Publications

You can also find my articles on my Google Scholar profile.

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers

Published in NeurIPS 2025, 2025

This paper investigates the theoretical foundations of how unlabeled data in the prompt improves In-Context Learning.

Recommended citation: Renpu Liu, Jing Yang. (2025). "Unlabeled Data Can Provably Enhance In-Context Learning of Transformers." NeurIPS 2025.
Download Paper

In-Context Learning Based Efficient Spectrum Sensing

Published in ISIT 2025, 2025

Applying In-Context Learning techniques to efficient spectrum sensing problems.

Recommended citation: Renpu Liu, Liwen Zhong, Wooram Lee, and Jing Yang. (2025). "In-Context Learning Based Efficient Spectrum Sensing." ISIT 2025.
Download Paper

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery

Published in ICLR 2025, 2025

We demonstrate that Transformers can implement LISTA-type learning-to-optimize algorithms for LASSO-based sparse recovery.

Recommended citation: Renpu Liu*, Ruida Zhou*, Cong Shen, and Jing Yang. (2025). "On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery." ICLR 2025.
Download Paper

A Shared Low-Rank Adaptation Approach to Personalized RLHF

Published in AISTATS 2025, 2025

A personalized RLHF framework leveraging shared LoRA modules to capture both common and user-specific features.

Recommended citation: Renpu Liu, Peng Wang, Donghao Li, Cong Shen, Jing Yang. (2025). "A Shared Low-Rank Adaptation Approach to Personalized RLHF." AISTATS 2025.
Download Paper

Federated Representation Learning in the Under-Parameterized Regime

Published in ICML 2024, 2024

This paper explores Federated Representation Learning (FRL) in the under-parameterized regime.

Recommended citation: Renpu Liu, Cong Shen, and Jing Yang. (2024). "Federated Representation Learning in the Under-Parameterized Regime." ICML 2024.
Download Paper

Exploiting Feature Heterogeneity for Improved Generalization in Federated Multi-task Learning

Published in ISIT 2023, 2023

We prove that statistical heterogeneity in federated learning can enhance generalization performance under certain conditions.

Recommended citation: Renpu Liu, Jing Yang, and Cong Shen. (2023). "Exploiting Feature Heterogeneity for Improved Generalization in Federated Multi-task Learning." ISIT 2023.
Download Paper

Timely Broadcasting in Erasure Networks: Age-Rate Tradeoffs

Published in ISIT 2021, 2021

Investigating the benefits of coding on the Age of Information (AoI) and rate in memoryless broadcast channels.

Recommended citation: Chen, Xingran, Renpu Liu, Shaochong Wang, and Shirin Saeedi Bidokhti. (2021). "Timely Broadcasting in Erasure Networks: Age-Rate Tradeoffs." ISIT 2021.
Download Paper