Alert button
Picture for Seong Joon Oh

Seong Joon Oh

Alert button

Shortcut Bias Mitigation via Ensemble Diversity Using Diffusion Probabilistic Models

Nov 23, 2023
Luca Scimeca, Alexander Rubinstein, Damien Teney, Seong Joon Oh, Armand Mihai Nicolicioiu, Yoshua Bengio

Viaarxiv icon

Exploring Practitioner Perspectives On Training Data Attribution Explanations

Oct 31, 2023
Elisa Nguyen, Evgenii Kortukov, Jean Song, Seong Joon Oh

Viaarxiv icon

Trustworthy Machine Learning

Oct 12, 2023
Bálint Mucsányi, Michael Kirchhof, Elisa Nguyen, Alexander Rubinstein, Seong Joon Oh

Viaarxiv icon

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Jul 07, 2023
Michael Kirchhof, Bálint Mucsányi, Seong Joon Oh, Enkelejda Kasneci

Figure 1 for URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
Figure 2 for URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
Figure 3 for URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
Figure 4 for URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
Viaarxiv icon

ProPILE: Probing Privacy Leakage in Large Language Models

Jul 04, 2023
Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, Seong Joon Oh

Figure 1 for ProPILE: Probing Privacy Leakage in Large Language Models
Figure 2 for ProPILE: Probing Privacy Leakage in Large Language Models
Figure 3 for ProPILE: Probing Privacy Leakage in Large Language Models
Figure 4 for ProPILE: Probing Privacy Leakage in Large Language Models
Viaarxiv icon

A Bayesian Perspective On Training Data Attribution

May 31, 2023
Elisa Nguyen, Minjoon Seo, Seong Joon Oh

Figure 1 for A Bayesian Perspective On Training Data Attribution
Figure 2 for A Bayesian Perspective On Training Data Attribution
Figure 3 for A Bayesian Perspective On Training Data Attribution
Figure 4 for A Bayesian Perspective On Training Data Attribution
Viaarxiv icon

Playing repeated games with Large Language Models

May 26, 2023
Elif Akata, Lion Schulz, Julian Coda-Forno, Seong Joon Oh, Matthias Bethge, Eric Schulz

Figure 1 for Playing repeated games with Large Language Models
Figure 2 for Playing repeated games with Large Language Models
Figure 3 for Playing repeated games with Large Language Models
Figure 4 for Playing repeated games with Large Language Models
Viaarxiv icon

Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts

Apr 04, 2023
Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh

Figure 1 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 2 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 3 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 4 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Viaarxiv icon

Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts

Mar 30, 2023
Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh

Figure 1 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 2 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 3 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 4 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Viaarxiv icon

Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs

Feb 06, 2023
Michael Kirchhof, Enkelejda Kasneci, Seong Joon Oh

Figure 1 for Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
Figure 2 for Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
Figure 3 for Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
Figure 4 for Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
Viaarxiv icon