iiinova — where your digital self keeps evolving

Fred Sala

@fredsala.bsky.social

150 followers 281 following 8 posts

Wisconsin CS. Snorkel AI. Working on machine learning & information theory. pages.cs.wisc.edu/~fredsala

Posts Replies Media

Fred Sala @fredsala.bsky.social · 27/03/2026

Samsung's Silicon Valley HQ is a giant hollow cube: www.swagroup.com/projects/sam...

swagroup.com

Samsung Headquarters

Shanghai TowerChina’s tallest building, Shanghai Tower, is located in the [...]

071

Fred Sala @fredsala.bsky.social · 09/01/2026

They also regularly go down right before paper deadlines.

160

Fred Sala @fredsala.bsky.social · 23/04/2025

Today at @iclr-conf.bsky.social, come chat with @changho.bsky.social about what types of data drive weak-to-strong generalization!

0103

Fred Sala @fredsala.bsky.social · 06/01/2025

Some of our work that uses these ideas (and applies to code): harit7.github.io/posts/2023/0...

harit7.github.io

Aggregating Foundation Model Objects

CS PhD Candidate at UW Madison

010

Fred Sala @fredsala.bsky.social · 06/01/2025

The generalization of majority vote is a en.wikipedia.org/wiki/Fr%C3%A.... For code, this is the snippet whose total (square) distance to all the generated snippets is smallest. It gets more fun when you try to use a weighted mean, with weights corresponding to how “accurate” each snippet is.

en.wikipedia.org

Fréchet mean - Wikipedia

120

Fred Sala @fredsala.bsky.social · 06/01/2025

Probably not how the plot is made, but this type of problem is studied frequently in statistical phylogenetics. People often define spaces of phylogenetic trees, often continuous versions, equipped with a metric. For code, these trees are e.g. ASTs.

110

Fred Sala @fredsala.bsky.social · 11/12/2024

First up at #NeurIPS2024 from our group, our work on labeling via programmatic distillation (a spotlight!). Label your data orders of magnitude faster and cheaper — come join us today at Poster Session 2 East for a demo!

0158

Fred Sala @fredsala.bsky.social · 11/12/2024

Landed in Vancouver for #NeurIPS! Looking forward to seeing everyone. If you would like to chat about data-centric AI and foundation models, reach out!

0110