Sotabase

Career

· Research Scientist, Google DeepMind2024–
· Research Scientist, Character.AI2023–2024
· Senior Researcher, AI Cognitive Services Research Group, Microsoft2020–2023
· Quantitative Research Intern, Jump Trading LLC2019–2019
· Research Intern, Microsoft Research Redmond2017–2017
· PhD Student, Machine Learning Department, Carnegie Mellon University2015–2020
· Research Intern, Microsoft Research Asia2013–2015
· Undergraduate Student, IIIS, Tsinghua University2011–2015
· Research Scientist, Meta AI

Publications (40)

An Empirical Study of Training End-to-End Vision-and-Language Transformers
Computer Vision and Pattern Recognition · 2021
438
cited
Generate rather than Retrieve: Large Language Models are Strong Context Generators
International Conference on Learning Representations · 2022
398
cited
Want To Reduce Labeling Cost? GPT-3 Can Help
Conference on Empirical Methods in Natural Language Processing · 2021
302
cited
DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
AAAI Conference on Artificial Intelligence · 2021
145
cited
Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data
Annual Meeting of the Association for Computational Linguistics · 2022
114
cited
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
Annual Meeting of the Association for Computational Linguistics · 2021
104
cited
REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
Neural Information Processing Systems · 2022
100
cited
Small Models are Valuable Plug-ins for Large Language Models
Annual Meeting of the Association for Computational Linguistics · 2023
76
cited
Fusing Context Into Knowledge Graph for Commonsense Question Answering
Findings · 2020
75
cited
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Findings · 2021
69
cited
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
International Joint Conference on Artificial Intelligence · 2021
62
cited
i-Code: An Integrative and Composable Multimodal Learning Framework
AAAI Conference on Artificial Intelligence · 2022
53
cited
On Strategyproof Conference Peer Review
International Joint Conference on Artificial Intelligence · 2018
53
cited
Retrieval Enhanced Model for Commonsense Generation
Findings · 2021
34
cited
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Conference on Empirical Methods in Natural Language Processing · 2023
28
cited
Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering
Conference on Empirical Methods in Natural Language Processing · 2022
28
cited
Fusing Context Into Knowledge Graph for Commonsense Reasoning
arXiv.org · 2020
25
cited
Leveraging Knowledge in Multilingual Commonsense Reasoning
Findings · 2021
19
cited
Task Compass: Scaling Multi-task Pre-training with Task Prefix
Conference on Empirical Methods in Natural Language Processing · 2022
19
cited
Sparse Modular Activation for Efficient Sequence Modeling
Neural Information Processing Systems · 2023
17
cited
Sotabase
Yichong Xu | Researcher Profile | Sotabase | Sotabase