Michael Zeng
Artificial Intelligence · 2018–2023
A researcher in the Science corpus: 23 papers; trusts 874 researchers and is trusted by 15 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 648 citations into it; #11,318 of 35,345 by trust here, #2,484 by citations
- Computer Vision and Pattern Recognition — 471 citations into it; #14,057 of 21,575 by trust here, #2,688 by citations
- Natural Language Processing — 304 citations into it; #2,943 of 5,688 by trust here, #2,045 by citations
- Multimodal Learning — 182 citations into it
- Large Language Models — 167 citations into it
- Evaluation & Benchmarks — 119 citations into it; #2,674 of 3,147 by trust here, #2,938 by citations
- Representation & Self-Supervised Learning — 89 citations into it
- Model Architectures — 75 citations into it
Whom Michael Zeng trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Alex Graves
- Yann LeCun
- Jimmy Ba
- Sepp Hochreiter
Who trusts Michael Zeng overall
Papers from Michael Zeng's perspective
Ordered by how strongly the researchers Michael Zeng 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Florence: A New Foundation Model for Computer Vision (2021) — 1,142 citations
- MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action (2023) — 603 citations
- An Empirical Study of Training End-to-End Vision-and-Language Transformers (2021) — 462 citations
- Generate rather than Retrieve: Large Language Models are Strong Context Generators (2022) — 431 citations
- Automatic Prompt Optimization with "Gradient Descent" and Beam Search (2023) — 730 citations
- Few-shot Natural Language Generation for Task-Oriented Dialog (2020) — 210 citations
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering (2018) — 131 citations
- UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data (2021) — 143 citations
- Enhancing Factual Consistency of Abstractive Summarization (2021) — 158 citations
- Want To Reduce Labeling Cost? GPT-3 Can Help (2021) — 338 citations
- SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding (2021) — 72 citations
- KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (2021) — 112 citations
- MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization (2021) — 163 citations
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks (2023) — 565 citations
- i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2023) — 4 citations
- AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022) — 53 citations
- ReCo: Region-Controlled Text-to-Image Generation (2022) — 214 citations
- Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning (2022) — 31 citations
- Speech-Language Pre-Training for End-to-End Spoken Language Understanding (2021) — 54 citations
- Retrieval Enhanced Model for Commonsense Generation (2021) — 36 citations