Lune

Profiles2020-2026

Virginia Smith

Carnegie Mellon University

12Papers
9Last author
24Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers12

  1. Membership Inference Attacks for Unseen ClassesAuthor 4 of 4ICML 2026
  2. Many-Objective Multi-Solution TransportAuthor 3 of 5ICLR 2025
  3. Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign RelearningAuthor 4 of 4ICLR 2025
  4. No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design ChoicesAuthor 4 of 4NeurIPS 2024 · 56 citations
  5. Label Leakage and Protection in Two-party Split LearningAuthor 7 of 8ICLR 2022 · 170 citations
  6. On Privacy and Personalization in Cross-Silo Federated LearningAuthor 4 of 4NeurIPS 2022 · 78 citations
  7. On Large-Cohort Training for Federated LearningAuthor 5 of 5NeurIPS 2021 · 130 citations
  8. Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-SharingAuthor 6 of 7NeurIPS 2021 · 111 citations
  9. Tilted Empirical Risk MinimizationAuthor 4 of 4ICLR 2021 · 42 citations
  10. Two Sides of Meta-Learning Evaluation: In vs. Out of DistributionAuthor 3 of 3NeurIPS 2021 · 17 citations
  11. Progressive Compressed Records: Taking a Byte out of Deep Learning DataAuthor 3 of 3VLDB 2021 · 11 citations
  12. Fair Resource Allocation in Federated LearningAuthor 4 of 4ICLR 2020 · 971 citations
Dusk over the sea between two cliffs drawn in fine vertical lines