Diane Bouchacourt

Computer Science · Physical Sciences

11h-index755citations49works4.52yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Domain Adaptation and Few-Shot Learning(11), Language and cultural evolution(11), Natural Language Processing Techniques(9), Generative Adversarial Networks and Image Synthesis(9), Topic Modeling(8)

Publications49 total

Reassessing the Validity of Spurious Correlations Benchmarks
arXiv (Cornell University)·2024Open Access
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
arXiv (Cornell University)·2024Open Access
$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
arXiv (Cornell University)·2024Open Access
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
arXiv (Cornell University)·2024· 2 citedOpen Access
Embracing Diversity: Interpretable Zero-shot Classification Beyond One Vector Per Class
2024· 1 citedOpen Access
An Introduction to Vision-Language Modeling
arXiv (Cornell University)·2024· 33 citedOpen Access
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
2024
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
2024
Understanding the Detrimental Class-level Effects of Data Augmentation
arXiv (Cornell University)·2023· 2 citedOpen Access
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
arXiv (Cornell University)·2023Open Access
Discovering environments with XRM
arXiv (Cornell University)·2023Open Access
PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning
arXiv (Cornell University)·2023· 4 citedOpen Access
Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?
arXiv (Cornell University)·2023Open Access
Birth of a Transformer: A Memory Viewpoint
arXiv (Cornell University)·2023· 9 citedOpen Access
Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies
arXiv (Cornell University)·2023· 2 citedOpen Access
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
arXiv (Cornell University)·2022· 11 citedOpen Access
Robust Self-Supervised Learning with Lie Groups
arXiv (Cornell University)·2022· 2 citedOpen Access
The Robustness Limits of SoTA Vision Models to Natural Variation
arXiv (Cornell University)·2022· 8 citedOpen Access
Disentanglement of Correlated Factors via Hausdorff Factorized Support
arXiv (Cornell University)·2022· 5 citedOpen Access
Measuring and signing fairness as performance under multiple stakeholder distributions
arXiv (Cornell University)·2022· 1 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Mark Ibrahim(21), Marco Baroni(14), Sebastian Nowozin(6), Randall Balestriero(5), Ari S. Morcos(5), David López-Paz(4), Rahma Chaabouni(4), Eugene Kharitonov(4), Quentin Garrido(4), Caner Hazırbaş(4), Ryota Tomioka(3), Haider Al-Tahan(3), Megan Richards(3), P. Vincent(3), Stéphane Deny(3), Laura Ruis(2), Jacob Andreas(2), Brenden M. Lake(2), Florian Bordes(2), Melissa Hall(2)