elizabeth

[elizabeth @EPDonoway]

logging back into this account after 13 years to invite you (yes you!) to come argue with me about whether your favorite post-training method is actually teaching your model anything :~)
(spoiler: it’s fewer bits than you think)

paper: https://t.co/aj91pVQ2et
poster @ 5 today!👇🏻

[Judy Shen @judyhshen]

A new lens to study how much information a model actually learns during training: EDL explains why (and when!) a single example can be enough!

👇Check out @EPDonoway and @HaileyJoren’s paper:
Wed July 8th: 5 - 6:45pm
A200