Viewing profile — vvolhejn

A lot actually, since the model has all information given to it in the four views, it doesn't have to deal with any "theory of mind" of modeling the other players or being consiste…

Václav here from the team, we're happy to answer questions :) The most surprising part to me is the auto-recovery behavior we mention at the end of the blog post, since any other m…

> Is this just sort of expected for these models? Should users of this expect only truncation or can hallucinated bits happen too? Basically, yes, sort of expected: we don't have d…

Václav from Kyutai here. Thanks for the bug report! A workaround for now is to chunk the text into smaller parts where the model is more reliable. We already do some chunking in th…

Václav from Kyutai here. Yes the original naming scheme was from Les Miserables, glad you noticed! We just stuck to Alba because that's the real name of the voice actor that provid…

I had no idea this existed, the internet is amazing

There's a great blog post from Sander Dieleman about exactly this - why do we need a two step pipeline, in particular for images and audio? https://sander.ai/2025/04/15/latents.htm…

I train for 1M steps (batch size 64, block size 2048), which is enough for the model to more-or-less converge. It's also a tiny model for LLM standards, with 150M parameters. The g…

Author here, thanks for the kind words! I think such a physics-based codec is unlikely to happen: in general, machine learning is always moving from handcrafted domain-specific ass…

merci, will fix tomorrow

I use Descript to edit videos/podcasts and it works great for this kind of thing! It transcribes your audio and then you can edit it as if you were editing text.

I had a part about this but I took it out: for compression, you could keep the embeddings unquantized and it would still compress quite well, depending on the embedding dimension a…

I don't know about linear models, but this kind of hierarchical modelling is quite a common idea in speech research. For example, OpenAI's Jukebox (2020) [1], which uses a proto-ne…

Author here. Speech-to-text is more or less solved, it's easy to automatically get captions including precise timestamps. For training Moshi, Kyutai's audio LLM, my colleagues used…

Author here. There are a few reasons, but the biggest one is simply the compression ratio. The OG neural audio codec SoundStream (whose first author is Neil, now at Kyutai) can sou…

Author here. I think it's more of a capability issue than a safety issue. Since learning audio is still harder than learning text, audio models don't generalize as well. To fix tha…

Source code: https://github.com/vvolhejn/sine_wave_speech An interactive website for exploring how human speech can be reduced to just a few sine waves and still be intelligible - …

Yes! The fact that isochrones become circles is one of my favorite things about this. I also discuss this in the video ( https://youtu.be/rC2VQ-oyDG0?t=134 ) I made about these.

Sorry, that must be a bug. On desktop the map is large enough to be visible in its entirety but it is supposed to pan on mobile... I'll try to fix that

Indeed, you can't do this perfectly – it's an approximation. I just use one of the two directions as the travel time because if I wanted to symmetrize I'd have to call the Google M…

Oh yes, unfortunately, you can't do this perfectly. There are some graphs that cannot be embedded in Euclidean space in any number of dimensions, e.g. a 4-cycle with distance measu…

Yes! This is a less practical but more funky version of isochrone maps.

Cool! I'd love to have a look at that, but the two links in the paper seem to be broken :( http://roadlessforest.eu/map.htm and http://www.map.ox.ac.uk/accessibility_to_cities/