Coline Devin

Artificial Intelligence · 2015–2025

A researcher in the Science corpus: 15 papers; trusts 674 researchers and is trusted by 29 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 271 citations into it; #8,293 of 35,345 by trust here, #4,018 by citations
• Computer Vision and Pattern Recognition — 225 citations into it; #16,151 of 21,575 by trust here, #5,987 by citations
• Reinforcement Learning — 192 citations into it; #606 of 2,242 by trust here, #347 by citations
• Control and Systems Engineering — 102 citations into it; #1,459 of 8,257 by trust here, #187 by citations
• Representation & Self-Supervised Learning — 55 citations into it; #1,636 of 3,145 by trust here, #1,507 by citations
• Robotics & Control — 40 citations into it
• Aerospace Engineering — 35 citations into it
• Biomedical Engineering — 28 citations into it

Whom Coline Devin trusts overall

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

1. Sergey Levine
2. Diederik P. Kingma
3. Alex Krizhevsky
4. Geoffrey E. Hinton
5. Yann LeCun
6. Kaiming He
7. David G. Lowe
8. Ross B. Girshick
9. Yoshua Bengio
10. Ilya Sutskever

Who trusts Coline Devin overall

1. Sergey Levine
2. Abhishek Gupta
3. Pieter Abbeel
4. Jorge Armando Mendez Mendez
5. Stephen James
6. Faraz Torabi
7. Jacob Andreas
8. Rahul Ramesh
9. Andrew Hundt
10. Chelsea Finn

Papers from Coline Devin's perspective

Ordered by how strongly the researchers Coline Devin 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. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Learning modular neural network policies for multi-task and multi-robot transfer (2016) — 453 citations
• Towards Adapting Deep Visuomotor Representations from Simulated to Real Environments (2015) — 105 citations
• Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning (2017) — 292 citations
• Adapting Deep Visuomotor Representations with Weak Pairwise Constraints (2015) — 143 citations
• Deep Object-Centric Representations for Generalizable Robot Learning (2017) — 127 citations
• Learning To Reach Goals Without Reinforcement Learning (2019) — 38 citations
• Grasp2Vec: Learning Object Representations from Self-Supervised Grasping (2018) — 119 citations
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration0 (2023) — 1,105 citations
• Self-Supervised Goal-Conditioned Pick and Place (2020) — 10 citations
• Deep Object-Centric Policies for Autonomous Driving (2018) — 110 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Gemini Robotics: Bringing AI into the Physical World (2025) — 385 citations
• SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments (2021) — 44 citations
• Modularity Improves Out-of-Domain Instruction Following (2020) — 5 citations
• Learning to Reach Goals via Iterated Supervised Learning (2019) — 245 citations