按年被提到
20242025 · 2 次2026
大模型与语言模型›量化、解码与分词·arXiv:2407.07723 · cs.IT

Lossless data compression by large models

Ziguang Li, Chao Huang, Xuliang Wang, Haibo Hu, Cole Wyeth, Dongbo Bu, Quan Yu, Wen Gao, Xingwu Liu, Ming Li · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-05-03 · 最近 2025-06-07
2不同的人
2活跃月份
2讨论串
24被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Modern data compression methods are slowly reaching their limits after 80 years of research, millions of papers, and wide range of applications. Yet, the extravagant 6G communication speed requirement raises a major open question for revolutionary new ideas of data compression. We have previously shown all understanding or learning are compression, under reasonable assumptions. Large language models (LLMs) understand data better than ever before. Can they help us to compress data? The LLMs may be seen to approximate the uncomputable Solomonoff induction. Therefore, under this new uncomputable paradigm, we present LMCompress. LMCompress shatters all previous lossless compression algorithms, doubling the lossless compression ratios of JPEG-XL for images, FLAC for audios, and H.264 for videos, and quadrupling the compression ratio of bz2 for texts. The better a large model understands the data, the better LMCompress compresses.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论compressedgas · 2025-05

“It is quite telling that they don't include any compression time or decompression time values. Only the compression ratios achieved.”

Understanding Is Compression原评论 ↗
被提交为 story · 2 次