Cover Image

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xiaohui, Ye, Peng, Huang, Chenyu, Zheng, Shenghe, Zhang, Bo, Bai, Lei, Ouyang, Wanli, Chen, Tao
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dynamic Base model Shift for Delta Compression
by: Huang, Chenyu, et al.
Published: (2025)

Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform
by: Huang, Chenyu, et al.
Published: (2025)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
by: Zheng, Shenghe, et al.
Published: (2025)

EMR-Merging: Tuning-Free High-Performance Model Merging
by: Huang, Chenyu, et al.
Published: (2024)

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
by: Huang, Chenyu, et al.
Published: (2026)

FREE-Merging: Fourier Transform for Efficient Model Merging
by: Zheng, Shenghe, et al.
Published: (2024)

Model Compression using Progressive Channel Pruning
by: Guo, Jinyang, et al.
Published: (2025)

Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression
by: Cai, Yuliang, et al.
Published: (2026)

Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
by: Tu, Chongjun, et al.
Published: (2025)

Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
by: Tan, Xudong, et al.
Published: (2025)

Delta-SVD: Efficient Compression for Personalized Text-to-Image Models
by: Zhang, Tangyuan, et al.
Published: (2025)

A CLIP-Powered Framework for Robust and Generalizable Data Selection
by: Yang, Suorong, et al.
Published: (2024)

Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression
by: Zhou, Bowen, et al.
Published: (2026)

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
by: Ye, Hancheng, et al.
Published: (2024)

Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision
by: Li, Minglei, et al.
Published: (2024)

CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer
by: Han, Tao, et al.
Published: (2024)

Transforming Weather Data from Pixel to Latent Space
by: Zhao, Sijie, et al.
Published: (2025)

Sparse Transformer for Ultra-sparse Sampled Video Compressive Sensing
by: Cao, Miao, et al.
Published: (2025)

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
by: Tang, Shengji, et al.
Published: (2024)

V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration
by: Zheng, Shenghe, et al.
Published: (2026)

HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates
by: Lu, Lei, et al.
Published: (2025)

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

Stereo Image Coding for Machines with Joint Visual Feature Compression
by: Jin, Dengchao, et al.
Published: (2025)

Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
by: Rogers, Ethan G., et al.
Published: (2025)

3D Gaussian Splatting Data Compression with Mixture of Priors
by: Liu, Lei, et al.
Published: (2025)

SnapCap: Efficient Snapshot Compressive Video Captioning
by: Sun, Jianqiao, et al.
Published: (2024)

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
by: Yang, Yantai, et al.
Published: (2025)

Delta-ICM: Entropy Modeling with Delta Function for Learned Image Compression
by: Shindo, Takahiro, et al.
Published: (2024)

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
by: Yang, Suorong, et al.
Published: (2025)

Data-Free Dynamic Compression of CNNs for Tractable Efficiency
by: Meiner, Lukas, et al.
Published: (2023)

Extreme Video Compression with Pre-trained Diffusion Models
by: Li, Bohan, et al.
Published: (2024)

Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation
by: Liang, Guotao, et al.
Published: (2026)

CompressNAS : A Fast and Efficient Technique for Model Compression using Decomposition
by: Sah, Sudhakar, et al.
Published: (2025)

FiT: Flexible Vision Transformer for Diffusion Model
by: Lu, Zeyu, et al.
Published: (2024)

An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks
by: Liu, Lei, et al.
Published: (2025)

Ultra-lightweight Neural Video Representation Compression
by: Kwan, Ho Man, et al.
Published: (2025)

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction
by: Chen, Junyi, et al.
Published: (2024)

HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation
by: Zhang, Sha, et al.
Published: (2024)

Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning
by: Zhang, Tianning, et al.
Published: (2024)

ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion
by: Song, Yuanyi, et al.
Published: (2025)