there’s been some interesting work lately on multiscale autoregressive image modeling arxiv.org/abs/2404.029...
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction...
arxiv.org
March 29, 2025 at 2:55 AM
there’s been some interesting work lately on multiscale autoregressive image modeling arxiv.org/abs/2404.029...
city of stairs and the tainted cup both very good 👍
March 28, 2025 at 12:00 PM
city of stairs and the tainted cup both very good 👍
i think they’re just starting to realize what they unleashed w the tweet
March 25, 2025 at 12:43 PM
i think they’re just starting to realize what they unleashed w the tweet
we’re doing ai exorcisms in 2025 huh
March 4, 2025 at 7:29 PM
we’re doing ai exorcisms in 2025 huh
Reposted by bilal
like one of the big things about 404 media, Brian Merchant, Paris Marx, Ed Zitron, etc., is that they neither know nor care how the subject of their criticism actually works
January 23, 2025 at 8:18 PM
like one of the big things about 404 media, Brian Merchant, Paris Marx, Ed Zitron, etc., is that they neither know nor care how the subject of their criticism actually works
Reposted by bilal
an LLM that uses streetview to pre-drive down the route and assemble comments like "at the big red barn, turn left" "when you get to the sorta squiggly road, take the exit" like a farmer would
January 9, 2025 at 12:44 AM
an LLM that uses streetview to pre-drive down the route and assemble comments like "at the big red barn, turn left" "when you get to the sorta squiggly road, take the exit" like a farmer would
if you squint hard enough everything in ml is either a special case of the KL div or newton’s method
January 4, 2025 at 4:27 PM
if you squint hard enough everything in ml is either a special case of the KL div or newton’s method
justine tunney the libc mutex micro optimizations person??
December 19, 2024 at 5:21 AM
justine tunney the libc mutex micro optimizations person??
pov: post training researchers learning what pretraining researchers do while waiting for the model to train
December 6, 2024 at 10:21 PM
pov: post training researchers learning what pretraining researchers do while waiting for the model to train
thanks for cleaning it up
December 1, 2024 at 1:57 AM
thanks for cleaning it up