Yuan Sui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yuan Sui has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Bryan Hooi
National University of Singapore, Singapore, Singapore
2 shared publications - Xiaoxin He
National University of Singapore, Singapore, Singapore
2 shared publications - Yufei He
National University of Singapore, Singapore, Singapore
2 shared publications - Dongmei Zhang
Microsoft Research Asia, Beijing, China
1 shared publication - Hao Ma
Beijing University of Posts and Telecommunications, Beijing 100876, P. R. China
1 shared publication - Huaxiang Zhang
Shandong Normal University
1 shared publication
Latest Publications
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 448-459
UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 448-459
Open AccessUniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1759-1770
UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1759-1770
Open AccessUniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
- Top Cited PapersOpen Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 645-654
Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study
Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. However, there is still much to learn about how well LLMs understand structured data, such as tables. Although tables can be used as input to LLMs with serialization, there is a lack of comprehensive studies that examine whether LLMs can truly comprehend such data. In this paper, we try to understand this by designing a benchmark to evaluate the structural understanding capabilities (SUC) of LLMs. The benchmark we create includes seven tasks, each with its own unique challenges, \eg, cell lookup, row retrieval, and size detection. We perform a series of evaluations on GPT-3.5 and GPT-4. We find that performance varied depending on several input choices, including table input format, content order, role prompting, and partition marks. Drawing from the insights gained through the benchmark evaluations, we proposeself-augmentation for effective structural prompting, such as critical value / range identification using internal knowledge of LLMs. When combined with carefully chosen input choices, these structural prompting methods lead to promising improvements in LLM performance on a variety of tabular tasks, \eg, TabFact(\uparrow2.31%), HybridQA(\uparrow2.13%), SQA(\uparrow2.72%), Feverous(\uparrow0.84%), and ToTTo(\uparrow5.68%). We believe that our open-source (please find code and data at https://github.com/microsoft/TableProvider) benchmark and proposed prompting methods can serve as a simple yet generic selection for future research.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 645-654
Top Cited PapersOpen AccessTable Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study
Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. However, there is still much to learn about how well LLMs understand structured data, such as tables. Although tables can be used as input to LLMs with serialization, there is a lack of comprehensive studies that examine whether LLMs can truly comprehend such data. In this paper, we try to understand this by designing a benchmark to evaluate the structural understanding capabilities (SUC) of LLMs. The benchmark we create includes seven tasks, each with its own unique challenges, \eg, cell lookup, row retrieval, and size detection. We perform a series of evaluations on GPT-3.5 and GPT-4. We find that performance varied depending on several input choices, including table input format, content order, role prompting, and partition marks. Drawing from the insights gained through the benchmark evaluations, we proposeself-augmentation for effective structural prompting, such as critical value / range identification using internal knowledge of LLMs. When combined with carefully chosen input choices, these structural prompting methods lead to promising improvements in LLM performance on a variety of tabular tasks, \eg, TabFact(\uparrow2.31%), HybridQA(\uparrow2.13%), SQA(\uparrow2.72%), Feverous(\uparrow0.84%), and ToTTo(\uparrow5.68%). We believe that our open-source (please find code and data at https://github.com/microsoft/TableProvider) benchmark and proposed prompting methods can serve as a simple yet generic selection for future research.
- 9 August 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 126
Intelligent predictive maintenance of hydraulic systems based on virtual knowledge graph
- 9 August 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 126
Intelligent predictive maintenance of hydraulic systems based on virtual knowledge graph
- 5 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 250
Causality-aware Enhanced Model for Multi-hop Question Answering over Knowledge Graphs
- 5 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 250
Causality-aware Enhanced Model for Multi-hop Question Answering over Knowledge Graphs
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 690-694
3D cognitive radio: A way to improve spectrum utilization by exploiting the height dimension
In this paper, the height dimension is exploited to improve the spectrum utilization and capacity of cognitive radio networks. As we notice that the majority of primary users are distributed in the low-height places, such as the street, shopping mall, subway, etc. Even in the metropolis full of skyscrapers, the users of primary networks at the top of skyscrapers are still the minorities. Thus the spectrum opportunities in the height dimension exist. Using directional antenna, the interference to primary users can be coordinated. This paper explores the possibility of height-dimensional spectrum access and constructs three-dimensional (3D) cognitive radio. Meanwhile, the conditions to exploit height-dimensional spectrum opportunities are provided and the relations are simulated.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 690-694
3D cognitive radio: A way to improve spectrum utilization by exploiting the height dimension
In this paper, the height dimension is exploited to improve the spectrum utilization and capacity of cognitive radio networks. As we notice that the majority of primary users are distributed in the low-height places, such as the street, shopping mall, subway, etc. Even in the metropolis full of skyscrapers, the users of primary networks at the top of skyscrapers are still the minorities. Thus the spectrum opportunities in the height dimension exist. Using directional antenna, the interference to primary users can be coordinated. This paper explores the possibility of height-dimensional spectrum access and constructs three-dimensional (3D) cognitive radio. Meanwhile, the conditions to exploit height-dimensional spectrum opportunities are provided and the relations are simulated.