Published in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024
We present RollStore, a hybrid data indexing approach for decentralized blockchain applications.
Recommended citation: Qi Lin, Binbin Gu, Faisal Nawab. "RollStore: Hybrid Data Indexing for Decentralized Blockchain Applications." IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024.
Published in Proceedings of ACM Conference on Management of Data (SIGMOD), 2026
We design an LSM-based KV store leveraging Disaggregated Memory via RDMA to scale writes, achieving 4.5x higher write throughput and 76% lower P99 latency.
Recommended citation: Qi Lin, Gangqi Huang, Te Guo, Chang Guo, Viraj Thakkar, Zichen Zhu, Jianguo Wang, Zhichao Cao. "O3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading." Proceedings of ACM Conference on Management of Data (SIGMOD), 2026.
Published in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
A comprehensive analysis and defense framework for bit-flip error resilience in large language models.
Recommended citation: Yuhang Chen, Zhen Tan, Ajay Kumar Jaiswal, Huaizhi Qu, Xinyu Zhao, Qi Lin, Yu Cheng, Andrew Kwong, Zhichao Cao, Tianlong Chen. "Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework." Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.
Published in Proceedings of the International Conference on Extending Database Technology (EDBT), 2024
We propose a method for serving deep learning models within relational database systems.
Recommended citation: Lixi Zhou*, Qi Lin*, Jia Zou. "Serving Deep Learning Model in Relational Databases." Proceedings of the International Conference on Extending Database Technology (EDBT), 2024.