profile_picture
Guangyuan Weng
翁光源
gweng.aca AT gmail.com
🔎 I am on the 2026-2027 job market, seeking full-time Research Scientist / Applied Scientist positions, and I am also open to Summer 2027 internships. Feel free to reach out!

I’m a Ph.D. candidate in Computer Science at Northeastern University, advised by Prof. Esteban Moro. I study how LLMs and recommender systems model and shape where people go, with work on LLM post-training, evaluation, and representation learning. I also work with Prof. David Bau on LLM interpretability. Most recently I was a Research Scientist II Intern at Chewy, and previously at Wormpex AI Research.

Earlier, I worked on action recognition and visual representation learning at the IU Computer Vision Lab with Prof. David J. Crandall, and on robotics and SLAM with Prof. Sören Schwertfeger at the Mobile Autonomous Robotic Systems Lab.

Interests

  • LLM Post-training & Evaluation
  • Recommender Systems
  • Representation Learning
  • Spatiotemporal Data Mining
  • Responsible AI

Academia

Northeastern University
Sept. 2021 - Present
Ph.D. Computer Science
ShanghaiTech University
Sept. 2017 - July 2021
B.E. Computer Science

Experience

  • Research Scientist II Intern, Chewy, Summer 2026
    Built from scratch a multimodal GenAI pipeline that turns marketing videos into structured creative elements, and an interactive dashboard that predicts how new creatives will perform to guide campaign and studio decisions.
  • Research Intern, Wormpex AI Research, Bellevue WA, Summer 2023
    Designed RAG classifiers for long-tail image recognition, with a self-attention module that down-weights noisy retrieved examples.
  • Visiting Research Intern, IU Computer Vision Lab, Indiana University, July 2020 - June 2021
    Trained graph convolutional networks on action-object co-occurrence in egocentric video for out-of-distribution action recognition. Published at ICDL 2022.

News

Publications

Beyond Distance: Mobility Neural Embeddings Reveal Visible and Invisible Barriers in Urban Space, 2026, Science Advances (accepted)
Learned neural place embeddings from 25.4M trajectories in 11 US cities, treating places as tokens and visit sequences as sentences; embedding distance explains mobility flows far better than map distance (R² 0.61 vs. 0.33 in Boston).
Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation, 2026, Under review
Built a realistic simulation of next-place recommenders in four US metros: the most accurate recommender raises income segregation by 15 to 21% and leaves 1 in 5 venues with no visits; promoting less popular venues more than halves venue loss.
Large language models create an uneven informational layer over cities, 2026, Under review
End-to-end evaluation of venue recommendations from three LLM families across 304 neighborhoods in five US cities: 36.8% of recommended venues do not exist, and even with real venue lists, 47.5% of venues are never recommended.
Action Recognition based on Cross-Situational Action-object Statistics, 2022, The 12th IEEE International Conference on Development and Learning (ICDL 2022)
Advanced mapping robot and high-resolution dataset, 2020, Journal of Robotics and Autonomous Systems
Hongyu Chen , Zhijie Yang , Xiting Zhao , Guangyuan Weng , Haochuan Wan , Jianwen Luo , Xiaoya Ye , Zehao Zhao , Zhenpeng He , Yongxia Shen , Sören Schwertfeger
Towards Generation and Evaluation of Comprehensive Mapping Robot Datasets, 2019, IEEE Conference on Robotics and Automation (ICRA) 2019 workshop
Hongyu Chen , Xiting Zhao , Jianwen Luo , Zhijie Yang , Zehao Zhao , Haochuan Wan , Xiaoya Ye , Guangyuan Weng , Zhenpeng He , Tian Dong , Sören Schwertfeger

Teaching

  • CS 5100 Foundations of Artificial Intelligence (TA) , Fall 2025
  • CS 5520 Mobile Application Development (Head TA) , Spring 2024, Fall 2024, Spring 2025, Summer 2025
  • CS 4520 Mobile Application Development (TA) , Summer 1 2024
  • CS 5330 Pattern Recognition and Computer Vision (TA) , Fall 2021, Fall 2022
  • Penn AI Robotics Summer Camp (TA) , GRASP Lab, Summer 2019

Honors

  • Outstanding PhD Student Award for Teaching , Northeastern University, 2026
  • Scholarship for Outstanding Undergraduates (RMB 30,000) , ShanghaiTech University, 2020
  • Merit Students (Top 5%) , ShanghaiTech University, 2020
  • Global Talent Attraction Program, International Summer Research Fellowship ($ 4,000) , Indiana University Bloomington, 2020

Academic Service

  • Reviewer: IC2S2 (2024, 2025, 2026), NetSci (2025, 2026), NeurIPS (2026)

Contact

Miscellaneous

  • Our days may come to seventy years, or eighty, if our strength endures;
  • Yet the best of them are but trouble and sorrow, for they quickly pass, and we fly away.
  • If only we knew the power of your anger!
  • Your wrath is as great as the fear that is your due.
  • Teach us to number our days, that we may gain a heart of wisdom.
  • (Psalm 90:10-12 NIV)