Qi Liu

Qi Liu

Assistant Professor at the University of Hong Kong

The University of Hong Kong

Biography

I am an assistant professor at the Department of Computer Science, the University of Hong Kong, and a cofounder of Reka. I earned my Ph.D. in computer science from the University of Oxford. In the past, I obtained a Master of Science degree from the National University of Singapore, and a Bachelor of Engineering degree from Shandong University. My research interests include natural language processing and machine learning. I also spent some time at Google DeepMind, Facebook AI Research, and Microsoft Research before and during my PhD study.

I have multiple fully-funded PhD, MPhil, postdoc, RA, and intern positions available at the University of Hong Kong. Email me for more information.

Reka is hiring for platform and machine learning. Email us for more information. We are committed to the development of multimodal foundation models.

Interests
  • Natural Language Processing
  • Machine Learning
  • Artificial Intelligence
Education
  • Ph.D. in Artificial Intelligence

    University of Oxford, Advisors: Phil Blunsom, Matt Kusner

  • M.Sc in Computer Science

    National University of Singapore, Advisor: Anthony K.H. Tung

  • BEng in Computer Science

    Shandong University

Experiences

 
 
 
 
 
Google DeepMind
Research Scientist Intern
Google DeepMind
Jul 2020 – Jun 2021 London
Advisors: Phil Blunsom, Dani Yogatama, Lei Yu, Laura Rimell
 
 
 
 
 
Facebook AI Research
Researcher
Facebook AI Research
Aug 2018 – Aug 2019 New York City
Advisors: Douwe Kiela, Maximilian Nickel
 
 
 
 
 
Microsoft Research
Research Intern
Microsoft Research
Mar 2018 – Jun 2018 Cambridge
Advisors: Alexander Gaunt, Marc Brockschmidt, Miltos Allamanis
 
 
 
 
 
SUTD
Research Assistant
SUTD
Feb 2017 – Feb 2018 Singapore
Advisor: Yue Zhang
 
 
 
 
 
Microsoft Research
Research Intern
Microsoft Research
Sep 2016 – Dec 2016 Beijing
Advisors: Ying Yan, Thomas Moscibroda

Selected Awards

AMiner AI Most Influential Scholar
Google DeepMind Scholarship
Lee Kuan Yew Global Business Plan Competition Winner (3 out of 550)
NUS Research Scholarship

Publications

Quickly discover relevant content by filtering publications.
(2023). M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. In arXiv.

PDF

(2023). GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning. In bioRxiv.

PDF

(2023). Can Language Models Understand Physical Concepts?. In arXiv.

PDF

(2023). Large Language Models are not Fair Evaluators. In arXiv.

PDF

(2023). TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models. In arXiv.

PDF

(2023). Retrieved Sequence Augmentation for Protein Representation Learning. In bioRxiv.

PDF

(2022). Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play. In EMNLP Findings.

PDF Code

(2022). Causal Machine Learning: A Survey and Open Problems. In arXiv.

PDF

(2022). Evaluating Self-Supervised Learning for Molecular Graph Embeddings. In arXiv.

PDF

(2022). Augmenting Message Passing by Retrieving Similar Graphs. In arXiv.

PDF

(2022). Relational Memory Augmented Language Models. In TACL.

PDF

(2022). Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction. In PAMI.

PDF

(2021). Causal Effect Inference for Structured Treatments. In NeurIPS.

PDF Code

(2021). Unsupervised Point Cloud Pre-Training via View-Point Occlusion Completion. In ICCV.

PDF Code

(2021). Pretraining the Noisy Channel Model for Task-Oriented Dialogue. In TACL.

PDF

(2021). Counterfactual Data Augmentation for Neural Machine Translation. In NAACL.

PDF

(2021). Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition. In NAACL Short Paper.

PDF

(2020). A Survey on Contextual Embeddings. In arXiv.

PDF

(2020). Smart Contract Vulnerability Detection using Graph Neural Network. In IJCAI.

PDF

(2020). Multi-Task Self-Supervised Learning for Disfluency Detection. In AAAI.

PDF

(2019). Hyperbolic Graph Neural Networks. In NeurIPS.

PDF Code

(2019). Quaternion Knowledge Graph Embedding. In NeurIPS.

PDF Code

(2019). Insertion-based Decoding with Automatically Inferred Generation Order. In TACL.

PDF

(2019). Towards Natural and Accurate Future Motion Prediction of Humans and Animals. In CVPR.

PDF Code

(2018). Constrained Graph Variational Autoencoders for Molecule Design. In NeurIPS.

PDF Code

(2018). Sentence-State LSTM for Text Representation. In ACL.

PDF Code

(2018). Mining Evidences for Concept Stock Recommendation. In NAACL.

PDF Code

(2018). Multi-modal Multi-task Learning for Automatic Dietary Assessment. In AAAI.

PDF

(2017). QALink: Enrich Text Documents with Relevant Q&A Site Contents. In CIKM.

PDF

(2017). EtherQL: A Query Layer for Blockchain. In DASFAA.

PDF Code

(2017). Towards Personalized Activity Level Prediction in Community Question Answering Websites. In TOMM.

PDF

(2017). Behavior Pattern Clustering in Blockchain Networks. In MTAP.

PDF

(2016). Fusion of Magnetic and Visual Sensors for Indoor Localization: Infrastructure-free and More Effective. In TMM.

PDF

(2016). I Ate This: A Photo-based Food Journaling System with Expert Feedback. In SIGCHI Workshop.

PDF

(2015). DocRicher: An Automatic Annotation System for Text Documents Using Social Media. In SIGMOD Demo Track.

PDF