Kempe, Julia

28 publications

NeurIPS 2025 Asymmetric REINFORCE for Off-Policy Reinforcement Learning: Balancing Positive and Negative Rewards Charles Arnal, Gaëtan Narozniak, Vivien Cabannes, Yunhao Tang, Julia Kempe, Remi Munos

ICLR 2025 Beyond Model Collapse: Scaling up with Synthesized Data Requires Verification Yunzhen Feng, Elvis Dohmatob, Pu Yang, Francois Charton, Julia Kempe

ICLR 2025 DRoP: Distributionally Robust Data Pruning Artem M Vysogorets, Kartik Ahuja, Julia Kempe

ICLR 2025 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks Nikolaos Tsilivis, Gal Vardi, Julia Kempe

ICML 2025 PILAF: Optimal Human Preference Sampling for Reward Modeling Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng, Julia Kempe, Yaqi Duan

ICLRW 2025 PILAF: Optimal Human Preference Sampling for Reward Modeling Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng, Julia Kempe, Yaqi Duan

ICLR 2025 Strong Model Collapse Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe

ICML 2024 A Tale of Tails: Model Collapse as a Change of Scaling Laws Elvis Dohmatob, Yunzhen Feng, Pu Yang, Francois Charton, Julia Kempe

ICLRW 2024 A Tale of Tails: Model Collapse as a Change of Scaling Laws Yunzhen Feng, Elvis Dohmatob, Pu Yang, Francois Charton, Julia Kempe

TMLR 2024 Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks Yunzhen Feng, Tim G. J. Rudner, Nikolaos Tsilivis, Julia Kempe

ICMLW 2024 Beyond Model Collapse: Scaling up with Synthesized Data Requires Reinforcement Yunzhen Feng, Elvis Dohmatob, Pu Yang, Francois Charton, Julia Kempe

ICML 2024 Deconstructing the Goldilocks Zone of Neural Network Initialization Artem M Vysogorets, Anna Dawid, Julia Kempe

ICLR 2024 Embarrassingly Simple Dataset Distillation Yunzhen Feng, Shanmukha Ramakrishna Vedantam, Julia Kempe

NeurIPSW 2024 Emergent Properties with Repeated Examples Francois Charton, Julia Kempe

NeurIPSW 2024 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks Nikolaos Tsilivis, Gal Vardi, Julia Kempe

NeurIPS 2024 Iteration Head: A Mechanistic Study of Chain-of-Thought Vivien Cabannes, Charles Arnal, Wassim Bouaziz, Alice Yang, Francois Charton, Julia Kempe

ICMLW 2024 Iteration Head: A Mechanistic Study of Chain-of-Thought Vivien Cabannes, Charles Arnal, Wassim Bouaziz, Xingyu Alice Yang, Francois Charton, Julia Kempe

AISTATS 2024 Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors Tim G. J. Rudner, Ya Shi Zhang, Andrew Gordon Wilson, Julia Kempe

NeurIPS 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs Jingtong Su, Julia Kempe, Karen Ullrich

ICMLW 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs Jingtong Su, Julia Kempe, Karen Ullrich

NeurIPS 2024 Model Collapse Demystified: The Case of Regression Elvis Dohmatob, Yুনzhen Feng, Julia Kempe

TMLR 2024 On the Robustness of Neural Collapse and the Neural Collapse of Robustness Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis, Julia Kempe

NeurIPSW 2024 Repeated Examples Help Learn Arithmetic Francois Charton, Julia Kempe

NeurIPS 2024 The Price of Implicit Bias in Adversarially Robust Generalization Nikolaos Tsilivis, Natalie S. Frank, Nathan Srebro, Julia Kempe

JMLR 2023 Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity Artem Vysogorets, Julia Kempe

NeurIPSW 2023 Embarrassingly Simple Dataset Distillation Yunzhen Feng, Shanmukha Ramakrishna Vedantam, Julia Kempe

NeurIPSW 2023 On the Robustness of Neural Collapse and the Neural Collapse of Robustness Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis, Julia Kempe

NeurIPS 2022 What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? Nikolaos Tsilivis, Julia Kempe