

Theoretical Guarantees of Data Augmented Last Layer Retraining Methods
by: Welfert, Monica, et al.
Published: (2024)

Enhancing Subsequent Video Retrieval via Vision-Language Models (VLMs)
by: Duan, Yicheng, et al.
Published: (2025)

SAFT: Sensitivity-Aware Filtering and Transmission for Adaptive 3D Point Cloud Communication over Wireless Channels
by: Mekki, Huda Adam Sirag, et al.
Published: (2026)

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

DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compression
by: Fu, Chunyang, et al.
Published: (2026)

A Novel Image Similarity Metric for Scene Composition Structure
by: Haque, Md Redwanul, et al.
Published: (2025)

Towards Universal & Efficient Model Compression via Exponential Torque Pruning
by: Modi, Sarthak Ketanbhai, et al.
Published: (2025)

Sampling Strategies for Efficient Training of Deep Learning Object Detection Algorithms
by: Shen, Gefei, et al.
Published: (2025)

Bi-Level Spatial and Channel-aware Transformer for Learned Image Compression
by: Soltani, Hamidreza, et al.
Published: (2024)

Point Cloud Compression with Implicit Neural Representations: A Unified Framework
by: Ruan, Hongning, et al.
Published: (2024)

Lossless Image Compression Using Multi-level Dictionaries: Binary Images
by: Agnihotri, Samar, et al.
Published: (2024)

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
by: Yan, Yibo, et al.
Published: (2026)

Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition
by: Lan, Yifan, et al.
Published: (2025)

Recursive Vision Transformer with Dynamic Depth and Width Adjustment for Resource-Efficient Image Semantic Communication
by: Zhang, Zhilong, et al.
Published: (2026)

HawkRover: An Autonomous mmWave Vehicular Communication Testbed with Multi-sensor Fusion and Deep Learning
by: Zhu, Ethan, et al.
Published: (2024)

Optimal Brain Connection: Towards Efficient Structural Pruning
by: Chen, Shaowu, et al.
Published: (2025)

Computationally Efficient Information-Driven Optical Design with Interchanging Optimization
by: Markley, Eric, et al.
Published: (2025)

Fast and Robust Phase Retrieval via Deep Expectation-Consistent Approximation
by: Shastri, Saurav K., et al.
Published: (2024)

Robust Sparse Signal Recovery with Outliers: A Hard Thresholding Pursuit Approach Based on LAD
by: Xu, Jiao, et al.
Published: (2026)

Towards Lossless Ultimate Vision Token Compression for VLMs
by: Zheng, Dehua, et al.
Published: (2025)

MambaVC: Learned Visual Compression with Selective State Spaces
by: Qin, Shiyu, et al.
Published: (2024)

A Rate-Distortion-Classification Approach for Lossy Image Compression
by: Zhang, Yuefeng
Published: (2024)