Ananya Kumar
16 papers · 2019–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21) π Academic Marathon (6) π Conference Polyglot (6) π§ Keyword Pioneer
π§
Keyword Pioneer
π
Triple Crown
π€
Dynamic Duo
(11)
π₯
Mega-Team
(20)
π
Century Club
(16)
β‘
Prolific Year
(6)
π₯
Unstoppable
(7)
β
The Questioner
(2)
Conferences
ICLR (7)
NIPS (4)
ICML (2)
ACL (1)
CVPR (1)
UAI (1)
Top co-authors
Keywords
distribution shift
(4)
contrastive learning
(3)
out-of-distribution generalization
(2)
domain adaptation
(2)
unsupervised domain adaptation
(2)
representation learning
(2)
algorithmic fairness
(1)
model calibration
(1)
feature learning
(1)
uncertainty quantification
(1)
ensemble learning
(1)
model robustness
(1)
robust classification
(1)
empirical study
(1)
sample efficiency
(1)
feature disentanglement
(1)
prompt learning
(1)
entropy minimization
(1)
machine learning
(1)
zero-shot learning
(1)
Papers
Generative Classifiers Avoid Shortcut Solutions
ICLR 2025
How to Fine-Tune Vision Models with SGD
ICLR 2024
Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models
CVPR 2023
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
ICLR 2023
Are Sample-Efficient NLP Models More Robust?
ACL 2023
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
UAI 2022
Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
NIPS 2022
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
NIPS 2022
Extending the WILDS Benchmark for Unsupervised Adaptation
ICLR 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
ICLR 2022
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
ICML 2022
Selective Classification Can Magnify Disparities Across Groups
ICLR 2021
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
ICLR 2021
Self-training Avoids Using Spurious Features Under Domain Shift
NIPS 2020
Understanding Self-Training for Gradual Domain Adaptation
ICML 2020
Verified Uncertainty Calibration
NIPS 2019