← Authors

Virginia Smith

35 papers · 2014–2026 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (6) πŸƒ Academic Marathon (11) πŸ—ΊοΈ Taxonomy Completionist (63) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (9) πŸ’Ž Century Club (34) ⚑ Prolific Year (5) πŸ“ˆ Trend Setter ❓ The Questioner πŸ—ƒοΈ Keyword Collector (109)

Conferences

NIPS (13) ICLR (9) ICML (6) EMNLP (2) JMLR (2) NAACL (2) EACL (1)

Top co-authors

Tian Li (10) Amrith Setlur (7) Oscar Li (4) Shengyuan Hu (4) Maziar Sanjabi (4) Mona T. Diab (4) Ahmad Beirami (4) Aashiq Muhamed (4) Sergey Levine (3) Saurabh Garg (3)

Research topics

Differential Privacy (2) Privacy (2)

Keywords

federated learning (6) distributed optimization (3) distribution shift (3) differential privacy (3) communication efficiency (3) primal-dual optimization (2) few-shot learning (2) multi-task learning (2) large language model (2) retrieval-augmented generation (2) machine learning (2) ensemble learning (2) text generation (2) transfer learning (1) data poisoning (1) contrastive learning (1) representation learning (1) semi-supervised learning (1) knowledge distillation (1) benchmark evaluation (1)

Papers

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models EACL 2026
Semantic Agreement Enables Efficient Open-Ended LLM Cascades EMNLP 2025
Many-Objective Multi-Solution Transport ICLR 2025
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning ICLR 2025
CoRAG: Collaborative Retrieval-Augmented Generation NAACL 2025
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models NAACL 2025
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold NIPS 2024
Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models ICML 2024
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift NIPS 2024
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices NIPS 2024
GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients EMNLP 2024
On Tilted Losses in Machine Learning: Theory and Applications JMLR 2023
Differentially Private Adaptive Optimization with Delayed Preconditioners ICLR 2023
Progressive Ensemble Distillation: Building Ensembles for Efficient Inference NIPS 2023
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies NIPS 2023
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift NIPS 2023
Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts ICLR 2023
Label Leakage and Protection in Two-party Split Learning ICLR 2022
Adversarial Unlearning: Reducing Confidence Along Adversarial Directions NIPS 2022
On Privacy and Personalization in Cross-Silo Federated Learning NIPS 2022
Private Adaptive Optimization with Side information ICML 2022
Diverse Client Selection for Federated Learning via Submodular Maximization ICLR 2022
Tilted Empirical Risk Minimization ICLR 2021
Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution NIPS 2021
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing NIPS 2021
On Large-Cohort Training for Federated Learning NIPS 2021
Heterogeneity for the Win: One-Shot Federated Clustering ICML 2021
Ditto: Fair and Robust Federated Learning Through Personalization ICML 2021
Fair Resource Allocation in Federated Learning ICLR 2020
A Kernel Theory of Modern Data Augmentation ICML 2019
Efficient Augmentation via Data Subsampling ICLR 2019
CoCoA: A General Framework for Communication-Efficient Distributed Optimization JMLR 2018
Federated Multi-Task Learning NIPS 2017
Adding vs. Averaging in Distributed Primal-Dual Optimization ICML 2015
Communication-Efficient Distributed Dual Coordinate Ascent NIPS 2014