Scholar
Shanshan Wu
Google Scholar ID: AWuH7l0AAAAJ
Google Research, PhD at UT Austin
Citations & Impact
Citations
1,178
H-index
11
i10-index
12
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications' at ACL 2025 (Industry Track), equal contribution.
- Published 'Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs' at ICML 2025.
- Published 'Prompt Public Large Language Models to Synthesize Data for Private On-device Applications' at COLM 2024, equal contribution.
- Best Paper Award at NeurIPS Workshop on Federated Learning 2023 for 'Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning'.
- Published 'Motley: Benchmarking Heterogeneity and Personalization in Federated Learning' at NeurIPS Workshop on Federated Learning 2022.
- Co-authored the survey-style work 'A Field Guide to Federated Optimization' (2021, collaborative effort with 50+ authors).
- Published 'Federated Reconstruction: Partially Local Federated Learning' at NeurIPS 2021.
- Published 'Implicit Regularization and Convergence for Weight Normalization' at NeurIPS 2020, equal contribution.
- Published two papers at NeurIPS 2019: 'Learning Distributions Generated by One-Layer ReLU Networks' and 'Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models' (the latter was a Spotlight).
- Published 'Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling' at ICML 2019.
- Published two papers at NeurIPS 2016: 'Single Pass PCA of Matrix Products' and 'Leveraging Sparsity for Efficient Submodular Data Summarization'.
- Published 'Distributed Opportunistic Scheduling with QoS Constraints for Wireless Networks with Hybrid Links' in IEEE TVT 2015.
- Earlier work on CSMA/CA-based MAC protocols for MIMO WLANs, presented at IEEE Globecom 2013 and later published.
