Lily Zhang
4 papers · 2021–2023 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (3) π£ Hot Topic Early Bird π Cross-Pollinator (8)
πΊοΈ
Taxonomy Completionist
(13)
Conferences
ICML (2)
MLHC (1)
NIPS (1)
Top co-authors
Keywords
shortcut learning
(1)
feature learning
(1)
domain adaptation
(1)
medical imaging
(1)
gradient descent
(1)
set prediction
(1)
deep neural network
(1)
inductive bia
(1)
out-of-distribution detection
(1)
spurious correlation
(1)
group fairness
(1)
estimation error
(1)
deep generative model
(1)
dataset bia
(1)
normalization layer
(1)
residual connection
(1)
permutation invariance
(1)
cross entropy
(1)
worst-group generalization
(1)
typical set
(1)
Papers
Donβt blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
NIPS 2023
When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations
MLHC 2023
Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
ICML 2022
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
ICML 2021