Ananya Kumar
16 papers · 2019–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (30) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π₯
Mega-Team Β· Squad
π€
Dynamic Duo
(11)
π¬
Deep Specialist
(10)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Trend Setter
β
The Questioner
(2)
ποΈ
Keyword Collector
(63)
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(15)
Application Areas
(13)
Learning Types Β· Machine Learning
(10)
Deep Learning
(6)
Core Methods
(4)
Learning Types Β· Deep Learning
(4)
Artificial Intelligence
(3)
Learning Paradigms
(2)
Optimization & Theory
(2)
Techniques
(2)
Natural Language Processing
(1)
Applications
(1)
Core AI
(1)
Models
(1)
Keywords
distribution shift
(8)
domain adaptation
(4)
contrastive learning
(3)
domain generalization
(3)
unsupervised learning
(2)
out-of-distribution generalization
(2)
representation learning
(2)
spurious correlation
(2)
unsupervised domain adaptation
(2)
transfer learning
(2)
out-of-distribution robustness
(2)
ensemble learning
(1)
vision transformer
(1)
uncertainty quantification
(1)
entropy minimization
(1)
sample efficiency
(1)
empirical study
(1)
robust classification
(1)
algorithmic fairness
(1)
model robustness
(1)
Papers
Generative Classifiers Avoid Shortcut Solutions
ICLR 2025
How to Fine-Tune Vision Models with SGD
ICLR 2024
Are Sample-Efficient NLP Models More Robust?
ACL 2023
Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models
CVPR 2023
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
ICLR 2023
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
NeurIPS 2022
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
UAI 2022
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
ICML 2022
Extending the WILDS Benchmark for Unsupervised Adaptation
ICLR 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
ICLR 2022
Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
NeurIPS 2022
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
ICLR 2021
Selective Classification Can Magnify Disparities Across Groups
ICLR 2021
Self-training Avoids Using Spurious Features Under Domain Shift
NeurIPS 2020
Understanding Self-Training for Gradual Domain Adaptation
ICML 2020
Verified Uncertainty Calibration
NeurIPS 2019