Arvind Neelakantan
Artificial Intelligence · 2014–2025
A researcher in the Science corpus: 16 papers; trusts 1,330 researchers and is trusted by 1,023 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 541 citations into it; #1,059 of 36,961 by trust here, #147 by citations
- Natural Language Processing — 328 citations into it; #853 of 5,725 by trust here, #710 by citations
- Computer Vision and Pattern Recognition — 199 citations into it; #2,895 of 21,973 by trust here, #956 by citations
- Representation & Self-Supervised Learning — 78 citations into it; #1,762 of 3,156 by trust here, #1,081 by citations
- Model Architectures — 73 citations into it
- Optimization & Training — 43 citations into it; #1,961 of 2,605 by trust here, #799 by citations
- Large Language Models — 40 citations into it; #634 of 810 by trust here, #28 by citations
- Generative Models — 39 citations into it
Whom Arvind Neelakantan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ilya Sutskever
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Graves
- Oriol Vinyals
- Richard Socher
- Diederik P. Kingma
- Alex Krizhevsky
- Tomas Mikolov
- Sepp Hochreiter
Who trusts Arvind Neelakantan overall
- Rajarshi Das
- Tim Rocktaschel
- Sahisnu Mazumder
- Quoc V. Le
- Andrew McCallum
- Sebastian Riedel
- Nitish Gupta
- Mohit Bansal
- Barret Zoph
- Sebastian Ruder
Papers from Arvind Neelakantan's perspective
Ordered by how strongly the researchers Arvind Neelakantan 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Language Models are Few-Shot Learners (2020) — 61,005 citations
- GPT-4 Technical Report (2023) — 26,133 citations
- Neural Programmer: Inducing Latent Programs with Gradient Descent (2015) — 270 citations
- Adding Gradient Noise Improves Learning for Very Deep Networks (2015) — 597 citations
- Learning a Natural Language Interface with Neural Programmer (2016) — 139 citations
- Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset (2019) — 246 citations
- Compositional Vector Space Models for Knowledge Base Completion (2015) — 299 citations
- Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks (2016) — 278 citations
- Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space (2014) — 474 citations
- Trading Off Diversity and Quality in Natural Language Generation (2020) — 133 citations
- Theory and Experiments on Vector Quantized Autoencoders (2018) — 100 citations
- Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning (2019) — 15 citations
- Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema (2016) — 48 citations
- Text and Code Embeddings by Contrastive Pre-Training (2022) — 613 citations
- Parallel Scheduled Sampling (2019) — 24 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations