I am a research scientist in Sakana AI. Before that, I was a research scientist in Google DeepMind (formerly Google Brain) based in Tokyo, after I had obtained my PhD in Computer Science at Stony Brook University in May 2019 advised by Prof. Steven Skiena. and my B.S. in Computer Science and Technology at Fudan University in 2014 advised by Prof. Yanghua Xiao.

My research interests lie in generative models and representation learning, as well as their applications in image generation, natural language processing, knowledge base modeling, social network modeling, bioinformatics, and much more. Recently I particularly focus on the interdisciplinary research of creativity / humanities research and machine intelligence such as using either non-differentiable evolution strategies or differentiable operations.

Please also see my Research Statment (PDF), my Curriculum Vitae (PDF) and my Google Scholar page for details of my research.

In Google I am honored to work with my wonderful teammates Yujin Tang, Bert Chan, Tarin Clanuwat et. al. Their works can be found in respective websites.

Timeline Google DeepMind (formerly Google Brain) in Tokyo: July 2022 - Now -- Research Scientist July 2019 - July 2022 -- Research Software Engineer Research on generative models, computational creativity and more. Aug 2014 - May 2019 Stony Brook University: PhD in Computer Science Advised by Prof. Steven Skiena. Summer 2018 Magenta, Google Brain: Intern Research on the latent space of generative models Summer 2017 Facebook SearchNLP: Intern Researches on Web Query Parsing and Natural Language Interface to Database System, both with Haixun Wang Summer and Fall 2016 Google Brain: Intern Research on representation learning with Stephan Gouws Summer 2015 Google: Intern Profiling and analysis for user-generated activity with Xiaomeng Ban Aug 2010 - Jun 2014 Fudan University: B.Sc. Advised by Prof. Yanghua Xiao. Feb. 2013 - Dec. 2013 Microsoft Research Asia: Intern Learning semantic vector representation from large knowledge base with Haixun Wang
Concept level semantic analysis with Zhongyuan Wang
Public Talks May 2023 Talk at MIT CSAIL - HCI Seminar [recording] [slides] Feb 2023 Tutorial on The 6th Workshop of Artificial Life Japan in Tsukuba University [Youtube recording] Jan 2022 Talk on Yanai Initiative Seminar, The Haruki Murakami Library, Waseda University Jan 2022 Talk on Artificial Intelligence Seminar, ISI, University of Southern California Dec 2021 Talk on 95th ARC Seminar, Ritsumeikan University Aug 2020 Talk on 12th CODH Seminar, CODH, ROIS Publications / Working Papers Evolving Collective AI: Beyond Individual Optimization
Ryosuke Takata, Yujin Tang, Yingtao Tian, Norihiro Maruyama, Hiroki Kojima, Takashi Ikegami [paper]
Working paper
Position Paper: Leveraging Foundational Models for Black-Box Optimization: Benefits, Challenges, and Future Directions
Xingyou Song, Yingtao Tian, Robert Tjarko Lange, Chansoo Lee, Yujin Tang, Yutian Chen [paper]
Accepted to International Conference on Machine Learning (ICML) 2024
DiffCJK: Conditional Diffusion Model for High-Quality and Wide-coverage CJK Character Generation
Yingtao Tian [paper]
In the Proceedings of the 15th International Conference on Computational Creativity, ICCC'24. Oral Presentation.
Shaping Realities: Enhancing 3D Generative AI with Fabrication Constraints
Faraz Faruqi, Yingtao Tian, Vrushank Phadnis, Varun Jampani, Stefanie Mueller [paper]
GenAICHI 2024: Generative AI and HCI at CHI 2024
Evolution Transformer: In-Context Evolutionary Optimization
Robert Tjarko Lange, Yingtao Tian, Yujin Tang [paper]
The Genetic and Evolutionary Computation Conference (GECCO) 2024
Large Language Models As Evolution Strategies
Robert Tjarko Lange, Yingtao Tian, Yujin Tang [paper] [paper (ACM DL)]
The Genetic and Evolutionary Computation Conference (GECCO) 2024
MingOfficial: A Ming Official Career Dataset and a Historical Context-Aware Representation Learning Framework
You-Jun Chen, Hsin-Yi Hsieh, Yu Tung Lin, Yingtao Tian, Bert Chan, Yu-Sin Liu, Yi-Hsuan Lin, Richard Tzong-Han Tsai [paper] [bib]
The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
NeuroEvoBench: Benchmarking Neuroevolution for Large-Scale Machine Learning Applications
Robert Tjarko Lange, Yujin Tang, Yingtao Tian [paper]
Thirty-seventh Conference on Neural Information Processing (NeurIPS 2023) Systems Datasets and Benchmarks Track
Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones
Asanobu Kitamoto, Jared Hwang, Bastien Vuillod, Lucas Gautier, Yingtao Tian, Tarin Clanuwat [paper] [dataset]
Thirty-seventh Conference on Neural Information Processing (NeurIPS 2023) Systems Datasets and Benchmarks Track
Evolving Collective AI: Simulation of Ants Communicating via Chemicals
Ryosuke Takata, Yujin Tang, Yingtao Tian, Norihiro Maruyama, Hiroki Kojima, Takashi Ikegami [paper]
The 2023 Conference on Artificial Life
Evolving Three Dimension (3D) Abstract Art: Fitting Concepts by Language
Yingtao Tian [paper] [supplimentary] [colab notebook]
Working paper
DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards
Shanchuan Wan, Yujin Tang, Yingtao Tian, Tomoyuki Kaneko [paper]
In the Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI-23
Simultaneous Multiple-Prompt Guided Generation Using Differentiable Optimal Transport
Yingtao Tian, Marco Cuturi, David Ha [paper]
In the Proceedings of the 13th International Conference on Computational Creativity, ICCC'22
EvoJAX: Hardware-Accelerated Neuroevolution
Yujin Tang, Yingtao Tian, David Ha [paper] [code]
In the Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2022.
Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein
Marco Cuturi, Laetitia Meng-Papaxanthos, Yingtao Tian, Charlotte Bunne, Geoff Davis, Olivier Teboul [paper] [code]
In submission.
Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts
Yingtao Tian, David Ha [paper] [paper (online, animated)] [Colab: Concrete Image, Abstract Concept] [repo]
The 11th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) 2022. Oral Presentation.
Machine Learning for Creativity and Design Workshop, NeurIPS 2021
Ukiyo-e Analysis and Creativity with Attribute and Geometry Annotation
Yingtao Tian, Tarin Clanuwat, Chikahiko Suzuki, Asanobu Kitamoto [paper] [dataset] [project]
In the Proceedings of the 12th International Conference on Computational Creativity, ICCC'21
KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
Yingtao Tian, Chikahiko Suzuki, Tarin Clanuwat, Mikel Bober-Irizar, Alex Lamb, Asanobu Kitamoto [paper] [dataset] [project]
In the Proceedings of the 11th International Conference on Computational Creativity, ICCC'20
A Natural Language Interface for Database: Achieving Transfer-learnability Using Adversarial Method for Question Understanding
Wenlu Wang, Yingtao Tian, Haixun Wang, Wei-Shinn Ku [paper]
In the Proceedings of the IEEE International Conference on Data Engineering (ICDE) 2020
Learning to Represent Bilingual Dictionaries
Muhao Chen*, Yingtao Tian*, Haochen Chen, Kai-Wei Chang, Steven Skiena, Carlo Zaniolo (* Equal Contribution) [paper]
In the Proceedings of the SIGNLL Conference on Computational Natural Language Learning (CoNLL) 2019
SpatialNLI: A Spatial Domain Natural Language Interface to Databases Using Spatial Comprehension
Jingjing Li, Wenlu Wang, Wei-Shinn Ku, Yingtao Tian and Haixun Wang [paper]
In the Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2019
Fast and Accurate Network Embeddings via Very Sparse Random Projection
Haochen Chen, Syed Fahad Sultan, Yingtao Tian, Muhao Chen and Steven Skiena [paper]
In the Proceedings of the International Conference on Information and Knowledge Management (CIKM) 2019
Learning Bilingual Embeddings Using Lexical Definitions
Weijia Shi, Muhao Chen, Yingtao Tian, Kai-Wei Chang [paper]
In the Proceedings of the 4th ACL Workshop on Representation Learning for NLP (RepL4NLP) 2019
Social Relation Inference via Label Propagation
Yingtao Tian, Haochen Chen, Bryan Perozzi, Muhao Chen, Xiaofei Sun, Steven Skiena [paper]
In the proceeding of the 41st European Conference on Information Retrieval (ECIR 2019)
Enhanced Network Embeddings via Exploiting Edge Attributes
Haochen Chen, Xiaofei Sun, Yingtao Tian, Muhao Chen, Bryan Perozzi and Steven Skiena [paper]
In Proceedings of the International Conference on Information and Knowledge Management (CIKM) 2018
DeepAnnotator: Genome Annotation with Deep Learning
Mohammad Ruhul Amin, Alisa Yurovsky, Yingtao Tian, Steven Skiena [paper]
In Proceedings of the 9th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB), 2018.
Simple Neologism Based Domain Independent Models to Predict Year of Authorship
Vivek Kulkarni, Yingtao Tian , Parth Dandiwala, Steven Skiena [paper]
In Proceedings of the 27th International Conference on Computational Linguistics (COLING), 2018.
Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment
Muhao Chen, Yingtao Tian , Kai-Wei Chang, Steven Skiena, Carlo Zaniolo [paper]
In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018.
Syntax-Directed Variational Autoencoder for Structured Data
Hanjun Dai*, Yingtao Tian * , Bo Dai, Steven Skiena, Le Song (* Equal Contribution) [paper]
In Proceedings of the International Conference on Learning Representations (ICLR), 2018.
Best paper award, NIPS 2017 workshop for Machine Learning for Molecules and Materials.
Embedding-based Relation Prediction for Ontology Population
Muhao Chen, Yingtao Tian, Xuelu Chen, Zijun Xue, Carlo Zaniolo [paper]
In Proceedings of the 17th SIAM International Conference on Data Mining (SDM), SIAM 2018.
Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
Yanghua Jin, Jiakai Zhang, Minjun Li, Yingtao Tian, Huachun Zhu, Zhihao Fang [paper] [web demo]
Accepted and presented in spotlight, NIPS 2017 workshop for Machine Learning for Creativity and Design.
Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
Muhao Chen, Yingtao Tian, Mohan Yang, Carlo Zaniolo [paper] [code] [data]
In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), IJCAI/AAAI Press 2017.
Online Showcase Previously, I have made some interesting things in the show case that can be accessible from the web. * means joint work with friends. As I am not anymore working on these projects, these links are for archival purpose only. Deep GAN (Generative Adversarial Network) in Browser: A deep GAN that generates (or dreams) images completely in browser . Pre-trained high resolution realistic image generators now run on web browser that supports WebGL, with the help of web-runnable TensorFlow.js model. * Crypko: Next generation crypko-collectibles powered by deep generative models and consensus-based smart contracts from blockchain that attracts attention from both machine learning and blockchain communities. * MakeGirlsMoe: High-quality Anime Characters Generation with Generative Adversarial Networks in Browser that attracts both community and academic attention. Professional Services Organizers NeurIPS 2022, 2023 Workshop on Machine Learning for Creativity and Design Meta-Reviewer AAAI Reviewer ICML, ICLR, NeurIPS, AAAI, IJCAI, LREC, COLING Patents US20210398336A1 Method for generating image, image generator, and program US10810493B1 Training and/or utilizing recurrent neural network model to determine subsequent source(s) for electronic resource interaction WO2022066156A1 Node embedding via hash-based projection of transformed personalized pagerank (Old) Awards in Competitive Programming 27th place 35th Annual World Final of the ACM-ICPC 2011 Gold Medal ACM-ICPC Asia Chengdu Regional Contest 2011 Championship and Gold medal ACM-ICPC Asia Amritapri Regional Contest 2010