Concepedia

Tri Dao

TD

22

Publications

2.6K

Citations

17

H-Index

2017

Active since

Affiliations

Stanford University(Current)

Cornell University

University at Buffalo, State University of New York

Tri Dao is an author at Stanford University specializing in engineering, computer science, and data science.

Top concepts

EngineeringComputer ScienceData ScienceMachine LearningDeep LearningComputer EngineeringPattern RecognitionParallel ProgrammingMachine VisionParallel Computing

Publications per year

2017–2024

22

Publications

22

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Albert Gu, Tri Dao · arXiv (Cornell University) · 2023 · 954 citations · Full text

Engineering, Machine Learning, Recurrent Models +16

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Tri Dao, Daniel Y. Fu, Stefano Ermon et al. · arXiv (Cornell University) · 2022 · 456 citations · Full text

Engineering, Approximate Attention Algorithm, Computer Architecture +19

StarCoder: may the source be with you!

Raymond Li, Loubna Ben Allal, Yangtian Zi et al. · arXiv (Cornell University) · 2023 · 191 citations · Full text

Starcoder Models, Engineering, Bigcode Community +20

HiPPO: Recurrent Memory with Optimal Polynomial Projections

Albert Gu, Tri Dao, Stefano Ermon et al. · arXiv (Cornell University) · 2020 · 148 citations · Full text

Sequence Modelling, Engineering, Machine Learning +13

Combining Recurrent, Convolutional, and Continuous-time Models with\n Linear State-Space Layers

Albert Gu, Isys Johnson, Karan Goel et al. · arXiv (Cornell University) · 2021 · 141 citations · Full text

Rows per page

1–5 of 22