Ankit Singh Rawat

Artificial Intelligence · 2010–2025

A researcher in the Science corpus: 13 papers; trusts 260 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 224 citations into it; #31,544 of 35,345 by trust here, #11,192 by citations
• Computer Vision and Pattern Recognition — 103 citations into it
• Natural Language Processing — 72 citations into it
• Model Architectures — 41 citations into it
• Computer Networks and Communications — 38 citations into it
• Large Language Models — 38 citations into it
• Optimization & Training — 26 citations into it
• Representation & Self-Supervised Learning — 25 citations into it; #2,911 of 3,145 by trust here, #2,863 by citations

Whom Ankit Singh Rawat trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Kaiming He
5. Ilya Sutskever
6. Yann LeCun
7. Diederik P. Kingma
8. Itzhak Tamo
9. Tomas Mikolov
10. Alex Graves

Who trusts Ankit Singh Rawat overall

1. Shuhao Cao
2. Kevin Meng
3. Swanand Ravindra Kadhe
4. Tian Zhou
5. Mohammed Hassanin
6. Hao Peng
7. Krzysztof Marcin Choromanski
8. Eric Mitchell
9. Sebastian Angel
10. Yunyang Xiong

Papers from Ankit Singh Rawat's perspective

Ordered by how strongly the researchers Ankit Singh Rawat trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Are Transformers universal approximators of sequence-to-sequence functions? (2019) — 533 citations
• Sampled Softmax with Random Fourier Features (2019) — 61 citations
• $O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers (2020) — 108 citations
• Think before you speak: Training Language Models With Pause Tokens (2023) — 302 citations
• Collaborative Spectrum Sensing in the Presence of Byzantine Attacks in Cognitive Radio Networks (2010) — 351 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• A statistical perspective on distillation (2021) — 107 citations
• Long-tail learning via logit adjustment (2020) — 1,020 citations
• Modifying Memories in Transformer Models (2020) — 278 citations
• Federated Learning with Only Positive Labels (2020) — 125 citations
• Centralized Repair of Multiple Node Failures With Applications to Communication Efficient Secret Sharing (2016) — 66 citations
• Locality and Availability in Distributed Storage (2014) — 269 citations
• Batch codes through dense graphs without short cycles (2014) — 53 citations