James Lee-Thorp

17 papers receiving 858 citations

James Lee-Thorp's Hit Papers

GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints 2023 · 215 citations
2150+1+2Years since publication100200300

Peers

James Lee-Thorp
Comparison fields: 5 of 67
  • Mathematical Physics 167
  • Computer Vision and Pattern Recognition 201
  • Hardware and Architecture 52
  • Artificial Intelligence 189
  • Atomic and Molecular Physics, and Optics 168
Replace Amina Chebira with:
Amina Chebira United States
Jonas Gomes Brazil
B. Keith Jenkins United States
Daniel Pak-Kong Lun Hong Kong
KENNETH R. CROUNSE United States
K. Goser Germany
P.-E. Danielsson Sweden
N. Papamarkos Greece
Zihan Zhang China
James Lee-Thorp relative to Amina Chebira United States Amina Chebira's profile →
Citations per field
00.5×5×10×15.3×
Amina Chebira · 1×
Citations per year

Countries citing papers authored by James Lee-Thorp

Since Specialization
Citations

This map shows the geographic impact of James Lee-Thorp'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 James Lee-Thorp with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites James Lee-Thorp more than expected).

Fields of papers citing papers by James Lee-Thorp

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by James Lee-Thorp. 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 James Lee-Thorp. The network helps show where James Lee-Thorp may publish in the future.

Co-authors

The 25 scholars most cited alongside James Lee-Thorp, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with James Lee-Thorp Line = papers co-authored together James Lee-Thorp links everyone, so they are left out of the graph.

All Works

17 of 17 papers shown
#Work
1
FNet: Mixing Tokens with Fourier Transforms
Hit paper breakdown →
2022343
2
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Hit paper breakdown →
2023215
3 201464
4 201764
5 201656
6 201852
7 201729
8 201622
9 202321
10 201616
11 201713
12 20206
13 20164
14 20163
15 20223
16 20242
17 20161

About James Lee-Thorp

James Lee-Thorp is a scholar working on Mathematical Physics, Atomic and Molecular Physics, and Optics, Artificial Intelligence, Materials Chemistry and Computer Vision and Pattern Recognition, having authored 17 papers that have together received 914 indexed citations. Recurring topics across this work include Topological Materials and Phenomena (8 papers), Topic Modeling (5 papers), Spectral Theory in Mathematical Physics (5 papers), Natural Language Processing Techniques (4 papers), Solidification and crystal growth phenomena (2 papers), Advanced Neural Network Applications (1 paper) and Photonic Crystals and Applications (1 paper). The work is most often cited by research in Mathematical Physics (167 citations), Computer Vision and Pattern Recognition (201 citations), Hardware and Architecture (52 citations), Artificial Intelligence (189 citations) and Atomic and Molecular Physics, and Optics (168 citations). James Lee-Thorp has collaborated with scholars based in United States and China. Frequent co-authors include Joshua Ainslie, Michael I. Weinstein, Santiago Ontañón, Ilya Eckstein, Charles Fefferman, Sumit K. Sanghai, Yury Zemlyanskiy, Michiel de Jong, Yi Zhu and Alexander G. Shtukenberg. Their work appears in journals such as Crystal Growth & Design, 2D Materials, Communications on Pure and Applied Mathematics, Memoirs of the American Mathematical Society and Archive for Rational Mechanics and Analysis.

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.

Explore authors with similar magnitude of impact