“How small a thought it takes to fill a whole life!” — Ludwig Wittgenstein

Research Interests

My current research interests lie in the field of Artificial Intelligence, including Reinforcement Learning, Deep Learning and Neuro-Inspired Machine Learning, Bayesian Inference and Graphical Models, Game Theory and Multi-Agent Systems, as well as their application in Dialogue Systems, Linguistics, Robotics and Scientific Discoveries — especially Neuroscience.


September 2018 - Present
Research Assistant @ Seung Lab, Princeton University.
Mentored by Prof. Sebastian Seung on Computational Neuroscience and Machine Learning.

September 2018 - Present
Research Assistant @ Princeton NLP Group, Princeton University.
Mentored by Prof. Karthik Narasimhan on Natural Language Processing and Reinforcement Learning.

June 2017 - Feburary 2018
Research Intern @ Institute for Computational Sustainability, Cornell University.
Mentored by Prof. Carla Gomes on Artificial Intelligence and Computational Sustainability.
Collaborators: Prof. Yexiang Xue, Junwen Bai, Brendan Rappazzo, Guillaume Perez

July 2016 – June 2018
Undergraduate Researcher @ SJTU Speech Lab, Shanghai Jiao Tong University.
Mentored by Prof. Kai Yu on Spoken Dialogue System.
Collaborators: Lu Chen, Cheng Chang, Xiang Zhou, Zihao Ye

August 2016 – June 2017
Member of ZIRC Program @ Laboratory of Quantum Technology (QUTEC).
Collaborated on Interdisciplinary Research Project of Photonic Boson Sampling.

I was fortunate to join many collaborative research projects during my undergraduate. For instance, our project “Urban Air Policy Evaluation via Spatio-Temporal Data Analysis” with Yiyi Zhang (Research Intern at MSRA Urban Computing Group) and Bicheng Gao won the first prize in the 4th “Hsue-shen Tsien Cup” Collegiate Science and Technology Contest. I also worked part-time with AIMS Laboratory on some interesting research topics connecting Economics with Computer Science.


Machine Learning

  • [C6] A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation.
    Runzhe Yang, Xingyuan Sun and Karthik Narasimhan.
    In proceedings of the 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, December 2019.
    [ Paper | Bib | Appendix | Code | Poster ]

  • [C5] Unsupervised Learning by a “Softened” Correlation Game: Duality and Convergence.
    Runzhe Yang, with Kyle Luther and Sebastian Seung (theoretical paper, invited).
    In proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers (ACSSC 2019), Pacific Grove, USA, November 2019 .
    [ Paper | Bib ]

  • [C4] Imitation Refinement for X-Ray Diffraction Signal Processing.
    Junwen Bai, Zihang Lai, Runzhe Yang, Yexiang Xue, John Gregoire and Carla Gomes.
    In proceedings of the 2019 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019), Brighton, UK, May 2019.
    [ Paper | Bib ]

Dialogue System

  • [C3] Affordable On-line Dialogue Policy Learning.
    Runzhe Yang*, Cheng Chang* (equal authorship), Lu Chen, Xiang Zhou and Kai Yu.
    In proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Copenhagen, Denmark, September 2017.
    [ Paper | Bib | Appendix ]

  • [C2] Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning.
    Lu Chen, Xiang Zhou, Cheng Chang, Runzhe Yang and Kai Yu.
    In proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), Copenhagen, Denmark, September 2017.
    [ Paper | Bib | Appendix ]

  • [C1] On-line Dialogue Policy Learning with Companion Teaching.
    Lu Chen, Runzhe Yang, Cheng Chang, Zihao Ye, Xiang Zhou and Kai Yu.
    In proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), Valencia, Spain, April 2017.
    [ Paper | Bib | Poster ]



  • [A2] Unsupervised Feature Discovery by Neural Networks with Disynaptic Recurrent Inhibition.
    Runzhe Yang, Kyle Luther, H. Sebastian Seung
    Selected talk at the From Neuroscience to Artificially Intelligent Systems conference (NAISys 2020), Online, November 2020.
    [ Abstract | Talk ]

  • [A1] Mitochondrial Size Gradients in Cortical Neurons Suggested by 3D Electron Microscopy.
    Nicholas L. Turner, Runzhe Yang, Agata Foryciarz, Kisuk Lee, William Silversmith, William Wong, Jingpeng Wu, Sven Dorkenwald, T. L. Lewis, Yusuke Hirabayashi, Franck Polleux, Nuno da Costa, R. Clay Reid, H. Sebastian Seung
    Poster presentation at the conference of Society for Neuroscience (SfN 2018), San Diego, CA, USA, November 2018.
    [ Abstract | Poster ]



  • [M7] Modularity and Neural Coding from a Brainstem Synaptic Wiring Diagram.
    Ashwin Vishwanathan, Alexandro D. Ramirez*, Jingpeng Wu*, Alex Sood, Runzhe Yang, Nico Kemnitz, Dodam Ih, Nicholas Turner, Kisuk Lee, Ignacio Tartavull, William M. Silversmith, Chris S. Jordan, Celia David, Doug Bland, Mark S. Goldman, Emre R. F. Aksay, H. Sebastian Seung, the EyeWirers. October 2020.
    [ bioRxiv | Bib ]

  • [M6] Multiscale and Multimodal Reconstruction of Cortical Structure and Function.
    Nicholas L. Turner*, Thomas Macrina*, J. Alexander Bae*, Runzhe Yang*, Alyssa M. Wilson*, Casey Schneider-Mizell*, Kisuk Lee*, Ran Lu*, Jingpeng Wu*, Agnes L. Bodor*, Adam A. Bleckert*, Derrick Brittain*, Emmanouil Froudarakis*, Sven Dorkenwald*, Forrest Collman*, Nico Kemnitz*, Dodam Ih, William M. Silversmith, Jonathan Zung, Aleksandar Zlateski, Ignacio Tartavull, Szi-chieh Yu, Sergiy Popovych, Shang Mu, William Wong, Chris S. Jordan, Manuel Castro, JoAnn Buchanan, Daniel J. Bumbarger, Marc Takeno, Russel Torres, Gayathri Mahalingam, Leila Elabbady, Yang Li, Erick Cobos, Pengcheng Zhou, Shelby Suckow, Lynne Becker, Liam Paninski, Franck Polleux, Jacob Reimer, Andreas S. Tolias, R. Clay Reid, Nuno Maçarico da Costa, H. Sebastian Seung. October 2020.
    [ bioRxiv | Bib ]

Dialogue System

  • [M5] Generating Strategic Dialogue for Negotiation with Theory of Mind.
    Runzhe Yang*, Jingxiao Chen* and Karthik Narasimhan. October 2020.
    [ ArXiv | Bib ]

Machine Learning

  • [M4] A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation.
    Runzhe Yang, Xingyuan Sun and Karthik Narasimhan. August 2019.
    [ ArXiv | Bib | Code ]

  • [M3] Imitation Refinement.
    Runzhe Yang*, Junwen Bai* (equal authorship), Yexiang Xue, John Gregoire and Carla Gomes. May 2018.
    [ ArXiv | Bib | Code]

  • [M2] Multi-Armed Image Segmentation.
    Brendan Rappazzo, Guillaume Perez, Runzhe Yang, Olivia Graham, Drew Harvell and Carla Gomes. Feburary 2018.

Human Computing & Crowdsourcing

  • [M1] Pedagogical Value-Aligned Crowdsourcing.
    Runzhe Yang, Yexiang Xue and Carla Gomes. December 2017.
    [ Paper1 | Paper2 | Appendix | Code]


  • Deep Multi-Objective Reinforcement Learning and Its Application in Task-Oriented Dialogue Systems.
    Runzhe Yang, 2018 Excellent Bachelor Thesis of Shanghai Jiao Tong University (top 1%)
    [ Thesis | Bib | Code]