Marcin Junczys-Dowmunt (Marian NMT)
@marian-nmt.bsky.social
160 followers 130 following 16 posts
NLP. NMT. Main author of Marian NMT. Research Scientist at Microsoft Translator. https://marian-nmt.github.io
Posts Media Videos Starter Packs
Pinned
marian-nmt.bsky.social
Hi, the Microsoft Translator research team is looking for an intern for the summer. If you a PhD student in Machine Translation, Natural Language Processing, or related, check it out: aka.ms/mtintern
Search Jobs | Microsoft Careers
aka.ms
Reposted by Marcin Junczys-Dowmunt (Marian NMT)
clem.hf.co
Just 10 days after o1's public debut, we’re thrilled to unveil the open-source version of the technique behind its success: scaling test-time compute

By giving models more "time to think," Llama 1B outperforms Llama 8B in math—beating a model 8x its size. The full recipe is open-source!
marian-nmt.bsky.social
Rant: Apparently every vector-based sentence alignment tool insists on having an unusable file-based API.
marian-nmt.bsky.social
It's more confusing than that. It does exist and seems to mean crucifix which had me even more confused. Suddenly very high stakes 😀
marian-nmt.bsky.social
Missing bookmarks are a much bigger deal for me. But I think it's funny that they didn't go for one of the most requested features. Seemed like an easy win.
Reposted by Marcin Junczys-Dowmunt (Marian NMT)
porcoesphino.bsky.social
It's messier, but I think this one slaps the point home a bit stronger by adding the giant squid footage. I think unique weather, like lighting sprites, would make the point just as well.
Chart of time vs:
- number of cameras (exponentially increasing ),
- giant squid footage (exponentially increasing ),
- bigfoot footage (small and not increasing), and
- good quality UFO footage (small and not increasing)
Reposted by Marcin Junczys-Dowmunt (Marian NMT)
Reposted by Marcin Junczys-Dowmunt (Marian NMT)
artidoro.bsky.social
🚀 Introducing the Byte Latent Transformer (BLT) – A LLM architecture that scales better than Llama 3 using patches instead of tokens 🤯
Paper 📄 dl.fbaipublicfiles.com/blt/BLT__Pat...
Code 🛠️ github.com/facebookrese...
marian-nmt.bsky.social
Oh no no. VSCode is a an actual recommendation. My actual favorite piece of software that I didn't write.
marian-nmt.bsky.social
And they laughed at us when we pursued PhDs. Who's laughing now?
marian-nmt.bsky.social
Ah, are these size-limited? And you guys continue with running numbering?
marian-nmt.bsky.social
Oh. There you are. Where's that starter pack?