's Avatar

@jamesaoldfield

Visiting scholar @ UW-Madison & PhD student in machine learning @ QMUL. Interested in interpretability and AI safety. https://james-oldfield.github.io/

77
Followers
100
Following
1
Posts
27.11.2024
Joined
Posts Following

Latest posts by @jamesaoldfield

Post image

Looking forward to speaking with folks thinking about architecture design for interpretability at #NeurIPS2024 next week. Feel free to drop by our poster #3003 on scaling MoE's expert specialization on Friday 13th @ 4:30pm! arxiv.org/abs/2402.12550

06.12.2024 15:15 ๐Ÿ‘ 2 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0