Julia Kempe
16 papers · 2022–2026 · 5 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 ↓+4 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (34) π Triple Crown π Century Club Β· Bronze
ποΈ
Keyword Collector
(81)
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(15)
Optimization & Theory Β· Machine Learning
(14)
Artificial Intelligence
(9)
Core AI
(7)
Deep Learning
(6)
Natural Language Processing
(4)
Application Areas
(4)
Optimization & Theory Β· Deep Learning
(4)
Architectures
(3)
Learning Types
(3)
Generation
(2)
Resources & Methods
(2)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Bayesian & Probabilistic
(1)
Keywords
model collapse
(4)
neural network optimization
(3)
large language model
(3)
implicit bia
(3)
reward modeling
(2)
synthetic data
(2)
neural network
(2)
scaling law
(2)
steepest descent
(2)
statistical learning
(2)
margin maximization
(2)
adversarial robustness
(2)
subpopulation shift
(1)
transformer
(1)
domain generalization
(1)
preference alignment
(1)
attention mechanism
(1)
learning theory
(1)
data verification
(1)
gradient descent
(1)
Papers
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
JMLR 2026
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
ICLR 2025
DRoP: Distributionally Robust Data Pruning
ICLR 2025
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
ICLR 2025
PILAF: Optimal Human Preference Sampling for Reward Modeling
ICML 2025
Strong Model Collapse
ICLR 2025
A Tale of Tails: Model Collapse as a Change of Scaling Laws
ICML 2024
Deconstructing the Goldilocks Zone of Neural Network Initialization
ICML 2024
Embarrassingly Simple Dataset Distillation
ICLR 2024
Iteration Head: A Mechanistic Study of Chain-of-Thought
NeurIPS 2024
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
AISTATS 2024
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
NeurIPS 2024
Model Collapse Demystified: The Case of Regression
NeurIPS 2024
The Price of Implicit Bias in Adversarially Robust Generalization
NeurIPS 2024
Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity
JMLR 2023
What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?
NeurIPS 2022