How to improve the geometry of multimodal representations in CLIP? New preprint out on "Cyclic Contrastive Language-Image Pretraining (CyCLIP)"! Go check it out: arxiv.org/abs/2205.14459
How to improve the geometry of multimodal representations in CLIP? New preprint out on "Cyclic Contrastive Language-Image Pretraining (CyCLIP)"! Go check it out: arxiv.org/abs/2205.14459
GIVEAWAY TIME!
POV: you want to become an ipad kid in college
here's how:
⭐️ follow us @ASUCLAStudentU
⭐️ tag your 2 late night study friends
⭐️ RT this tweet
*Must be a UCLA student to enter
Random winner will be chosen 11/11
6K Followers 3K FollowingAbsurdist humor, AI stuff, recsys, machine learning, mythology, meditation. Tech Emmy & book author. Work on robots. eigenhector on bsky and subst4ck
4K Followers 826 FollowingIncoming Assistant Professor @GeorgiaTech / @ICatGT / @GTrobotics.
Prev: PhD from @StanfordAILab @stanfordnlp.
I like robots, language, and people.
1.2M Followers 279 FollowingWe’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
4.4M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
717K Followers 288 FollowingTogether with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.