Chunyuan Li
Artificial Intelligence · Neural Information Processing Systems · 2015–2023
A researcher in the Science corpus: 51 papers; trusts 4,176 researchers and is trusted by 1,831 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,689 citations into it; #1,257 of 36,961 by trust here, #595 by citations
- Computer Vision and Pattern Recognition — 1,545 citations into it; #1,410 of 21,973 by trust here, #465 by citations
- Natural Language Processing — 432 citations into it; #2,257 of 5,725 by trust here, #1,453 by citations
- Multimodal Learning — 403 citations into it; #100 of 1,215 by trust here, #53 by citations
- Generative Models — 357 citations into it; #669 of 1,963 by trust here, #307 by citations
- Representation & Self-Supervised Learning — 286 citations into it; #1,717 of 3,156 by trust here, #1,081 by citations
- Model Architectures — 252 citations into it; #1,668 of 2,288 by trust here, #524 by citations
- Large Language Models — 203 citations into it; #233 of 810 by trust here, #266 by citations
Whom Chunyuan Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Yoshua Bengio
- Ilya Sutskever
- Radford M. Neal
- Yann LeCun
- Ross B. Girshick
- Karen Simonyan
Who trusts Chunyuan Li overall
- Yibo Yang
- Zhe Gan
- Changyou Chen
- Stanislav Fort
- Jianwei Yang
- Bo Li
- Yunchen Pu
- Haotian Liu
- Jianfeng Gao
- Fei Ye
Papers from Chunyuan Li's perspective
Ordered by how strongly the researchers Chunyuan Li 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
- Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (2020) — 2,259 citations
- Florence: A New Foundation Model for Computer Vision (2021) — 1,142 citations
- Visual Instruction Tuning (2023) — 10,396 citations
- Grounded Language-Image Pre-training (2021) — 1,697 citations
- Measuring the Intrinsic Dimension of Objective Landscapes (2018) — 566 citations
- ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching (2017) — 227 citations
- Variational Autoencoder for Deep Learning of Images, Labels and Captions (2016) — 851 citations
- Improved Baselines with Visual Instruction Tuning (2023) — 5,499 citations
- Instruction Tuning with GPT-4 (2023) — 837 citations
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (2020) — 366 citations
- Towards Language-Free Training for Text-to-Image Generation (2021) — 229 citations
- Efficient Self-supervised Vision Transformers for Representation Learning (2021) — 230 citations
- Focal Self-attention for Local-Global Interactions in Vision Transformers (2021) — 538 citations
- Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks (2015) — 368 citations
- Robust Navigation with Language Pretraining and Stochastic Sampling (2019) — 132 citations
- Learning Generic Sentence Representations Using Convolutional Neural Networks (2016) — 101 citations
- Generalized Decoding for Pixel, Image, and Language (2022) — 380 citations
- Symmetric Variational Autoencoder and Connections to Adversarial Learning (2017) — 73 citations
- An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models (2023) — 44 citations
- Generative Adversarial Network Training is a Continual Learning Problem (2018) — 53 citations