Search filters

List of works by Tri Dao

A Kernel Theory of Modern Data Augmentation

scientific article published on 01 June 2019

An Empirical Study of Mamba-based Language Models

scientific article published on 12 June 2024

Approximating the Permanent by Sampling from Adaptive Partitions

scientific article published in January 2019

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling

scientific article published on 5 March 2024

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

Gaussian Quadrature for Kernel Features

scientific article published in January 2017

HiPPO: Recurrent Memory with Optimal Polynomial Projections

scientific article published in November 2020

Learning Compressed Transforms with Low Displacement Rank

article published in 2018

Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations

scientific article published on 01 June 2019

Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation

scientific article published on 01 April 2019

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

scientific article published on 1 December 2023

On the Downstream Performance of Compressed Word Embeddings

scientific article published on 01 December 2019

StarCoder: may the source be with you!

journal article from 'CoRR' published in 2023

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

scientific article published on 31 May 2024