Baotong Lu

Senior Researcher

Publications

View by:

- MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
  
  Beidi Zhao, Yaoqi Chen, Yuru Feng, Menghao Li, Qianxi Zhang, Baotong Lu, Jianan Lu, Zilong Wang, Xinjiang Wang, Shusen Xu, Zengzhong Li, Xiaoxiao Li, Qi Chen
  
  August 2026
  
  arXiv | August 2026
  
  Publication
- DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
  
  Yizou Chen, Tsun-Yu Yang, Zhisheng Hu, Baotong Lu, Ming-Chang Yang
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
  
  Yaoqi Chen, Haibin Lai, Yuru Feng, Chuyu Han, Qianxi Zhang, Baotong Lu, Menghao Li, Xinjiang Wang, Zilong Wang, Shusen Xu, Zengzhong Li, Zewen Jin, Hao Wu, Cheng Li, Qi Chen
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
  
  Mo Li, Baotong Lu, James Cheng, Chenhao Ma
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
  
  Zihan Zhao, Baotong Lu, Shengjie Lin, Yizou Chen, Jing Liu, Yanqi Zhang, Ziming Miao, Ming-Chang Yang, Haiying Shen, Qi Chen, Fan Yang
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
  
  Zebin Yang, Tong Xie, Baotong Lu, Shaoshan Liu, Bo Yu, Meng Li
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Scalable Distributed Vector Search via Accuracy Preserving Index Construction
  
  Yuming Xu, Qianxi Zhang, Qi Chen, Baotong Lu, Menghao Li, Philip Adams, Mingqin Li, Zengzhong Li, Jing Liu, Cheng Li, Fan Yang
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study
  
  Mocheng Li, Xiao Yan, Baotong Lu, Yue Zhang, James Cheng, Chenhao Ma
  
  Proceedings of the ACM on Management of Data | August 2025, Vol 3: pp. 1-26
  
  DOI Publication Publication
- CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA
  
  Xiangyu Zhi, Meng Chen, Xiao Yan, Baotong Lu, Hui Li, Qianxi Zhang, Qi Chen, James Cheng
  
  Proceedings of the ACM on Management of Data | July 2025, Vol 4: pp. 1-27
  
  DOI Publication Publication
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
  
  Yaoqi Chen, Jin-Kang Zhang, Baotong Lu, Qianxi Zhang, Cheng Zhang, Jing Liu, Jingjia Luo, Di Liu, Huiqiang Jiang, Qi Chen, Bailu Ding, Xiao Yan, Jiawei Jiang, Chen Chen, Mingxing Zhang, Cheng Li, Yuqing Yang, Fan Yang, Mao Yang
  
  VLDB Endowment | May 2025, Vol 19(5)
  
  DOI Publication
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  
  Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
  
  NeurIPS 2025 | September 2024
  
  Best Paper Award | ENLSP NeurIPS Workshop 2024
  
  Publication
- DEX: Scalable Range Indexing on Disaggregated Memory
  
  Baotong Lu, Kaisong Huang, Chieh-Jan Mike Liang, Tianzheng Wang, Eric Lo
  
  VLDB (International Conference on Very Large Data Bases) | August 2024
  
  DOI Preprint

- MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
  
  Beidi Zhao, Yaoqi Chen, Yuru Feng, Menghao Li, Qianxi Zhang, Baotong Lu, Jianan Lu, Zilong Wang, Xinjiang Wang, Shusen Xu, Zengzhong Li, Xiaoxiao Li, Qi Chen
  
  August 2026
  
  arXiv | August 2026
  
  Publication
- Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
  
  Yaoqi Chen, Haibin Lai, Yuru Feng, Chuyu Han, Qianxi Zhang, Baotong Lu, Menghao Li, Xinjiang Wang, Zilong Wang, Shusen Xu, Zengzhong Li, Zewen Jin, Hao Wu, Cheng Li, Qi Chen
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
  
  Zihan Zhao, Baotong Lu, Shengjie Lin, Yizou Chen, Jing Liu, Yanqi Zhang, Ziming Miao, Ming-Chang Yang, Haiying Shen, Qi Chen, Fan Yang
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
  
  Zebin Yang, Tong Xie, Baotong Lu, Shaoshan Liu, Bo Yu, Meng Li
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
  
  Yaoqi Chen, Jin-Kang Zhang, Baotong Lu, Qianxi Zhang, Cheng Zhang, Jing Liu, Jingjia Luo, Di Liu, Huiqiang Jiang, Qi Chen, Bailu Ding, Xiao Yan, Jiawei Jiang, Chen Chen, Mingxing Zhang, Cheng Li, Yuqing Yang, Fan Yang, Mao Yang
  
  VLDB Endowment | May 2025, Vol 19(5)
  
  DOI Publication
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  
  Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
  
  NeurIPS 2025 | September 2024
  
  Best Paper Award | ENLSP NeurIPS Workshop 2024
  
  Publication
- DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
  
  Yizou Chen, Tsun-Yu Yang, Zhisheng Hu, Baotong Lu, Ming-Chang Yang
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
  
  Mo Li, Baotong Lu, James Cheng, Chenhao Ma
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
  
  Yizou Chen, Tsun-Yu Yang, Zhisheng Hu, Baotong Lu, Ming-Chang Yang
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  
  Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
  
  NeurIPS 2025 | September 2024
  
  Best Paper Award | ENLSP NeurIPS Workshop 2024
  
  Publication
- DEX: Scalable Range Indexing on Disaggregated Memory
  
  Baotong Lu, Kaisong Huang, Chieh-Jan Mike Liang, Tianzheng Wang, Eric Lo
  
  VLDB (International Conference on Very Large Data Bases) | August 2024
  
  DOI Preprint
- Scalable Distributed Vector Search via Accuracy Preserving Index Construction
  
  Yuming Xu, Qianxi Zhang, Qi Chen, Baotong Lu, Menghao Li, Philip Adams, Mingqin Li, Zengzhong Li, Jing Liu, Cheng Li, Fan Yang
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study
  
  Mocheng Li, Xiao Yan, Baotong Lu, Yue Zhang, James Cheng, Chenhao Ma
  
  Proceedings of the ACM on Management of Data | August 2025, Vol 3: pp. 1-26
  
  DOI Publication Publication
- CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA
  
  Xiangyu Zhi, Meng Chen, Xiao Yan, Baotong Lu, Hui Li, Qianxi Zhang, Qi Chen, James Cheng
  
  Proceedings of the ACM on Management of Data | July 2025, Vol 4: pp. 1-27
  
  DOI Publication Publication
- CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA
  
  Xiangyu Zhi, Meng Chen, Xiao Yan, Baotong Lu, Hui Li, Qianxi Zhang, Qi Chen, James Cheng
  
  Proceedings of the ACM on Management of Data | July 2025, Vol 4: pp. 1-27
  
  DOI Publication Publication
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  
  Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
  
  NeurIPS 2025 | September 2024
  
  Best Paper Award | ENLSP NeurIPS Workshop 2024
  
  Publication

- MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
  
  Beidi Zhao, Yaoqi Chen, Yuru Feng, Menghao Li, Qianxi Zhang, Baotong Lu, Jianan Lu, Zilong Wang, Xinjiang Wang, Shusen Xu, Zengzhong Li, Xiaoxiao Li, Qi Chen
  
  August 2026
  
  arXiv | August 2026
  
  Publication
- DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System
  
  Yizou Chen, Tsun-Yu Yang, Zhisheng Hu, Baotong Lu, Ming-Chang Yang
  
  July 2026
  
  arXiv | July 2026
  
  Publication
- Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
  
  Yaoqi Chen, Haibin Lai, Yuru Feng, Chuyu Han, Qianxi Zhang, Baotong Lu, Menghao Li, Xinjiang Wang, Zilong Wang, Shusen Xu, Zengzhong Li, Zewen Jin, Hao Wu, Cheng Li, Qi Chen
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
  
  Mo Li, Baotong Lu, James Cheng, Chenhao Ma
  
  May 2026
  
  arXiv | May 2026
  
  Publication
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
  
  Zihan Zhao, Baotong Lu, Shengjie Lin, Yizou Chen, Jing Liu, Yanqi Zhang, Ziming Miao, Ming-Chang Yang, Haiying Shen, Qi Chen, Fan Yang
  
  April 2026
  
  arXiv | April 2026
  
  Publication
- KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
  
  Zebin Yang, Tong Xie, Baotong Lu, Shaoshan Liu, Bo Yu, Meng Li
  
  February 2026
  
  arXiv | February 2026
  
  Publication
- Scalable Distributed Vector Search via Accuracy Preserving Index Construction
  
  Yuming Xu, Qianxi Zhang, Qi Chen, Baotong Lu, Menghao Li, Philip Adams, Mingqin Li, Zengzhong Li, Jing Liu, Cheng Li, Fan Yang
  
  December 2025
  
  arXiv | December 2025
  
  Publication
- Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study
  
  Mocheng Li, Xiao Yan, Baotong Lu, Yue Zhang, James Cheng, Chenhao Ma
  
  Proceedings of the ACM on Management of Data | August 2025, Vol 3: pp. 1-26
  
  DOI Publication Publication
- CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA
  
  Xiangyu Zhi, Meng Chen, Xiao Yan, Baotong Lu, Hui Li, Qianxi Zhang, Qi Chen, James Cheng
  
  Proceedings of the ACM on Management of Data | July 2025, Vol 4: pp. 1-27
  
  DOI Publication Publication
- RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference
  
  Yaoqi Chen, Jin-Kang Zhang, Baotong Lu, Qianxi Zhang, Cheng Zhang, Jing Liu, Jingjia Luo, Di Liu, Huiqiang Jiang, Qi Chen, Bailu Ding, Xiao Yan, Jiawei Jiang, Chen Chen, Mingxing Zhang, Cheng Li, Yuqing Yang, Fan Yang, Mao Yang
  
  VLDB Endowment | May 2025, Vol 19(5)
  
  DOI Publication
- RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  
  Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, Lili Qiu
  
  NeurIPS 2025 | September 2024
  
  Best Paper Award | ENLSP NeurIPS Workshop 2024
  
  Publication
- DEX: Scalable Range Indexing on Disaggregated Memory
  
  Baotong Lu, Kaisong Huang, Chieh-Jan Mike Liang, Tianzheng Wang, Eric Lo
  
  VLDB (International Conference on Very Large Data Bases) | August 2024
  
  DOI Preprint

Baotong Lu

Publications

MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory

DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System

Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents

EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

Scalable Distributed Vector Search via Accuracy Preserving Index Construction

Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study

CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

DEX: Scalable Range Indexing on Disaggregated Memory

MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory

Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System

EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates

DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

DEX: Scalable Range Indexing on Disaggregated Memory

Scalable Distributed Vector Search via Accuracy Preserving Index Construction

Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study

CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA

CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory

DMG: A Scalable and Efficient Memory-Disaggregated Graph Processing System

Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents

EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates

Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

Scalable Distributed Vector Search via Accuracy Preserving Index Construction

Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study

CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

DEX: Scalable Range Indexing on Disaggregated Memory