Christina Baek
10 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (15) π Conference Polyglot (4) πΊοΈ Taxonomy Completionist (20)
π
Century Club
(10)
β
The Questioner
Conferences
ICLR (4)
NIPS (3)
CVPR (2)
AISTATS (1)
Top co-authors
Keywords
distribution shift
(2)
model selection
(2)
continual learning
(1)
catastrophic forgetting
(1)
network architecture
(1)
variational inference
(1)
ensemble learning
(1)
test-time adaptation
(1)
incremental learning
(1)
out-of-distribution generalization
(1)
foundation model
(1)
out-of-distribution accuracy
(1)
neural network classifier
(1)
ensemble diversity
(1)
out-of-distribution performance
(1)
in-distribution accuracy
(1)
neural network
(1)
agreement prediction
(1)
rate reduction
(1)
white box architecture
(1)
Papers
Theory of Agreement-on-the-Line in Linear Models and Gaussian Data
AISTATS 2025
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
ICLR 2025
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
NIPS 2024
Why is SAM Robust to Label Noise?
ICLR 2024
On the Joint Interaction of Models, Data, and Features
ICLR 2024
Predicting the Performance of Foundation Models via Agreement-on-the-Line
NIPS 2024
Efficient Maximal Coding Rate Reduction by Variational Forms
CVPR 2022
Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift
NIPS 2022
Assessing Generalization of SGD via Disagreement
ICLR 2022
Incremental Learning via Rate Reduction
CVPR 2021