Junnan Li
Artificial Intelligence · with Hoi · 2020–2023
A researcher in the Science corpus: 15 papers; trusts 2,605 researchers and is trusted by 1,425 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 512 citations into it; #2,315 of 36,961 by trust here, #1,257 by citations
- Computer Vision and Pattern Recognition — 506 citations into it; #1,558 of 21,973 by trust here, #926 by citations
- Multimodal Learning — 188 citations into it; #84 of 1,215 by trust here, #81 by citations
- Representation & Self-Supervised Learning — 158 citations into it; #1,280 of 3,156 by trust here, #535 by citations
- Evaluation & Benchmarks — 78 citations into it
- Large Language Models — 73 citations into it; #107 of 810 by trust here, #190 by citations
- Natural Language Processing — 73 citations into it
- Optimization & Training — 51 citations into it
Whom Junnan Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Ross B. Girshick
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Yann LeCun
- Christian Szegedy
- Karen Simonyan
Who trusts Junnan Li overall
- Wenliang Dai
- Dongxu Li
- Bo Li
- Steven C. H. Hoi
- Chunyuan Li
- Caiming Xiong
- Renrui Zhang
- Haotian Liu
- Zhe Gan
- Antoine Yang
Papers from Junnan Li's perspective
Ordered by how strongly the researchers Junnan 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)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (2022) — 7,032 citations
- Align before Fuse: Vision and Language Representation Learning with Momentum Distillation (2021) — 2,847 citations
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (2023) — 8,665 citations
- Prototypical Contrastive Learning of Unsupervised Representations (2020) — 1,199 citations
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning (2023) — 3,705 citations
- The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation (2020) — 207 citations
- Align and Prompt: Video-and-Language Pre-training with Entity Prompts (2021) — 230 citations
- DivideMix: Learning with Noisy Labels as Semi-supervised Learning (2020) — 1,389 citations
- The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation (2020) — 7 citations
- Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training (2022) — 141 citations
- BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing (2023) — 559 citations
- MoPro: Webly Supervised Learning with Momentum Prototypes (2020) — 115 citations
- Open Vocabulary Object Detection with Pseudo Bounding-Box Labels (2021) — 118 citations
- CoMatch: Semi-supervised Learning with Contrastive Graph Regularization (2020) — 352 citations
- CodeT5+: Open Code Large Language Models for Code Understanding and Generation (2023) — 742 citations