Julia Kempe

5

Papers

46

Total Citations

Papers (5)

Embarrassingly Simple Dataset Distillation

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

PILAF: Optimal Human Preference Sampling for Reward Modeling

A Tale of Tails: Model Collapse as a Change of Scaling Laws

Deconstructing the Goldilocks Zone of Neural Network Initialization