Xiujun Li
Artificial Intelligence · 2015–2021
A researcher in the Science corpus: 20 papers; trusts 1,587 researchers and is trusted by 283 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 604 citations into it; #3,056 of 36,961 by trust here, #1,484 by citations
- Computer Vision and Pattern Recognition — 355 citations into it; #3,076 of 21,973 by trust here, #1,403 by citations
- Natural Language Processing — 270 citations into it; #2,030 of 5,725 by trust here, #1,208 by citations
- Reinforcement Learning — 166 citations into it; #1,025 of 2,250 by trust here, #740 by citations
- Multimodal Learning — 147 citations into it; #287 of 1,215 by trust here, #167 by citations
- Evaluation & Benchmarks — 57 citations into it
- Generative Models — 53 citations into it
- Large Language Models — 50 citations into it
Whom Xiujun Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- Alex Krizhevsky
- Ilya Sutskever
- Alex Graves
- Richard S. Sutton
- Yann LeCun
- Ross B. Girshick
Who trusts Xiujun Li overall
- Bing Liu
- Zhe Gan
- Jianfeng Wang
- Xiaowei Hu
- Jianfeng Gao
- Zhengyuan Yang
- Yicong Hong
- Linjie Li
- Pengchuan Zhang
- Chunyuan Li
Papers from Xiujun Li's perspective
Ordered by how strongly the researchers Xiujun 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
Their papers
- Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks (2020) — 2,259 citations
- VinVL: Revisiting Visual Representations in Vision-Language Models (2021) — 1,112 citations
- Recurrent Reinforcement Learning: A Hybrid Approach (2015) — 77 citations
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (2020) — 366 citations
- BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems (2016) — 173 citations
- Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation (2019) — 185 citations
- VinVL: Making Visual Representations Matter in Vision-Language Models (2021) — 175 citations
- Efficient Exploration for Dialog Policy Learning with Deep BBQ Networks \& Replay Buffer Spiking (2016) — 58 citations
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (2018) — 318 citations
- Towards Coherent and Cohesive Long-form Text Generation (2018) — 58 citations
- Robust Navigation with Language Pretraining and Stochastic Sampling (2019) — 132 citations
- Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access (2016) — 310 citations
- MiniVLM: A Smaller and Faster Vision-Language Model (2020) — 76 citations
- End-to-End Task-Completion Neural Dialogue Systems (2017) — 382 citations
- Few-shot Natural Language Generation for Task-Oriented Dialog (2020) — 210 citations
- Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning (2017) — 195 citations
- Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020) — 202 citations
- Complementary Auxiliary Classifiers for Label-Conditional Text Generation (2020) — 23 citations
- End-to-End Reinforcement Learning of Dialogue Agents for Information Access (2016) — 45 citations
- Efficient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking (2016)