Jingwei Yu
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
Research Subjects
Jingwei Yu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Wei Xia
Huawei Noah's Ark Lab, Shenzhen, China
2 shared publications Bingxiong Lu
College of Resources and Environment of Qinzhou University, Qinzhou 535000, Guangxi, China
1 shared publicationErshe Xu
Wuxi Research Institute of Petroleum Geology, SINOPEC, Wuxi, 214151, Jiangsu, China
1 shared publication- Jianghao Lin
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Jiayi Lei
School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xian, China
1 shared publication - Kounianhua Du
Shanghai Jiao Tong University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4211-4221
LLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4211-4221
Open AccessLLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis
- Open Access
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SACAT: Student-Adaptive Computerized Adaptive Testing
Computerized Adaptive Testing refers to an online student ability testing system. It consists of Selection Algorithm and Cognitive Diagnosis Module (CDM). The Selection Algorithm aims to carefully select a small set of questions for the newly arrived student to answer, and the CDM aims to infer the ability of the newly arrived student based on his answers to the selected questions. The CDM faces the challenge of inferring student ability based on the short question-answer sequence. The state-of-the-art approach employs a meta-learning framework to solve this challenge. Specifically, in the outer-layer of the meta-learning framework, it learns an average student ability from all students as the initial ability for the newly arrived student, while in the inner-layer of the meta-learning framework, it infers the newly arrived student’s ability from the short sequence. However, this approach suffers from two major limitations: Firstly, collaborative information between the newly arrived student and all students was not utilized. Secondly, the meta-learning framework has a slow convergence. This paper introduces Student-Adaptive Computerized Adaptive Testing (SACAT), which addresses these issues by: Firstly, use the short sequence of the newly arrived student to retrieve similar students from all students. Secondly, design a fast adaptive function that can adaptively generate an ability representation suitable for the newly arrived student from abilities of similar students. Through extensive experiments on three real-world student response datasets, we validate that SACAT can outperform existing CAT methods. Furthermore, through the fast adaptation, we show that SACAT achieves fast model convergence.
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSACAT: Student-Adaptive Computerized Adaptive Testing
Computerized Adaptive Testing refers to an online student ability testing system. It consists of Selection Algorithm and Cognitive Diagnosis Module (CDM). The Selection Algorithm aims to carefully select a small set of questions for the newly arrived student to answer, and the CDM aims to infer the ability of the newly arrived student based on his answers to the selected questions. The CDM faces the challenge of inferring student ability based on the short question-answer sequence. The state-of-the-art approach employs a meta-learning framework to solve this challenge. Specifically, in the outer-layer of the meta-learning framework, it learns an average student ability from all students as the initial ability for the newly arrived student, while in the inner-layer of the meta-learning framework, it infers the newly arrived student’s ability from the short sequence. However, this approach suffers from two major limitations: Firstly, collaborative information between the newly arrived student and all students was not utilized. Secondly, the meta-learning framework has a slow convergence. This paper introduces Student-Adaptive Computerized Adaptive Testing (SACAT), which addresses these issues by: Firstly, use the short sequence of the newly arrived student to retrieve similar students from all students. Secondly, design a fast adaptive function that can adaptively generate an ability representation suitable for the newly arrived student from abilities of similar students. Through extensive experiments on three real-world student response datasets, we validate that SACAT can outperform existing CAT methods. Furthermore, through the fast adaptation, we show that SACAT achieves fast model convergence.
- 1 September 2017
- Published by American Scientific Publishers in Journal of Nanoscience and Nanotechnology
- Vol. 17 (9) , 6318-6327
Characteristics of Micro/Nano Pore in the Shale Gas Reservoir of Da’anzhai Section in Eastern Sichuan Basin
Argon ion polishing and FE-SEM techniques were used to study the Micro/nano pore of the shale Gas reservoir of Da’anzhai section in eastern Sichuan basin. Six types of pores were found to have developed in the reservoir: (1) Organic matter with nm-grade pores on the surface in dispersed form with poor connectivity; (2) nm-grade intergranular pores inside berry spherical pyrite aggregation with poor connectivity; (3) nm-grade grain pores in biological debris with poor connectivity; (4) alignment nm-grade pores between layers of clay minerals with good connectivity; (5) nm–μm grade solvent hole in clay mineral layer with good connectivity; and (6) microcracks, also nm–um grade, most of which are developed in the organic matter and brittle mineral edge with good connectivity. Among them, types 4, 5, and 6 are the main reservoir spaces. With the use of the cryogenic liquid nitrogen adsorption and BET equation, the calculated pore size distribution of shale reservoir in Da’anzhai includes 10 nm–25 nm mesopores, 100 nm–150 nm large pores, which account for a greater proportion, and a few <5 nm small pores. The specific surface area of shale reservoir was positively correlated to the pore volume, confirming that the pore diameters were mainly nanoscale mesopores. Correlated analyses were conducted between the specific surface area and clay minerals, organic carbon content, and vitrinite reflectance. Results show that clay mineral content exerted the most obvious control over shale reservoirs relative to nanoscale pore development. Meanwhile, organic maturity also had a certain influence, whereas content exerted very limited control over pore development.
- 1 September 2017
- Published by American Scientific Publishers in Journal of Nanoscience and Nanotechnology
- Vol. 17 (9) , 6318-6327
Characteristics of Micro/Nano Pore in the Shale Gas Reservoir of Da’anzhai Section in Eastern Sichuan Basin
Argon ion polishing and FE-SEM techniques were used to study the Micro/nano pore of the shale Gas reservoir of Da’anzhai section in eastern Sichuan basin. Six types of pores were found to have developed in the reservoir: (1) Organic matter with nm-grade pores on the surface in dispersed form with poor connectivity; (2) nm-grade intergranular pores inside berry spherical pyrite aggregation with poor connectivity; (3) nm-grade grain pores in biological debris with poor connectivity; (4) alignment nm-grade pores between layers of clay minerals with good connectivity; (5) nm–μm grade solvent hole in clay mineral layer with good connectivity; and (6) microcracks, also nm–um grade, most of which are developed in the organic matter and brittle mineral edge with good connectivity. Among them, types 4, 5, and 6 are the main reservoir spaces. With the use of the cryogenic liquid nitrogen adsorption and BET equation, the calculated pore size distribution of shale reservoir in Da’anzhai includes 10 nm–25 nm mesopores, 100 nm–150 nm large pores, which account for a greater proportion, and a few <5 nm small pores. The specific surface area of shale reservoir was positively correlated to the pore volume, confirming that the pore diameters were mainly nanoscale mesopores. Correlated analyses were conducted between the specific surface area and clay minerals, organic carbon content, and vitrinite reflectance. Results show that clay mineral content exerted the most obvious control over shale reservoirs relative to nanoscale pore development. Meanwhile, organic maturity also had a certain influence, whereas content exerted very limited control over pore development.