Boris Ginsburg
Artificial Intelligence · 2017–2026
A researcher in the Science corpus: 25 papers; trusts 1,360 researchers and is trusted by 1,944 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 404 citations into it; #1,470 of 36,961 by trust here, #3,068 by citations
- Computer Vision and Pattern Recognition — 181 citations into it; #1,318 of 21,973 by trust here, #1,600 by citations
- Signal Processing — 128 citations into it; #2,132 of 7,592 by trust here, #1,035 by citations
- Natural Language Processing — 124 citations into it; #4,513 of 5,725 by trust here, #2,787 by citations
- Speech & Audio — 115 citations into it; #1,006 of 1,080 by trust here, #439 by citations
- Model Architectures — 101 citations into it; #960 of 2,288 by trust here, #1,219 by citations
- Optimization & Training — 74 citations into it; #296 of 2,605 by trust here, #185 by citations
- Evaluation & Benchmarks — 43 citations into it
Whom Boris Ginsburg trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Alex Graves
- Christian Szegedy
- Sergey Ioffe
- Yann LeCun
Who trusts Boris Ginsburg overall
- Yang You
- Xinlei Chen
- Elad Hoffer
- Tao Lei
- Yu Zhang
- Stanislav Beliaev
- Karanbir Singh Chahal
- Mahmoud Assran
- Kaiming He
- Ting-Li Chen
Papers from Boris Ginsburg's perspective
Ordered by how strongly the researchers Boris Ginsburg 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)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Mixed Precision Training (2017) — 2,457 citations
- Large Batch Training of Convolutional Networks (2017) — 967 citations
- Scaling SGD Batch Size to 32K for ImageNet Training (2017) — 424 citations
- Factorization tricks for LSTM networks (2017) — 122 citations
- Jasper: An End-to-End Convolutional Neural Acoustic Model (2019) — 288 citations
- OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models (2018) — 33 citations
- Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification (2017) — 69 citations
- Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions (2019) — 328 citations
- NeMo: a toolkit for building AI applications using Neural Modules (2019) — 411 citations
- Spatially Parallel Convolutions (2018) — 10 citations
- Training Neural Speech Recognition Systems with Synthetic Speech Augmentation (2018) — 61 citations
- Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks (2019) — 108 citations
- Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq (2018) — 52 citations
- Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling (2018) — 44 citations
- SPGISpeech: 5, 000 hours of transcribed financial audio for fully formatted end-to-end speech recognition (2021) — 113 citations
- BigVGAN: A Universal Neural Vocoder with Large-Scale Training (2022) — 483 citations
- SHERLOC: Structured Diagnostic Localization for Code Repair Agents (2026)
- RULER: What's the Real Context Size of Your Long-Context Language Models? (2024) — 1,085 citations
- Efficient Sequence Transduction by Jointly Predicting Tokens and Durations (2023)
- Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition (2023) — 30 citations