Virginia Smith

36 papers · 2014–2026 · 8 venues · across top CS/AI venues

This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 7 separate collaboration groups - the largest holds only 42% of them. Pick the group below that matches the researcher you mean. How a shared name is split.

Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.

Which Virginia Smith?

3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.

with Amrith Setlur, Mona T. Diab, Aashiq Muhamed 15 papers · 2021–2026 · NeurIPS, NAACL, ICLR Hide ▲

Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders ACL 2026 RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models EACL 2026 CoRAG: Collaborative Retrieval-Augmented Generation NAACL 2025 Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models NAACL 2025 GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients EMNLP 2024 On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift NeurIPS 2024 Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models ICML 2024 RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold NeurIPS 2024 Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts ICLR 2023 Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift NeurIPS 2023 Progressive Ensemble Distillation: Building Ensembles for Efficient Inference NeurIPS 2023 Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies NeurIPS 2023 Adversarial Unlearning: Reducing Confidence Along Adversarial Directions NeurIPS 2022 Label Leakage and Protection in Two-party Split Learning ICLR 2022 Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution NeurIPS 2021

with Tian Li, Maziar Sanjabi, Shengyuan Hu 14 papers · 2017–2025 · ICLR, NeurIPS, ICML Show ▼

with Martin Jaggi, Martin Takac, Michael I. Jordan 3 papers · 2014–2018 · JMLR, ICML, NeurIPS Show ▼

4 papers whose co-authors appear nowhere else under this name

Semantic Agreement Enables Efficient Open-Ended LLM Cascades EMNLP 2025 On Large-Cohort Training for Federated Learning NeurIPS 2021 A Kernel Theory of Modern Data Augmentation ICML 2019 Efficient Augmentation via Data Subsampling ICLR 2019

Venues · all papers under this name

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