Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Deep Learning Based Recommender System
2019795 citationsShuai Zhang, Lina Yao et al.ACM Computing Surveysprofile →
Efficient Transformers: A Survey
2022433 citationsYi Tay, Mostafa Dehghani et al.ACM Computing Surveysprofile →
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
2023121 citationsMirac Süzgün, Nathan Scales et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Yi Tay'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 Yi Tay with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Yi Tay more than expected).
This network shows the impact of papers produced by Yi Tay. 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 Yi Tay. The network helps show where Yi Tay may publish in the future.
Co-authorship network of co-authors of Yi Tay
This figure shows the co-authorship network connecting the top 25 collaborators of Yi Tay.
A scholar is included among the top collaborators of Yi Tay 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 Yi Tay. Yi Tay is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Süzgün, Mirac, Nathan Scales, Nathanael Schärli, et al.. (2023). Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them. 13003–13051.121 indexed citations breakdown →
Lee, Jason, Najoung Kim, Yi Tay, & Quoc V. Le. (2023). Inverse Scaling Can Become U-Shaped. OpenBU (Boston University). 15580–15591.15 indexed citations
Qin, Zhen, Le Yan, Honglei Zhuang, et al.. (2021). Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees. International Conference on Learning Representations.28 indexed citations
8.
Tay, Yi, Zhe Zhao, Dara Bahri, Donald Metzler, & Da-Cheng Juan. (2021). HyperGrid Transformers: Towards A Single Model for Multiple Tasks. International Conference on Learning Representations.7 indexed citations
9.
Tay, Yi, et al.. (2021). Synthesizer: Rethinking Self-Attention for Transformer Models. International Conference on Machine Learning. 10183–10192.5 indexed citations
10.
Metzler, Donald, Yi Tay, Dara Bahri, & Marc Najork. (2021). Rethinking Search: Making Experts out of Dilettantes. arXiv (Cornell University).4 indexed citations
11.
Tay, Yi, Dara Bahri, Yang Liu, Donald Metzler, & Da-Cheng Juan. (2020). Sparse Sinkhorn Attention. International Conference on Machine Learning. 1. 9438–9447.14 indexed citations
12.
Tay, Yi, Anh Tuan Luu, Aston Zhang, Shuohang Wang, & Siu Cheung Hui. (2019). Compositional De-Attention Networks. Neural Information Processing Systems. 32. 6132–6142.9 indexed citations
Tay, Yi, Luu Anh Tuan, & Siu Cheung Hui. (2017). HyperQA: Hyperbolic Embeddings for Fast and Efficient Ranking of Question Answer Pairs. arXiv (Cornell University).1 indexed citations
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.