Callista Krebs
@callistakrebs.bsky.social
Software Engineer in San Diego, CA interested in CS and ML applications in the biotech space.
Reposted by Callista Krebs
What's actually different between CLIP and DINOv2? CLIP knows what "Brazil" looks like: Rio's skyline, sidewalk patterns, and soccer jerseys.
We mapped 24,576 visual features in vision models using sparse autoencoders, revealing surprising differences in what they understand.
We mapped 24,576 visual features in vision models using sparse autoencoders, revealing surprising differences in what they understand.
February 26, 2025 at 1:12 PM
What's actually different between CLIP and DINOv2? CLIP knows what "Brazil" looks like: Rio's skyline, sidewalk patterns, and soccer jerseys.
We mapped 24,576 visual features in vision models using sparse autoencoders, revealing surprising differences in what they understand.
We mapped 24,576 visual features in vision models using sparse autoencoders, revealing surprising differences in what they understand.
Here's my latest update on #AdventOfCode: a summary of what I learned with Day 10 callistakrebs.github.io/projects/adv...
Home Projects Contact
callistakrebs.github.io
December 19, 2024 at 3:16 AM
Here's my latest update on #AdventOfCode: a summary of what I learned with Day 10 callistakrebs.github.io/projects/adv...
This is a summary of my #AdventofCode2024 adventure! (1/3)
December 17, 2024 at 3:15 AM
This is a summary of my #AdventofCode2024 adventure! (1/3)