Hugging Face's logo
Wang Weiyi's picture

Wang Weiyi PRO

kaupane
4 29 214
RajeshKothiya's profile picture 21world's profile picture webbraine81e439009383113's profile picture
·

AI & ML interests

Embodied AI and whatever is fun

Recent Activity

upvoted a paper 2 days ago
Loop the Loopies!
liked a model 2 days ago
zitian-gao/Loopie-20B-A2B-preview
reacted to Saccadic-AI's post with 🔥 6 days ago
One neural network. Five mathematical operations. Different learning times. We trained a small mixture-of-experts transformer on addition, subtraction, multiplication, division, and exponentiation modulo 113. The operations didn’t generalize together. Multiplication and division reached 90% held-out accuracy first, followed by exponentiation, subtraction, and finally addition. Multiplication before addition—the reverse of what we expect from a schoolchild. The accuracy chart in the linked article shows why a single overall accuracy number can hide an interesting learning story. Measured with IRIS from Saccadic LLC. More figures and analysis: https://huggingface.co/blog/Saccadic-AI/accuracy-plateaued-the-model-kept-changing Have you observed a similar ordering in multi-task grokking experiments?
View all activity

Organizations

None yet