Andreas Steiner

andreaspsteiner.bsky.social

20 February 2025 14:43

Looking for a small or medium sized VLM? PaliGemma 2 spans more than 150x of compute! Not sure yet if you want to invest the time 🪄finetuning🪄 on your data? Give it a try with our ready-to-use "mix" checkpoints: 🤗 huggingface.co/blog/paligem... 🎤 developers.googleblog.com/en/introduci...

Michael Tschannen

mtschannen.bsky.social

20 December 2024 15:34

Check out our detailed report about *Jet* 🌊 - a simple, transformer-based normalizing flow architecture without bells and whistles. Jet is an important part of JetFormer's engine ⚙️ As a standalone model it is very tame and behaves predictably (e.g. when scaling it up).

Jeremy Howard

howard.fm

19 December 2024 21:02

I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵

Chris Offner

chrisoffner3d.bsky.social

15 December 2024 11:07

I think it’s intellectually dishonest to engage in theatrical pearl clutching over Rosamund Picard’s slides and comments when there are good reasons to believe that there is a dark side to China’s hyper-competitive academic culture. www.nature.com/articles/d41...

Chris Offner

chrisoffner3d.bsky.social

10 December 2024 18:55

My earlier post was not intended to dunk on the Sora model or on Jim Fan, but to call out, and advise against, the ML community's frequent vice of resorting to "wishful mnemonics" – such as calling a video generation model a "physics engine". x.com/chrisoffner3...