Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pérez, Juan C., Pardo, Alejandro, Soldan, Mattia, Itani, Hani, Leon-Alcazar, Juan, Ghanem, Bernard
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909211325104128
author Pérez, Juan C.
Pardo, Alejandro
Soldan, Mattia
Itani, Hani
Leon-Alcazar, Juan
Ghanem, Bernard
author_facet Pérez, Juan C.
Pardo, Alejandro
Soldan, Mattia
Itani, Hani
Leon-Alcazar, Juan
Ghanem, Bernard
contents This study investigates whether Compressed-Language Models (CLMs), i.e. language models operating on raw byte streams from Compressed File Formats~(CFFs), can understand files compressed by CFFs. We focus on the JPEG format as a representative CFF, given its commonality and its representativeness of key concepts in compression, such as entropy coding and run-length encoding. We test if CLMs understand the JPEG format by probing their capabilities to perform along three axes: recognition of inherent file properties, handling of files with anomalies, and generation of new files. Our findings demonstrate that CLMs can effectively perform these tasks. These results suggest that CLMs can understand the semantics of compressed data when directly operating on the byte streams of files produced by CFFs. The possibility to directly operate on raw compressed files offers the promise to leverage some of their remarkable characteristics, such as their ubiquity, compactness, multi-modality and segment-nature.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration
Pérez, Juan C.
Pardo, Alejandro
Soldan, Mattia
Itani, Hani
Leon-Alcazar, Juan
Ghanem, Bernard
Computer Vision and Pattern Recognition
This study investigates whether Compressed-Language Models (CLMs), i.e. language models operating on raw byte streams from Compressed File Formats~(CFFs), can understand files compressed by CFFs. We focus on the JPEG format as a representative CFF, given its commonality and its representativeness of key concepts in compression, such as entropy coding and run-length encoding. We test if CLMs understand the JPEG format by probing their capabilities to perform along three axes: recognition of inherent file properties, handling of files with anomalies, and generation of new files. Our findings demonstrate that CLMs can effectively perform these tasks. These results suggest that CLMs can understand the semantics of compressed data when directly operating on the byte streams of files produced by CFFs. The possibility to directly operate on raw compressed files offers the promise to leverage some of their remarkable characteristics, such as their ubiquity, compactness, multi-modality and segment-nature.
title Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17146