Yishu Miao

I'm the Founder & CEO of MO Intelligence.

I did my PhD with Prof. Phil Blunsom in the Machine Learning & NLP research group at University of Oxford.

During my PhD, I have been working on deep generative models, neural variational inference and the corresponding applications for NLP. Recently, I'm focusing on natural language grounding and machine learning in robotics.

Prior to Oxford, I did my master on Data Mining, working with Prof. Chunping Li at Tsinghua University.


Email: mail [-at-] ymiao.me

Work Experiences:

Research Intern at DeepMind. Mar - Aug, 2017

Research Intern at DeepMind. May - Oct, 2016

Professional Activities:

Workshop Organization: Learning to Generate Natural Language (LGNL) at Sydney Australia, ICML 2017.

Program Committee Member:

ICML 2020/2019/2018, NIPS 2019/2018/2017, ACL 2020/2019/2018/2017/2016, ICLR 2018/2017, EMNLP 2019/2018/2017/2016

Selected Publications:

TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts

Ziyang Hong, Yvan Petillot, David Lane, Yishu Miao, Sen Wang. ICCV 2019.

"Read scene texts in the wild for visual place recognition"

Selective Sensor Fusion for Neural Visual Inertial Odometry

Changhao Chen‚ Stefano Rosa‚ Yishu Miao‚ Chris Xiaoxuan Lu‚ Wei Wu‚ Andrew Markham and Niki Trigoni. CVPR 2019.

"Neural VIO with discrete latent variables"

MotionTransformer: Transferring Neural Inertial Tracking Between Domains

Changhao Chen, Yishu Miao, Chris Xiaoxuan Lu, Linhai Xie, Phil Blunsom, Andrew Markham, Niki Trigoni. AAAI 2019.

"Generative Adversarial Networks for domain transformation"

Learning with Stochastic Guidance for Navigation

Linhai Xie, Yishu Miao, Sen Wang, Phil Blunsom, Zhihua Wang, Changhao Chen, Andrew Markham, Niki Trigoni. NIPS workshop 2018.

"Efficient and effective way for training DDPG"

Neural Allocentric Intuitive Physics Prediction from Real Videos

Zhihua Wang, Stefano Rosa, Yishu Miao, Zihang Lai, Linhai Xie, Andrew Markham, Niki Trigoni. NIPS workshop 2018.

"Intuitive Physics from video inputs"

Memory Architectures in Recurrent Neural Network Language Models.

Dani Yogatama, Yishu Miao, Gabor Melis, Wang Ling, Adhiguna Kuncoro, Chris Dyer and Phil Blunsom. ICLR 2018.

"Language model with stacks"

Discovering Discrete Latent Topics with Neural Variational Inference.

Yishu Miao‚ Edward Grefenstette and Phil Blunsom. ICML 2017.


"Neural interpretation of Bayesian non-parametrics"

Latent Intention Dialogue Models.

Tsung−Hsien Wen*Yishu Miao*‚ Phil Blunsom and Steve J. Young (*equal contribution). ICML 2017.

"Neural dialogue model with discrete latent variable for capturing intention"

Tag−Aware Personalized Recommendation Using a Hybrid Deep Model.

Zhenghua Xu‚ Thomas Lukasiewicz‚ Cheng Chen‚ Yishu Miao and Xiangwu Meng. IJCAI 2017.

"Deep Recommendation system with reconstruction learning signal"

"Discrete variational auto-encoder for text sequence"

Neural Variational Inference for Text Processing.

Yishu Miao, Lei Yu and Phil Blunsom. ICML 2016.

"Variational auto-encoder as neural topic model",

Default NTM algorithm on Amazon Sagemaker.

Tag−Aware Personalized Recommendation Using a Deep−Semantic Similarity Model with Negative Sampling.

Zhenghua Xu‚ Cheng Chen‚ Thomas Lukasiewicz‚ Yishu Miao and Xiangwu Meng. CIKM 2016.

"Deep neural model for recommendation system"

Bayesian Optimisation for Machine Translation.

Yishu Miao‚ Ziyu Wang and Phil Blunsom. Bayesian Optimisation Workshop‚ NIPS 2014.


"BO for statistical machine translation system"

Context−aware Reasoning Middleware Applied in the Mobile Environment.

Jian Wu‚ Chunping Li‚ Yishu Miao‚ Shaoxu Song‚ Li Li and Qiang Ding. ICMLC 2013.

Research on Mining Common Concern via Infinite Topic Modelling

Yishu Miao‚ Chunping Li‚ Qiang Ding and Li Li. ODMWI workshop‚ WI/IAT 2012.

Infinite Topic Modelling for Trend Tracking.

Yishu Miao‚ Chunping Li‚ Hui Wang and Lu Zhang. KDIR 2012.