Ashvin Nair
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 10 papers; trusts 631 researchers and is trusted by 1,085 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 253 citations into it; #1,255 of 36,961 by trust here, #1,088 by citations
- Reinforcement Learning — 214 citations into it; #215 of 2,250 by trust here, #237 by citations
- Control and Systems Engineering — 106 citations into it; #231 of 8,519 by trust here, #86 by citations
- Computer Vision and Pattern Recognition — 84 citations into it; #2,230 of 21,973 by trust here, #1,073 by citations
- Computational Theory and Mathematics — 44 citations into it; #4,037 of 12,489 by trust here, #6,679 by citations
- Management Science and Operations Research — 36 citations into it; #4,339 of 12,201 by trust here, #1,428 by citations
- Representation & Self-Supervised Learning — 28 citations into it
- Robotics & Control — 28 citations into it; #588 of 612 by trust here, #298 by citations
Whom Ashvin Nair trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Sergey Levine
- Diederik P. Kingma
- Richard S. Sutton
- Geoffrey E. Hinton
- Pieter Abbeel
- Alex Krizhevsky
- Jan Peters
- Yoshua Bengio
- J. Urgen Schmidhuber
- E. Todorov
Who trusts Ashvin Nair overall
- Sergey Levine
- Chelsea Finn
- Abhishek Gupta
- Pieter Abbeel
- Suraj Nair
- Benjamin Eysenbach
- Shansi Zhang
- Abhinav Kumar Gupta
- Scott Fujimoto
- Michael Janner
Papers from Ashvin Nair's perspective
Ordered by how strongly the researchers Ashvin Nair 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
- 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)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- GPT-4 Technical Report (2023) — 26,133 citations
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics (2016) — 613 citations
- Overcoming Exploration in Reinforcement Learning with Demonstrations (2017) — 892 citations
- Visual Reinforcement Learning with Imagined Goals (2018) — 603 citations
- Accelerating Online Reinforcement Learning with Offline Datasets (2020) — 858 citations
- Skew-Fit: State-Covering Self-Supervised Reinforcement Learning (2019) — 313 citations
- Residual Reinforcement Learning for Robot Control (2018) — 624 citations
- Offline Reinforcement Learning with Implicit Q-Learning (2021) — 1,586 citations
- Combining self-supervised learning and imitation for vision-based rope manipulation (2017) — 338 citations
- Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning (2022) — 47 citations