https://hackerpaper.kaipfister.de/p/2005.00341/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=45660560urn:hackerpapers:mention:2005.00341:45660560Tue, 21 Oct 2025 19:32:26 GMT<p>I don&#x27;t know about linear models, but this kind of hierarchical modelling is quite a common idea in speech research. For example, OpenAI&#x27;s Jukebox (2020) [1], which uses a proto-neural audio codec, has three levels of encoding that get coarser and coarser. They use a language model to predict continuations in the coarsest level and then have models to upscale to the finer levels and finally back to audio. The recent MiMo-audio bunches tokens into &quot;patches&quot; of four timesteps and has the model predict those. [2] [1] https://arxiv.org/abs/2005.00341 [2]…</p><p><a href="https://hackerpaper.kaipfister.de/p/2005.00341/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS