Ziwei Ji
- Artificial Intelligence top 1%
- Health Informatics top 0.2%
- Information Systems top 2%
- Computer Vision and Pattern Recognition top 5%
- Radiology, Nuclear Medicine and Imaging top 10%
- Topics
- Topic Modeling (6 papers)Stochastic Gradient Optimization Techniques (6 papers)Natural Language Processing Techniques (6 papers)
- Partner nations
- Hong KongUnited StatesCanada
In The Last Decade
Ziwei Ji
20 papers receiving 2.0k citations
Hit Papers
Peers
Comparison fields: 5 of 151
- Artificial Intelligence 1.3k
- Health Informatics 378
- Information Systems 259
- Computer Vision and Pattern Recognition 170
- Radiology, Nuclear Medicine and Imaging 146
Countries citing papers authored by Ziwei Ji
This map shows the geographic impact of Ziwei Ji's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ziwei Ji with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ziwei Ji more than expected).
Fields of papers citing papers by Ziwei Ji
This network shows the impact of papers produced by Ziwei Ji. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ziwei Ji. The network helps show where Ziwei Ji may publish in the future.
Co-authorship network of co-authors of Ziwei Ji
This figure shows the co-authorship network connecting the top 25 collaborators of Ziwei Ji. A scholar is included among the top collaborators of Ziwei Ji based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Ziwei Ji. Ziwei Ji is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 2 | |
| 2 | 7 | |
| 3 | 4 | |
| 4 | 1 | |
| 5 | 89 | |
| 6 | 1 | |
| 7 | 16 | |
| 8 | 1 | |
| 9 | 16 | |
| 10 | A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitybreakdown → | 388 |
| 11 | Survey of Hallucination in Natural Language Generationbreakdown → | 1469 |
| 12 | 0 | |
| 13 | Characterizing the implicit bias via a primal-dual analysis. | 1 |
| 14 | 75 | |
| 15 | Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks | 10 |
| 16 | Directional convergence and alignment in deep learning | 2 |
| 17 | Neural tangent kernels, transportation mappings, and universal approximation | 2 |
| 18 | Gradient descent follows the regularization path for general losses. | 0 |
| 19 | The implicit bias of gradient descent on nonseparable data | 14 |
| 20 | Gradient descent aligns the layers of deep linear networks | 15 |
About Ziwei Ji
Ziwei Ji is a scholar working on Health Informatics, Artificial Intelligence and Software, having authored 22 papers that have together received 2.1k indexed citations. Recurring topics across this work include Topic Modeling (6 papers), Stochastic Gradient Optimization Techniques (6 papers) and Natural Language Processing Techniques (6 papers). The work is most often cited by research in Health Informatics (378 citations), Artificial Intelligence (1.3k citations) and Computer Science Applications (98 citations). Ziwei Ji has collaborated with scholars based in Hong Kong, United States and Canada. Frequent co-authors include Tiezheng Yu, Pascale Fung, Yan Xu, Dan Su, Etsuko Ishii, Nayeon Lee, Andrea Madotto, Rita Frieske, Wenliang Dai and Samuel Cahyawijaya. Their work appears in journals such as Applied Physics Letters, ACM Computing Surveys and Surgical Endoscopy.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.