Andrew Tulloch

Most-cited papers

1. GPT-4o System Card

   OpenAI Aaron Hurst, A. Lerer, Adam P. Goucher, Adam Perelman +412 more

   20245,261 citations

   Semantic Scholar

   Save

2. Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

   Priya Goyal, Piotr Dollár, Ross B. Girshick, P. Noordhuis +5 more

   2017arXiv.org4,234 citations

   Semantic Scholar

   Save

3. Machine Learning at Facebook: Understanding Inference at the Edge

   Carole-Jean Wu, D. Brooks, Kevin Chen, Douglas Chen +22 more

   2019International Symposium on High-Performance Computer Architecture496 citations

   Semantic Scholar

   Save

4. Software-hardware co-design for fast and scalable training of deep learning recommendation models

   Dheevatsa Mudigere, Yuchen Hao, Jianyu Huang, Zhi-Hao Jia +49 more

   2021International Symposium on Computer Architecture219 citations Open access

   Semantic Scholar

   Save

5. Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

   Jongsoo Park, Maxim Naumov, Protonu Basu, Summer Deng +24 more

   2018arXiv.org207 citations

   Semantic Scholar

   Save

6. High-performance, Distributed Training of Large-scale Deep Learning Recommendation Models

   Dheevatsa Mudigere, Yuchen Hao, Jianyu Huang, Andrew Tulloch +47 more

   2021arXiv.org49 citations

   Semantic Scholar

   Save

7. Mixed-Precision Embedding Using a Cache

   J. Yang, Jianyu Huang, Jongsoo Park, Ping Tak Peter Tang +1 more

   2020arXiv.org43 citations

   Semantic Scholar

   Save

8. OpenAI GPT-4.5 System Card

   A. Paino, A. Kamali, Amin Tootoonchian, Andrew Tulloch +325 more

   30 citations

   Semantic Scholar

   Save

9. High performance ultra-low-precision convolutions on mobile devices

   Andrew Tulloch, Yang-Qing Jia

   2017arXiv.org29 citations

   Semantic Scholar

   Save

10. On Periodic Functions as Regularizers for Quantization of Neural Networks

    Maxim Naumov, Utku Diril, Jongsoo Park, Benjamin Ray +2 more

    2018arXiv.org26 citations

    Semantic Scholar

    Save

11. Accurate Low-Rank Approximations Via a Few Iterations of Alternating Least Squares

    A. Szlam, Andrew Tulloch, M. Tygert

    2017SIAM Journal on Matrix Analysis and Applications10 citations

    Semantic Scholar

    Save

12. MTrainS: Improving DLRM training efficiency using heterogeneous memories

    H. Kassa, Paul Johnson, Jason B. Akers, M. Ghosh +6 more

    2023arXiv.org4 citations Open access

    Semantic Scholar

    Save

13. Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition

    Bing Xu, Andrew Tulloch, Yunpeng Chen, Xiao-Meng Yang +1 more

    2019arXiv.org4 citations

    Semantic Scholar

    Save

14. Can LLMs Help Encoder Models Maintain Both High Accuracy and Consistency in Temporal Relation Classification?

    A. Meir, K. Bar, Aaron Grattafiori, Abhimanyu Dubey +496 more

    2025International Conference on Natural Language Generation0 citations

    Semantic Scholar

    Save

15. Accurate principal component analysis via a few iterations of alternating least squares

    A. Szlam, Andrew Tulloch, M. Tygert

    2016arXiv.org0 citations

    Semantic Scholar

    Save