Prajit Ramachandran
Artificial Intelligence · 2016–2025
A researcher in the Science corpus: 13 papers; trusts 1,486 researchers and is trusted by 3,162 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 306 citations into it; #830 of 36,961 by trust here, #1,627 by citations
- Computer Vision and Pattern Recognition — 230 citations into it; #1,016 of 21,973 by trust here, #1,274 by citations
- Model Architectures — 115 citations into it; #138 of 2,288 by trust here, #177 by citations
- Reinforcement Learning — 75 citations into it; #1,302 of 2,250 by trust here, #1,782 by citations
- Optimization & Training — 59 citations into it
- Natural Language Processing — 57 citations into it; #1,138 of 5,725 by trust here, #2,276 by citations
- Management Science and Operations Research — 30 citations into it; #5,477 of 12,201 by trust here, #4,300 by citations
- Evaluation & Benchmarks — 24 citations into it
Whom Prajit Ramachandran trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Christian Szegedy
- J. Urgen Schmidhuber
- Yann LeCun
- Alex Graves
Who trusts Prajit Ramachandran overall
- Quoc V. Le
- Yilun Du
- Noam Shazeer
- Christoph Feichtenhofer
- Mingxing Tan
- Yoshua Bengio
- Sergey Levine
- Irwan Bello
- A. Srinivas
- Jianwei Yang
Papers from Prajit Ramachandran's perspective
Ordered by how strongly the researchers Prajit Ramachandran trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Stand-Alone Self-Attention in Vision Models (2019) — 1,375 citations
- Searching for Activation Functions (2018) — 3,877 citations
- Unsupervised Pretraining for Sequence to Sequence Learning (2016) — 292 citations
- Scaling Local Self-Attention for Parameter Efficient Visual Backbones (2021) — 476 citations
- Swish: a Self-Gated Activation Function (2017) — 712 citations
- Fast Generation for Convolutional Autoregressive Models (2017) — 67 citations
- Seq-NMS for Video Object Detection (2016) — 323 citations
- Stein Variational Policy Gradient (2017) — 153 citations
- Diversity and Depth in Per-Example Routing Models (2018) — 35 citations
- Fast Wavenet Generation Algorithm (2016) — 88 citations
- Revisiting Fundamentals of Experience Replay (2020) — 318 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- Backprop Evolution (2018) — 9 citations