Heewoo Jun
Artificial Intelligence · 2017–2024
A researcher in the Science corpus: 14 papers; trusts 1,166 researchers and is trusted by 1,034 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 393 citations into it; #2,417 of 36,961 by trust here, #419 by citations
- Computer Vision and Pattern Recognition — 280 citations into it; #1,891 of 21,973 by trust here, #725 by citations
- Natural Language Processing — 161 citations into it; #3,354 of 5,725 by trust here, #2,256 by citations
- Generative Models — 144 citations into it; #1,045 of 1,963 by trust here, #263 by citations
- Signal Processing — 83 citations into it; #1,730 of 7,592 by trust here, #983 by citations
- Large Language Models — 65 citations into it
- Representation & Self-Supervised Learning — 62 citations into it
- Model Architectures — 60 citations into it
Whom Heewoo Jun trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Ilya Sutskever
- Jonathan Ho
- Kaiming He
- Aäron van den Oord
- Alex Graves
- Oriol Vinyals
Who trusts Heewoo Jun overall
- Jiaxiang Tang
- Minghua Liu
- Ting-Li Chen
- Yuan Liu
- Yinghao Xu
- Hanqun Cao
- Tara N. Sainath
- Jinyu Li
- Ronghang Hu
- Jiahao Li
Papers from Heewoo Jun's perspective
Ordered by how strongly the researchers Heewoo Jun 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)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Evaluating Large Language Models Trained on Code (2021) — 10,663 citations
- Generative Pretraining From Pixels (2020) — 1,828 citations
- Training Verifiers to Solve Math Word Problems (2021) — 9,717 citations
- GPT-4 Technical Report (2023) — 26,133 citations
- Deep Learning Scaling is Predictable, Empirically (2017) — 1,031 citations
- Jukebox: A Generative Model for Music (2020) — 984 citations
- Scaling Laws for Autoregressive Generative Modeling (2020) — 639 citations
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts (2022) — 874 citations
- Cold Fusion: Training Seq2Seq Models Together with Language Models (2017) — 311 citations
- Efficient Training of Language Models to Fill in the Middle (2022) — 317 citations
- Shap-E: Generating Conditional 3D Implicit Functions (2023) — 491 citations
- Fast Spectrogram Inversion Using Multi-Head Convolutional Neural Networks (2018) — 120 citations
- LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024) — 326 citations
- Distribution Augmentation for Generative Modeling (2020) — 70 citations