Michael Fitzke (@butterkaffee) 's Twitter Profile
Michael Fitzke

@butterkaffee

Building AI to create a better world for pets @MarsGlobal

ID: 2179747009

calendar_today07-11-2013 09:38:37

2,2K Tweet

332 Followers

777 Following

Ross Wightman (@wightmanr) 's Twitter Profile Photo

As I wait for the SigLIP2 OpenCLIP and timm checkpoints to upload, a few comments. Like v1, these are very strong image encoders, but even better. They should become a go to ViT encoder for many tasks. Yet, even when we had ViT encoders from SigLIP, DFN CLIP, DataComp CLIP,

Michael Fitzke (@butterkaffee) 's Twitter Profile Photo

Looking for a paper I remember but can't track down: optimal stopping for deep learning for chest X-ray radiology, multilabel classification with N labels, stops M times (M<N) for M checkpoints. Anyone know it?

Manuel Faysse (@manuelfaysse) 's Twitter Profile Photo

🚨Should We Still Pretrain Encoders with Masked Language Modeling? We have recently seen massively trained causal decoders take the lead in embedding benchmarks, surpassing encoders w/ bidirectional attention. We revisit whether Bert-style encoders are a thing of the past? (1/N)

🚨Should We Still Pretrain Encoders with Masked Language Modeling? We have recently seen massively trained causal decoders take the lead in embedding benchmarks, surpassing encoders w/ bidirectional attention.  We revisit whether Bert-style encoders are a thing of the past? (1/N)
Alfredo Canziani (@alfcnz) 's Twitter Profile Photo

My NYU Center for Data Science colleague, Carlos Fernandez-Granda, released the 700-page textbook «Probability and Statistics for Data Science», where he condenses 10 years of teaching experience at @NYUniversity. 200 exercises, 102 notebooks, 115 videos! 🥳🥳🥳 ps4ds.net

My <a href="/NYUDataScience/">NYU Center for Data Science</a> colleague, Carlos Fernandez-Granda, released the 700-page textbook «Probability and Statistics for Data Science», where he condenses 10 years of teaching experience at @NYUniversity.
200 exercises, 102 notebooks, 115 videos! 🥳🥳🥳
ps4ds.net
Michael Fitzke (@butterkaffee) 's Twitter Profile Photo

Hey Sam Altman OpenAI – small idea with big impact: If a prompt comes from an audio transcription, add a system-level note for the model. It would help interpret typical voice-related quirks: misheard names, sentence fragments, course corrections.

eigenron (@eigenron) 's Twitter Profile Photo

i saw this guy’s video on simulating gravity in C++ and that pushed me into learning OpenGL (failure lol). now he’s back with another one simulating black holes. he incorporated ray tracing, Einstein’s field equation, Schwarzschild solution to the field equation, space-time,

i saw this guy’s video on simulating gravity in C++ and that pushed me into learning OpenGL (failure lol).

now he’s back with another one simulating black holes. 

he incorporated ray tracing, Einstein’s field equation, Schwarzschild solution to the field equation, space-time,