Thread Reader
Share this page!
×
Post
Share
Email
Enter URL or ID to Unroll
×
Unroll Thread
You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649
How to get URL link on X (Twitter) App
On the Twitter thread, click on
or
icon on the bottom
Click again on
or
Share Via icon
Click on
Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at
Twitter Help
Rishi Jha
@rishi_d_jha
CS PhD student @Cornell_CS! Currently a Research Intern @Microsoft. Prev. @uwcse and UW Math.
Subscribe
Save as PDF
May 21
•
5 tweets
•
2 min read
I’m stoked to share our new paper: “Harnessing the Universal Geometry of Embeddings” with @jxmnop, Collin Zhang, and @shmatikov.
We present the first method to translate text embeddings across different spaces without any paired data or encoders.
Here's why we're excited: 🧵👇🏾
🌀 Preserving Geometry
Our method, vec2vec, reveals that all encoders—regardless of architecture or training data—learn nearly the same representations!
We demonstrate how to translate between these black-box embeddings without any paired data, maintaining high fidelity. (2/5)