I'm co-founder and CTO of Weco AI, where we're building AI that builds AI.
Previously, I completed my PhD in Computer Science at University College London, co-advised by Prof. Sebastian Riedel and Prof. Pontus Stenetorp in the UCL NLP Group. My research focused on Natural Language Processing, Question Answering, and knowledge-intensive NLP tasks. I also hold a research-based master's degree from the Hong Kong University of Science and Technology.
I'm currently working on Large Language Models and AI agents, and I write about these topics on this blog.
Experience
Weco AI
Co-founder & CTO
University College London
PhD in Computer Science
Allen Institute for AI
Research Intern, July-November 2021
Facebook AI Research
Research Intern, February-September 2019
Hong Kong University of Science and Technology
MPhil in Computer Science and Engineering
Tencent, WeChat Group
Research Intern, March-November 2017
Sun Yat-Sen University
BSc in Computer Science and Technology
Microsoft Research Asia
Research Intern, December 2014-July 2015
Publications
Aide: AI-driven Exploration in the Space of Code
Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko, Yuxiang Wu
arXiv 2025 paper
Analysing the Impact of Sequence Composition on Language Model Pre-training
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Miłoś, Yuxiang Wu, Pasquale Minervini
ACL 2024 paper
Using Natural Language Explanations to Improve Robustness of In-context Learning
Xuanli He, Yuxiang Wu, Oana-Maria Camburu, Pasquale Minervini, Pontus Stenetorp
ACL 2024 paper
G3Detector: General GPT-Generated Text Detector
Haolan Zhan, Xuanli He, Qiongkai Xu, Yuxiang Wu, Pontus Stenetorp
arXiv 2023 paper
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks
Yuxiang Wu, Yu Zhao, Baotian Hu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel
ACL 2022 paper
Towards Fine-grained Causal Reasoning and QA
Linyi Yang, Zhen Wang, Yuxiang Wu, Jie Yang, Yue Zhang
arXiv 2022 paper
Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets
Yuxiang Wu, Matt Gardner, Pontus Stenetorp, Pradeep Dasigi
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints
Yuxiang Wu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them
Patrick Lewis, Yuxiang Wu, Linqing Liu, Pasquale Minervini, Heinrich Küttler, Aleksandra Piktus, Pontus Stenetorp, Sebastian Riedel
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, et al.
NeurIPS 2020
Don't Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering
Yuxiang Wu, Sebastian Riedel, Pasquale Minervini, Pontus Stenetorp
How Context Affects Language Models' Factual Predictions
Fabio Petroni, Patrick Lewis, Aleksandra Piktus, Tim Rocktäschel, Yuxiang Wu, Alexander H Miller, Sebastian Riedel
Language Models as Knowledge Bases?
Fabio Petroni, Tim Rocktäschel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander H Miller, Sebastian Riedel
Learning to Extract Coherent Summary via Deep Reinforcement Learning
Yuxiang Wu, Baotian Hu
AAAI 2018 paper
End-to-end Adversarial Memory Network for Cross-domain Sentiment Classification
Zheng Li, Yu Zhang, Ying Wei, Yuxiang Wu, Qiang Yang
IJCAI 2017