Ankit Gupta
Artificial Intelligence · Neural Information Processing Systems · 2020–2022
A researcher in the Science corpus: 8 papers; trusts 342 researchers and is trusted by 20 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 197 citations into it; #10,242 of 35,345 by trust here, #6,266 by citations
- Natural Language Processing — 127 citations into it; #5,668 of 5,688 by trust here, #2,732 by citations
- Computer Vision and Pattern Recognition — 92 citations into it; #12,455 of 21,575 by trust here, #10,905 by citations
- Model Architectures — 76 citations into it
- Large Language Models — 51 citations into it; #397 of 799 by trust here, #600 by citations
- Evaluation & Benchmarks — 41 citations into it
- Efficiency & Compression — 16 citations into it
- Information Systems — 12 citations into it
Whom Ankit Gupta trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Ashish Vaswani
- Jimmy Ba
- Alex Krizhevsky
- Noam Shazeer
- Jacob Devlin
- Kaiming He
Who trusts Ankit Gupta overall
- Jimmy Smith
- Harsh Mehta
- Andrew Warrington
- Albert Gu
- Dingkang Liang
- Aydar Bulatov
- Scott W. Linderman
- Abhimanyu Das
- Tri Dao
- Jonathan Berant
Papers from Ankit Gupta's perspective
Ordered by how strongly the researchers Ankit Gupta trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Break It Down: A Question Understanding Benchmark (2020) — 228 citations
- Injecting Numerical Reasoning Skills into Language Models (2020) — 248 citations
- SCROLLS: Standardized CompaRison Over Long Language Sequences (2022) — 184 citations
- Long Range Language Modeling via Gated State Spaces (2022) — 377 citations
- GMAT: Global Memory Augmentation for Transformers (2020) — 53 citations
- On the Parameterization and Initialization of Diagonal State Space Models (2022) — 629 citations
- Diagonal State Spaces are as Effective as Structured State Spaces (2022) — 508 citations
- Analyzing Transformers in Embedding Space (2022) — 151 citations