Reminded me Google's earlier paper, "Language Modeling Is Compression" <a href="https://arxiv.org/abs/2309.10668" rel="nofollow">https://arxiv.org/abs/2309.10668Learning being a compression is also recently proposed as Gibbs compression proposition.See Gibbs randomness-compression proposition <a href="https://arxiv.org/abs/2505.23869v5" rel="nofollow">https://arxiv.org/abs/2505.23869v5
northlondoner · · focus · HN ↗
Learning being a compression is also recently proposed as Gibbs compression proposition.
See Gibbs randomness-compression proposition <a href="https://arxiv.org/abs/2505.23869v5" rel="nofollow">https://arxiv.org/abs/2505.23869v5