Ryan Yen

HCI Researcher / Entrepreneur / Developer
Human-AI Interactions/ Community-Centered AI/ Computational Theory Systems
Profile Picture

I am currently a Human-AI Researcher. In the past, I was a full-stack developer, and I aspire to become an entrepreneur in the future. My present research interest are human/community-AI interaction. Specifically, Designing interactive visualization systems that enhance AI's transparency and controllability for programmers; and Developing social computing systems that can derive insights to lay the groundwork for fostering the programmers-AI community.

I am pursuing my Thesis-based Master's in Computer Science at the University of Waterloo, mentored by Dr. Jian Zhao of the WatVis Lab at UWaterloo. In the past, I was guided by Dr. Zhicong Lu from DEER Lab and Dr. Can Liu of the ERFI Lab at CityU HK. After obtaining my Master's, I will pursue my PhD at MIT CSAIL under the supervision of Dr. Arvind Satyanarayan to continue my research in HAI.

Current State

I am going to present my LBW and Paper at CHI24 & I have accepted my offer from MIT CSAIL for my PhD.

  • Research Interest
    HAI/ Community-Centred AI/ Cogntive Engineering
  • Hobbies Violin/ Swimming/ Board Game

Latest News

1 Paper + 1LBW at CHI24! 🌺🏄 2024-02-06

We explored the workflow of collaborative natural language programming and designed a system to support prompt sharing and referring.

Paper Accepted by CUI! 🔤🇳🇱2023-02-26

This work explores literature from Cognitive Science to synthesize relevant theories and findings for the HCI audience to reference. Thanks to wonderful supervisor Can Liu and co-authors, Brinda Mehra and Kejia Shen.

Paper Accepted by CHI! ⛵️🇩🇪2023-01-16

I'm coming to the CHI23 conference at Hamburg, German in 2023. I will present my work on the collaboration between human and code generation models. I will also present my work on moderating online social media and fostering the sense of community.

Paper Accepted by CSCW23! 👬2023-01-07

Wizundry is a WoZ platform that allows multiple Wizards to collaboratively operate a speech-to-text based system remotely. Our findings reveal the promises and challenges of the multi-Wizard approach and open up new research questions.

Publications

Upcomming

Paper Image Preview

Reifying the Reuse of User-AI Conversational Memories [pdf] [doi] [video]

Ryan Yen, Jian Zhao

To support users in recalling and reusing relevant user-AI conversational memories, we introduce Memolet, an interactive object that reifies memory reuse. Users can directly manipulate Memolet to specify which memories to reuse and how to use them. We developed a system demonstrating Memolet's interaction across various memory reuse stages.

Memory Management Knowledge Reuse Conversational Agent Human-AI System

CHI24 LBW

Paper Image Preview

To Search or To Gen? Exploring the Synergy between Generative AI and Web Search in Programming [pdf] [doi] [video]

Ryan Yen, Nicole Sultanum, Jian Zhao

We have identified three major challenges and proposed three decision-making stages, each with its own relevant factors. Additionally, we present a thorough process model that captures programmers' interaction patterns.

LLM Information Seeking Programmer Human-AI Framework

CHI 2024

Paper Image Preview

CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming [pdf] [doi] [video]

Ryan Yen*, My girlfriend 😚Felicia Feng*, Yuzhe You, Mingming Fan, Jian Zhao, Zhicong Lu *These authors contributed equally to this work.

A system to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. It assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs.

LLM Collaborative Programming NL Programming Human-AI Visual Interface

Arxiv Preprint

Paper Image Preview

CoLadder: Supporting Programmers with Hierarchical Code Generation in Multi-Level Abstraction [pdf] [doi] [video]

Ryan Yen, Jiawen Zhu, Sangho Suh, Haijun Xia, Jian Zhao

A system that assists programmers by enabling hierarchical task decomposition, incremental code generation, and verification of results during prompt authoring. Bridging the abstraction gap between programmers and LLMs.

LLM Abstraction Gap Programmer Human-AI Visual Interface

CHI 2023

Paper Image Preview

StoryChat: Designing a Narrative-Based Viewer Participation Tool for Live Streaming Chatrooms [pdf] [doi] [video]

Ryan Yen, My girlfriend 😚Felicia Feng, Brinda Mehra, Ching Christie Pang, Siying Hu, Zhicong Lu

A narrative-based viewer participation tool that utilizes a dynamic graphical plot to reflect chatroom negativity. We discovered that StoryChat encouraged viewers to contribute prosocial comments, increased viewer engagement, and fostered viewers' sense of community.

Social Media Viewer Participation Narrative Online Community CHI23 System + Emperical Study

CUI 2023

Paper Image Preview

Gist and Verbatim: Understanding Speech to Inform New Interfaces for Verbal Text Composition [pdf] [doi] [video]

Brinda Mehra, Kejia Shen, Ryan Yen, Can Liu

Exploring speech input in HCI, we address editing challenges. Our study combines Cognitive Science with HCI, revealing memory patterns and proposing new interaction concepts for efficient speech editing.


Memory System Understanding Speech Input CUI23 Emperical Study

CSCW 2023

Paper Image Preview

Wizundry: A Cooperative Wizard of Oz Platform for Simulating Future Speech-based Interfaces with Multiple Wizards [pdf] [doi] [video]

Siying Hu, Ryan Yen, Ziwei Yu, Mingjian Zhao, Katie Seaborn, Can Liu

A real-time, web-based WoZ platform that allows multiple Wizards to collaboratively operate a speech-to-text based system remotely. Our findings reveal the promises and challenges of the multi-Wizard approach and open up new research questions.

WizardOfOz System Wizard-AI Interaction HAI CSCW23 Workflow

Working Experience (full-time)

AI Research Intern

May 2021 - Jan 2022

Huawei Research Centre

  • Lung Cancer Detection, CV, AI Explainability in pathology diagnosis
  • MindSpore Pathology Diagnosis AI Challenge organizer
  • Online AI training, testing and evaluation platform
  • Speaker of Training AI Model on Huawei Cloud ModelArts AI Platform
  • Opening Speaker of Huawei AI challenge
  • Invited guest to Huawei Cloud Summit 2021
  • Computer Vision Deep Learning Explainable AI Full-Stack Development
Applied Research Computer Vision Cancer Detection Explainable AI Full-Stack

CTO, Co-Founder

Oct 2021 - April 2021

Nérocean

We have developed a patented sensor for measuring dissolved oxygen in the ocean and used its fast and real-time nature to build AI network, which is dedicated to monitoring water quality in real time and predicting the health of the ocean within three months.

  • Ocean water sensor & Dissolved Oxygen prediction AI model
  • Deep-Learning based real-time classifier for ocean water quaity prediction
  • Funding from HK Government
  • Funding from Hong Kong Science Park
  • Funding from HKTech300, CityU
  • Startup Deep Learning Full-Stack

    Full-Stack Intern

    Sep 2020 - May 2021

    Networld Tech Ltd.

    I am part of a new team at Networld, nearD, a social networking site with a focus on privacy, multi-identity, and locality.

  • Cross-platform user interface, data visualization in nearD admin panel
  • Several Campaign Websites built with Leveral and React
  • Docker, K8s containerized and auto deployment to Google Cloud
  • Server side network and API management and scaling
  • CI/CD and two-step authorization on IP network restriction
  • Full-Stack Container Database Cloud Laravel

    Education

    Research-based Master Degree

    Jan 2023 - Present

    University of Waterloo

    David R. Cheriton School of Computer Science

    • UW Grad Scholarship
    • International Masters Award Excellence Scholarship
    • Graduate Research Studentship Scholarship
    • TA Funding
    • Research Assistant in WatVis Lab

    Visting Student

    June 2021 - Aug 2021

    Stanford University

    Department of Statistics

    • HKSAR Government Reaching Out Awards Funding
    • CGPA 4.0/4.0

    Bachelor Degree

    Sep 2018 - June 2022

    City University of Hong Kong

    Department of Computer Science

    • Vice President of Computer Science Student Chapter
    • 4 years Full CityU International Student Scholarship
    • Awarded Dean's List
    • HKSAR Government Scholarship Fund
    • HK STEM Internship Scholarship
    • Department Overseas Learning Funding
    • English Proficiency Scholarship
    • Departmental Research Funding
    • Research Assistant in DEER Lab
    • Research Assistant in ERFI Lab
    • Research Assistant in MEI Lab

    Communities & Events & Volunteers

    Lead

    • Google Developers Student Club
    • CityU CS Student Chapter
    • Microsoft Learn Ambassador
    • AWS Educate Ambassador
    • IEEE Student Chapter
    • CityU IT Team

    Organizer

    • AWS Cloud AI workshop 2021
    • CityU IT Team Tech seminars
    • CityHack 2018-21
    • MindSpore AI Challenge 2021
    • CityU AWSome Day 2020-21
    • Google Cloud Summit 2021
    • Google I/O Extend 2021
    • Python Workshop Series 2019

    Volunteer

    • Stage actor - Mikado Children Theatre
    • Hospital Violinist (Taipei)
    • International Educational Volunteer (Thailand)

    Papers that Inspired my Thinking

    I love to read therotical papers about interface design and HCI design principles.

    Reification, Polymorphism and Reuse

    Michel Beaudouin-Lafon & Wendy E. Mackay - 2000

    Reification turns concepts into first class objects, polymorphism permits commands to be applied to objects of different types, and reuse makes both user input and system output accessible for later use.

    Demonstrational Interfaces

    B.A. Myers - 1992

    Demonstrational interfaces, interfaces that let the user perform actions on concrete example objects while constructing an abstract program, thus letting the user create parameterized procedures and objects without learning a programming language, are discussed.

    Cognitive Engineering

    Donald A. Norman - 1986

    The seven-stage interaction model consists of (1) Establishing the Goal, (2) Forming the Intention, (3) Specifying the Action Sequence, (4) Executing the Action on the System's Interface, (5) Perceiving the System's State as a Response to the Action, (6) Interpreting the State, and (7) Evaluating the System State with respect to the Goals and Iterating until the goal is achieved.

    Designing Interaction, not Interfaces

    Michel Beaudouin-Lafon - 2004

    The paper argues for a shift from interface design to interaction design as the means to significantly enhance user interfaces. It calls for the development of powerful interaction models, a better understanding of sensory-motor aspects, and novel interaction architectures addressing key challenges like reinterpretability, resilience, and scalability.

    Instrumental Interaction

    Michel Beaudouin-Lafon - 2000

    Instrumental Interaction describes graphical user interfaces in terms of domain objects and interaction instruments. Interaction between users and domain objects is mediated by interaction instruments, similar to the tools and instruments we use in the real world to interact with physical objects.

    Direct Manipulation Interfaces

    Edwin L. Hutchins, James D. Hollan & Donald A. Norman - 1985

    Direct manipulation has been lauded as a good form of interface design, and some interfaces that have this property have been well received by users. This article delves into the cognitive aspects of direct manipulation interfaces, examining both their advantages and disadvantages.

    Thinking with External Representations

    David Kirsh - 2010

    Why do people create extra representations to help them make sense of situations, diagrams, illustrations, instructions and problems? The obvious explanation—external representations save internal memory and computation—is only part of the story.

    Ultra-Lightweight Constraints

    Scott E. Hudson & Ian Smith - 1996

    Layout constraints in a user interface toolkit provide a declarative mechanism for controlling the size and position of objects in an interactive display, along with an efficient update mechanism for maintaining display layouts automatically in the face of dynamic changes.

    What Is Interaction?

    Kasper Hornbæk, Antti Oulasvirta - 2017

    This paper explore the concept of "interaction" that lack of clear definitions in the field. It identifies various existing concepts, such as interaction as dialogue, transmission, optimal behavior, embodiment, and tool use. These concepts vary in scope and their understanding of the causal relationships between humans and computers.