Yichen Yang

Yichen Yang

PhD student in Computer Science

MIT

About me

I am a fourth-year Computer Science PhD student at MIT, advised by Martin Rinard. My research interest lies in the intersection between programming languages and machine learning. My recent work focuses on developing neurosymbolic techniques that combine neural and probabilistic methods with program synthesis.

Prior to joining MIT, I finished my B.A. and M.Eng. in Information Engineering at University of Cambridge. In summer 2020, I interned at Google Brain on systems for ML.

Interests
  • Neurosymbolic methods
  • Programming language + machine learning
Education
  • PhD in Computer Science, 2018 -

    Massachusetts Institute of Technology

  • BA & MEng in Information Engineering, 2014 - 2018

    University of Cambridge

Publications

(2021). Program Synthesis Guided Reinforcement Learning for Partially Observed Environments. NeurIPS 2021, Spotlight presentation.

PDF Code

(2021). Equality Saturation for Tensor Graph Superoptimization. MLSys 2021.

PDF Code

(2020). Neurosymbolic Transformers for Multi-Agent Communication. NeurIPS 2020.

PDF Code

(2019). Correctness Verification of Neural Networks. NeurIPS 2019 Workshop on Machine Learning with Guarantees.

PDF Code