25 citations · 58 across the 8 of their papers we have counts for
8 papers
Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach
Kejing Lu, Zhenpeng Pan, Jianbin Qin +2
Approximate Nearest Neighbor Search (ANNS) is fundamental to modern AI applications. Most existing solutions optimize query efficiency but fail to align with the practical requirem…
Reverse Neighbor Sliding and Order Selection for Efficient Multi-Proximity Graph Merging
Liuchang Jing, Mingyu Yang, Lei Li +2
Approximate k Nearest Neighbor (AKNN) search in high-dimensional space is a foundational problem in vector databases with widespread applications. Among the numerous AKNN indexes,…
Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models
Xiaojun Chen, Tianle Wang, Tianhao Qiu +2
Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these…
BClean: A Bayesian Data Cleaning System
Jianbin Qin, Sifan Huang, Yaoshu Wang +6
There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent…
Identification of deuteron at BESIII
Wei Wang, Bo Zheng, Jia Jia Qin +1
The identification of deuteron with momentum in range of - GeV/ has been studied with the specific ionization energy loss information, using the data sample collecte…
Consistent and Flexible Selectivity Estimation for High-Dimensional Data
Yaoshu Wang, Chuan Xiao, Jianbin Qin +5
Selectivity estimation aims at estimating the number of database objects that satisfy a selection criterion. Answering this problem accurately and efficiently is essential to many…
Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach
Yaoshu Wang, Chuan Xiao, Jianbin Qin +4
Due to the outstanding capability of capturing underlying data distributions, deep learning techniques have been recently utilized for a series of traditional database problems. In…
Pigeonring: A Principle for Faster Thresholded Similarity Search
Jianbin Qin, Chuan Xiao
The pigeonhole principle states that if items are contained in boxes, then at least one box has no more than items. It is utilized to solve many data management pro…