Vadim's picture

3 8

Vadim

thingumajig

·

thingumajig

AI & ML interests

nlp, computer vision

Organizations

None yet

upvoted a collection 7 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 588

upvoted a collection 8 months ago

HISTAI - Whole Slide Images dataset

A brightfield pathology diagnostic dataset featuring a variety of tissue types, staining methods, and magnification levels with reports • 10 items • Updated Mar 2 • 66

upvoted a paper over 1 year ago

No More Adam: Learning Rate Scaling at Initialization is All You Need

Paper • 2412.11768 • Published Dec 16, 2024 • 43