Tri Dao
Artificial Intelligence · Neural Information Processing Systems · 2018–2024
A researcher in the Science corpus: 15 papers; trusts 1,100 researchers and is trusted by 144 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 551 citations into it; #15,488 of 36,961 by trust here, #4,711 by citations
- Computer Vision and Pattern Recognition — 299 citations into it; #3,455 of 21,973 by trust here, #5,372 by citations
- Model Architectures — 218 citations into it; #165 of 2,288 by trust here, #287 by citations
- Efficiency & Compression — 151 citations into it; #1,138 of 1,273 by trust here, #283 by citations
- Large Language Models — 112 citations into it
- Natural Language Processing — 82 citations into it
- Optimization & Training — 61 citations into it; #2,198 of 2,605 by trust here, #2,165 by citations
- Signal Processing — 58 citations into it; #4,684 of 7,592 by trust here, #1,781 by citations
Whom Tri Dao trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- Ilya Sutskever
- Quoc V. Le
- Alex Graves
- Jimmy Ba
Who trusts Tri Dao overall
- Beidi Chen
- Songlin Yang
- Yunjie Tian
- Albert Gu
- Yichao Fu
- Yue Liu
- Daniel Y. Fu
- Guangxuan Xiao
- Albert Tseng
- Michael Poli
Papers from Tri Dao's perspective
Ordered by how strongly the researchers Tri Dao trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Hungry Hungry Hippos: Towards Language Modeling with State Space Models (2022) — 677 citations
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning (2023) — 2,998 citations
- HiPPO: Recurrent Memory with Optimal Polynomial Projections (2020) — 1,021 citations
- StarCoder: may the source be with you! (2023) — 1,263 citations
- A Kernel Theory of Modern Data Augmentation (2018) — 225 citations
- Hyena Hierarchy: Towards Larger Convolutional Language Models (2023) — 532 citations
- Scatterbrain: Unifying Sparse and Low-rank Attention Approximation (2021) — 175 citations
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers (2021) — 1,197 citations
- Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time (2023) — 356 citations
- Monarch: Expressive Structured Matrices for Efficient and Accurate Training (2022) — 133 citations
- Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models (2021) — 95 citations
- FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision (2024) — 595 citations
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness (2022) — 4,798 citations
- Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps (2020) — 56 citations
- Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations (2019) — 131 citations