Kimin Lee
Artificial Intelligence · 2017–2023
A researcher in the Science corpus: 18 papers; trusts 2,229 researchers and is trusted by 357 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 571 citations into it; #2,235 of 36,961 by trust here, #2,264 by citations
- Computer Vision and Pattern Recognition — 376 citations into it; #3,075 of 21,973 by trust here, #2,937 by citations
- Reinforcement Learning — 198 citations into it; #730 of 2,250 by trust here, #589 by citations
- Representation & Self-Supervised Learning — 100 citations into it; #676 of 3,156 by trust here, #613 by citations
- Optimization & Training — 79 citations into it
- Evaluation & Benchmarks — 76 citations into it
- Safety, Robustness & Interpretability — 58 citations into it; #258 of 2,259 by trust here, #301 by citations
- Generative Models — 57 citations into it
Whom Kimin Lee trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Diederik P. Kingma
- Yoshua Bengio
- Christian Szegedy
- Yann LeCun
- Ilya Sutskever
- Ross B. Girshick
- Karen Simonyan
Who trusts Kimin Lee overall
- Dan Hendrycks
- Gyuhak Kim
- Kibok Lee
- Stanislav Fort
- Yixuan Li
- Jie Jessie Ren
- Jinwoo Shin
- Rui Huang
- Yen-Chang Hsu
- Sae-Young Chung
Papers from Kimin Lee's perspective
Ordered by how strongly the researchers Kimin Lee 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Decision Transformer: Reinforcement Learning via Sequence Modeling (2021) — 2,391 citations
- Reinforcement Learning with Augmented Data (2020) — 798 citations
- Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples (2017) — 963 citations
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (2018) — 2,720 citations
- Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild (2019) — 237 citations
- Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning (2019) — 198 citations
- Decoupling Representation Learning from Reinforcement Learning (2020) — 402 citations
- Aligning Text-to-Image Models using Human Feedback (2023) — 471 citations
- PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training (2021) — 408 citations
- DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models (2023) — 460 citations
- Hierarchical Novelty Detection for Visual Object Recognition (2018) — 79 citations
- Regularizing Class-Wise Predictions via Self-Knowledge Distillation (2020) — 350 citations
- Using Pre-Training Can Improve Model Robustness and Uncertainty (2019) — 836 citations
- Robust Inference via Generative Classifiers for Handling Noisy Labels (2019) — 163 citations
- Incremental Learning with Unlabeled Data in the Wild (2019) — 7 citations
- Regularizing Predictions via Class-wise Self-knowledge Distillation (2019) — 3 citations
- Learning to Specialize with Knowledge Distillation for Visual Question Answering (2018) — 39 citations
- Confident Multiple Choice Learning (2017) — 52 citations