Yujia Li
Research Scientist
Google DeepMind
News
- Our latest large language model Gemini is released!
- Our tech report about the second version of AlphaCode is released! This model is based on Gemini and better than 85% of human competitors in competitive programming.
- Our paper on position embedding for directed graphs is published at ICML 2023.
- Our paper on optimizing sorting algorithms is published on Nature.
Publications
- [Google Scholar]
-
Gemini: A Family of Highly Capable Multimodal Models
arXiv:2312.11805, 2023
[Gemini]
-
Technical Report, 2023
-
Large Language Models as Analogical Reasoners
arXiv:2310.01714, 2023
-
Transformers Meet Directed Graphs
International Conference on Machine Learning (ICML), 2023
-
Faster sorting algorithms discovered using deep reinforcement learning
Nature, 2023
[blog]
-
Competition-Level Code Generation with AlphaCode
Science, 2022
arXiv:2203.07814, 2022
-
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
arXiv:2112.11446, 2021
[blog]
-
WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
TextGraphs-15: Graph-based Methods for Natural Language Processing (NAACL 2021 Workshop), 2021
-
ETA Prediction with Graph Neural Networks in Google Maps
The 30th ACM International Conference on Information & Knowledge Management (CIKM), 2021
-
Computer-Aided Design as Language
Neural Information Processing Systems (NeurIPS), 2021
-
Solving Mixed Integer Programs Using Neural Networks
arXiv:2012.13349, 2020
-
Strong Generalization and Efficiency in Neural Programs
arXiv:2007.03629, 2020
-
Scalable Deep Generative Modeling for Sparse Graphs
International Conference on Machine Learning (ICML), 2020
[code]
-
REGAL: Transfer Learning for Fast Optimization of Computation Graphs
International Conference on Learning Representations (ICLR), 2020
[data]
-
Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records
AAAI Conference on Artificial Intelligence (AAAI), 2020
ICML workshop on Learning and Reasoning with Graph-Structured Representations, 2019
-
Prioritized Unit Propagation with Periodic Resetting is (Almost) All You Need for Random SAT Solving
arXiv:1912.05906, 2019
-
Learning Transferable Graph Exploration
Neural Information Processing Systems (NeurIPS), 2019
-
Efficient Graph Generation with Graph Recurrent Attention Networks
Neural Information Processing Systems (NeurIPS), 2019
[code]
-
Fast Training of Sparse Graph Neural Networks on Dense Hardware
arXiv:1906.11786, 2019
-
Graph Matching Networks for Learning the Similarity of Graph Structured Objects
International Conference on Machine Learning (ICML), 2019Long Oral Presentation
-
Compositional Imitation Learning: Explaining and executing one task at a time
International Conference on Machine Learning (ICML), 2019Long Oral Presentation
A previous version appeared in the NeurIPS Learning by Instruction workshop, 2018
-
Deep Reinforcement Learing with Relational Inductive Biases
International Conference on Learning Representations (ICLR), 2019
-
Relational inductive biases, deep learning, and graph networks
arXiv:1806.01261, 2018
-
Learning Deep Generative Models of Graphs
arXiv:1803.03324, 2018
Invited to ICLR Workshop Track, 2018
[slides]
-
Learning Model-Based Planning from Scratch
arXiv:1707.06170, 2017
-
Neural Information Processing Systems (NIPS), 2017Spotlight Presentation
-
Imagination-Augmented Agents for Deep Reinforcement Learning
Neural Information Processing Systems (NIPS), 2017Oral Presentation
-
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
Neural Information Processing Systems (NIPS), 2016
-
Gated Graph Sequence Neural Networks
International Conference on Learning Representations (ICLR), 2016
-
The Variational Fair Auto Encoder
International Conference on Learning Representations (ICLR), 2016Oral Presentation
-
Generative Moment Matching Networks
International Conference on Machine Learning (ICML), 2015
[code][project page]
-
Feedback-Based Handwriting Recognition from Inertial Sensor Data for Wearable Devices
The 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015
-
NIPS workshop on Transfer and Multi-Task Learning, 2014
-
High Order Regularization for Semi-Supervised Learning of Structured Output Problems
International Conference on Machine Learning (ICML), 2014
-
ICML workshop on Learning Tractable Probabilistic Models, 2014
-
Exploring Compositional High Order Pattern Potentials for Structured Output Learning
The 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013Oral Presentation
-
Celebrity Recommendation with Collaborative Social Topic Regression
Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013
Thesis
Education / Work Experience
- 2023.5 - present Senior Staff Research Scientist, Google DeepMind.
- 2020.11 - 2023.5 Staff Research Scientist, DeepMind.
- 2018.5 - 2020.11 Senior Research Scientist, DeepMind.
- 2016.11 - 2018.5 Research Scientist, DeepMind.
- 2013.2 - 2017.2 Doctor of Philosophy, University of Toronto.
- 2015.6 - 2015.9 Research Intern, Microsoft Research Cambridge.
- 2014.6 - 2014.9 Research Intern, Microsoft Research Redmond.
- 2011.9 - 2013.1 Master of Science, University of Toronto.
- 2011.6 - 2011.8 R&D Intern, Baidu, Inc..
- 2007.8 - 2011.7 Bachelor of Engineering, Tsinghua University.
Community Service
- Area Chair: NeurIPS (2020, 2021, 2022), ICLR (2021, 2022, 2023).
- Action Editor: TMLR.
- Reviewer: NeurIPS (2015-2019), ICML (2016-2020, 2022), ICLR (2017, 2019, 2020), UAI (2015, 2016, 2018), CVPR (2017, 2019), ECCV (2016), JMLR, IJCV, TPAMI.
Teaching Experience
Courses TA'ed at University of Toronto:
- Winter 2015 CSC 412/2506Probabilistic Graphical Models
- Fall 2014 CSC 411Machine Learning and Data Mining
- Winter 2014 CSC 108Introduction to Computer Programming
- Fall 2013 CSC 263Data Structures
- Winter 2013 CSC 108Introduction to Computer Programming
- Fall 2012 CSC 411Machine Learning and Data Mining
- Winter 2012 CSC 190Computer Algorithms, Data Structures and Languages
- Fall 2011 CSC 165Mathematical Expression and Reasoning for Computer Science
Courses TA'ed at Tsinghua University:
- Spring 2011Advanced Data Structures
- Spring 2011Machine Learning and Knowledge Discovery
Honors and Awards
- 2019CVPR outstanding reviewer
- 2016ICLR travel award
- 2015Microsoft Ph.D. fellowship (US and Canada) finalist
- 2015ICML travel grant
- 2013CVPR travel grant
- 2013University of Toronto School of Graduate Studies conference grant
- 2008-2010University-wide comprehensive merit scholarship, three times - including Kai-Feng Scholarship, which is the highest amount among all scholarships and awarded to only 30 undergraduate students in Tsinghua University every year.
- 20082nd Prize - Chinese National College Physics Contest
- 20061st Prize - Chinese Physics Olympiad (CPhO) in Provinces
- 20052nd Prize - Chinese National Olympiad in Informatics in Provinces (NOIP)