Yaoyao(Freax) Qian

Yaoyao(Freax) Qian

Student

Northeastern University

About Me

Hi there 👋, I’m Yaoyao Qian (Freax Ruby) ✨

Welcome to my little corner of the internet! I’ve just wrapped up my first year of graduate school at Northeastern University. Alongside this, I’m currently a Machine Learning Engineer Co-op at Lendbuzz, where I’m applying my skills in AI to solve real-world problems in the fintech space.

In addition, I’m involved in robotics and artificial intelligence research as a Research Intern at The Helping Hands Lab, working under the guidance of Dr. Robert Platt on robotic grasping and manipulation systems. I also contribute as a Research Assistant at the CHATS Lab (Conversation, Human-AI Technology, Security) under Weiyan Shi, where we focus on interactive AI systems, privacy-preserving AI, and multi-modal conversational agents.

On the accessibility front, I collaborate with Dr. Rachel F. Adler at the Information Experience and Accessibility Lab at the University of Illinois Urbana-Champaign on projects that aim to improve accessibility in fintech and mHealth for older adults.

About Me

Before stepping into graduate school, I served as a Technical Manager at Zhejiang Chongxiao Zhong Han Medical Technology Co., where I developed tools and systems that improved operational efficiencies by up to 80%. At Wenzhou University of Technology, under the guidance of Professors Xianming Wang and Xu Xu, I focused on strategic insights for soccer teams and performed sentiment analysis on Amazon reviews. At Wenzhou Bopu Institute of Big Data, mentored by Professor Xianming Wang, I led public opinion analysis projects. I also worked with Professor Huaqing Mao at MIE DEMO Studio, where I launched an innovative volunteer management platform.

🌟🌟Feel free to reach out! Whether it’s for research, collaboration, or just to exchange ideas over a casual chat, I’m always open to connecting and exploring new possibilities!🌟🌟

News!!!!

What I’m Up To

Connect With Me

Open Source Projects and Articles

Meet My Pets

Lucas

Lucas Lucas may seem a little serious, but don’t be fooled! He’s actually quite the pampered cat and loves attention. Even with his perpetually unimpressed look, he always makes time for cuddles and affection every day.Cookie Cookie is my constant companion—she can’t stand being apart from me! With her cheerful personality and always-smiling face, she radiates happiness. It feels like Cookie is joyful every single moment, like she’s living in a world with 25 hours of happiness each day!

Thank you for visiting my page. Let’s make something great together!

Interests

  • Large Language Model
  • Robotic
  • Human–computer Interaction

Education

  • Master in Information System, 2023 - present

    Northeastern University

  • B.Eng. in Computer Science, 2016 - 2020

    Wenzhou University of Technology

Publications

ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter (CoRL 2024)

Robotic grasping in cluttered environments remains a significant challenge due to occlusions and complex object arrangements. We have …
ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter (CoRL 2024)

IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies (CoRL 2024)

Humans can imagine goal states during planning and perform actions to match those goals. In this work, we propose Imagination Policy, a …
IMAGINATION POLICY: Using Generative Point Cloud Models for Learning Manipulation Policies (CoRL 2024)

Optimal Design of Parking Lots through Mathematical Modeling: Addressing Space Constraints and Vehicle Accessibility

This paper tackles the challenge of optimizing parking lot designs amidst rapid increases in household car numbers and limited parking …
Optimal Design of Parking Lots through Mathematical Modeling: Addressing Space Constraints and Vehicle Accessibility

Optimizing Drone-Based Medical Supply Delivery in Disaster-Affected Areas: A Case Study from Puerto Rico

This paper presents an innovative approach to disaster response using drone-based systems for efficient medical supply delivery …
Optimizing Drone-Based Medical Supply Delivery in Disaster-Affected Areas: A Case Study from Puerto Rico

Analysis of football game performance based on social network

With the advent of big data and network era, the interpersonal relationship is getting closer and closer, and the advantage of teamwork …
Analysis of football game performance based on social network

Experience

 
 
 
 
 

Machine Learning Engineer Co-op

Lendbuzz

Oct 2024 – Present Boston, MA
  • Worked on integrating retrieval-augmented generation (RAG) techniques to improve chatbot capabilities and enhance user interactions.
  • Developed scalable systems for deploying machine learning models in production environments.
  • Collaborated across teams to explore AI-driven solutions for various fintech applications.
 
 
 
 
 

Research Assistant

CHATS Lab (Conversation, Human-AI Technology, Security) under Weiyan Shi

Sep 2024 – Present Northeastern University
  • Contributing to research on advanced interactive AI systems with a focus on enhancing multi-modal communication technologies.
  • Exploring innovative AI applications that aim to bridge the gap between human and AI conversational experiences.
  • Investigating privacy and security concerns in the development of AI-driven interaction models.
 
 
 
 
 

Research Assistant

the Information Experience and Accessibility Lab in the iSchool at the University of Illinois Urbana-Champaign

May 2024 – Present Champaign, IL (Remote)
  • Conducted research on FinTech for Older Adults, focusing on enhancing financial technology accessibility and usability for elderly users.
  • Investigated mHealth with Generative AI, integrating AI to enhance mobile health apps aimed at promoting physical activity and healthier lifestyles.
  • Led the development of PAT PAT – an Emotional Support Virtual Pet Application, integrating machine learning to improve user interaction and engagement.
 
 
 
 
 

Research Assistant

The Helping Hands Lab

Nov 2023 – Present Boston, MA

Keyword: Open World Manipulation With Planning, Grasping Learning, Equivariant Model

  • Equivariant Models for Robotic Grasping: Developed an advanced robotic grasping model incorporating SE(2) and safe-z prediction, reducing training epochs by 50%.

    • Implemented Equivariant DQN in CartPole, cutting training time in half, using state and image inputs.
    • Pioneered SO(2)-equivariant reinforcement learning techniques, improving grasping tasks and reducing failed attempts by 50%.
  • Vision-Language Models for Strategic Grasping: Integrated LLMs for “Open World Manipulation with Planning,” enhancing robot adaptability in dynamic environments. Developed ThinkGrasp, a vision-language grasping system utilizing GPT-4o, achieving a 98.0% success rate in cluttered scenes, outperforming previous methods by over 50%.

    • Built a robust error-handling framework with LangSAM, boosting reliability in real-world experiments.
  • Generative Models for Manipulation Policies: Contributed to the development of IMAGINATION POLICY, a generative point cloud model for key-frame manipulation, improving success rates on RLbench tasks by 20%.

    • Proposed a novel multi-task key-frame policy network, increasing generalization to unseen configurations.
 
 
 
 
 

Technical Manager

Zhejiang Chongxiao Zhong Han Medical Technology Co

May 2020 – Sep 2021 Hangzhou, China

In-service period

  • Independently developed a VC++-based Database Integration (DBI) tool for data export and import from Access to Oracle, enhancing deployment efficiency by 30%.
  • Engineered a Springboot+Vue electronic invoice management system, seamlessly integrated with the hospital system, boosting business efficiency by 80%.
  • Assembled and led a development team to create an internal management system tailored to the company’s operations; oversaw key coding, quality control, and project progression.
 
 
 
 
 

Research Assistant

Wenzhou University of Technology

Apr 2020 – May 2020 Wenzhou, China
  • Investigated strategic impact factors in soccer teams based on game records analysis.
  • Employed social networks and degree centrality for analytical modeling of contest records.
  • Revealed that teams prioritize coordination and communication over individual performance through analysis of Huskies and related soccer games.
 
 
 
 
 

Research Assistant

Institute of Modeling and Data Mining, Wenzhou University

Jul 2019 – Dec 2019 Wenzhou, China
  • Extracted shopping site reviews from Amazon using BeautifulSoup.
  • Performed sentiment analysis on the data corpus with Textblob.
  • Developed commenter user profiles through Wordcloud visualization.
 
 
 
 
 

Technical Leader

Wenzhou Bopu Institute of Big Data

Dec 2018 – Jan 2019 Wenzhou, China
  • Executed public opinion analysis based on news content from Wenzhou News Network.
  • Implemented dictionary-based sentiment analysis and structured single news article into a knowledge graph.
  • Utilized TextRank4ZH for extraction of news topic words and visualized topic “hotness.”
 
 
 
 
 

Technical Leader

MIE DEMO Studio

Dec 2018 – Jan 2019 Wenzhou, China
  • Led the studio to recognition as a national innovation and entrepreneurship training program for college students.
  • Initiated an online volunteer management platform for the existing party member volunteer system, optimized for mobile devices.
  • Managed maintenance and optimization of studio projects, including server-side responsibilities, and contributed to project analysis and testing.

Projects

*

Athenas Oracle

AI-Powered Document Insight Engine

PAT PAT

PATPAT is an innovative project that aimed to create a versatile chatbot capable of operating across web, iOS, and Edge Devices. Initiated as a vision to overcome the limitations of early LLM technologies, the project combined React, Langchain, Flask, and Swift to build a comprehensive solution for real-time interaction and automation.

Equivariant DQN in CartPole

A project that implements Deep Q-Networks (DQN) in OpenAI Gym’s CartPole environment, employing equivariant model techniques to achieve faster training speeds.

Grasping Model with Enhanced SE(2) Prediction

This project enhances a robotic grasping model using PyTorch by integrating safe-z prediction into an SE(2) model, achieving faster training and optimization for patch-based input.

University Information Management System Project

A comprehensive digital platform aimed at revolutionizing traditional university information systems by centralizing data management and enhancing user experience for students, professors, and administrative staff.

CUDA Optimization Techniques for Matrix Operations

This project delves into optimizing matrix operations using CUDA, demonstrating iterative improvements in addition and multiplication algorithms to enhance performance on GPU architectures.

Entity Recognition for Product Names

Conducted Named Entity Recognition (NER) on JD.com product titles in specific categories

Law Law: Legal Question Answering Bot

An Independent Project leveraging PyTorch to develop a question and answer bot based on a legal-like question and answer dataset using a Seq2Seq model.

Legal Text Named Entity Recognition (NER) Project

An Independent Project focused on developing a Named Entity Recognition system for legal texts using PyTorch with a BiLSTM + CRF architecture.

Bristol-Myers Squibb – Molecular Translation (Kaggle 88/874, top11%)

Converted images back to the underlying chemical structure annotated as InChI text

Collaborative Management System of Chongxiao Zhong Han Medical Technology Co.

Collaborative Management System of Chongxiao Zhong Han Medical Technology Co.

Electronic Invoice Management System

Electronic invoice management system based on hospital business

DBI

This tool is responsible for setting up the database environment when deploying enterprise SPD software within the hospital.

Chi Le Ma

Recommender system based takeaway platform

Ming Law

A legal platform based on big data and artificial intelligence technology to serve legal practitioners and consultants

Optimization of similarity algorithm for short texts

Provide a scalable short text similarity calculation scheme

Public opinion analysis project based on Wenzhou News Network

Public opinion analysis based on Wenzhou News Network

Yao Yi Yao

Logistics-based recommendation platform for over-the-counter proprietary Chinese medicines

Study&Chat

Intelligent online teaching platform

Accomplish­ments

the travel award to the William & Mary Computer Science Symposium in Williamsburg, Virginia

Outstanding Graduates of Zhejiang Province(5%)

Highest honor for graduates in Zhejiang Province

Wenzhou University 2020 Gu Chaohao Scholarship (1 out of 8773, 0.01%)

To reward undergraduate students of the university who are exceptionally outstanding in moral, intellectual, physical, aesthetic and labor aspects

University Student Science and Technology Innovation Star (1 out of 8773, 0.01%)

In order to reward students who have outstanding performance in various activities of science and technology innovation in the university

Honorable Mention Award in Mathematical Contest In Modeling (MCM)

Distinguished Employees

Meritorious Winner in Mathematical Contest In Modeling (MCM)

First Prize in the 2019 CUMCM Zhejiang Province Division

Awarded for exceptional achievement and securing the top position in the Zhejiang Province division of the national-level Mathematical Modeling Competition among undergraduate students in China.

First Prize of the 12th China Electrical Engineering Society Cup National Students’ Electrical and Mathematical Modeling

Two times won the third prize of Zhejiang Province E-commerce competition

Third Prize in the 2018 CUMCM Zhejiang Province Division

Recognized for commendable achievement in the Zhejiang Province division of the national-level Mathematical Modeling Competition among undergraduate students in China.

Zhejiang Provincial Government Scholarship (3%)

Outstanding student leaders

First Class Scholarship (5%)