guang

Guangwei Yu

guangweiyu [at] cs [dot] toronto [dot] edu

 

Brief Bio

I am Head of Engineering at Layer 6 and AVP at TD Bank. I obtained my Bachelor's and Master's degrees from University of Toronto. I am broadly interested in large language models, agentic systems, representation learning, information retrieval, and optimizing ML systems. I hold multiple wins in machine learning challenges including YouTube-8M Video Understanding and Google Landmark Retrieval, both largest international competition of its kind at the time, and ACM RecSys Challenge as the premier competition in recommender systems.

Publications

Refereed

  • A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization
    Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, Rasa Hosseinzadeh
    Oral
    In proceedings of NAACL 2025
    [pdf][code]
  • LakeQuest: A Three-Domain Benchmark for Grounded Question Answering across Data Lakes
    Michael Solodko, Steven Gong, Guangwei Yu, Satya Krishna Gorti, Jesse C. Cresswell, Victor Zhong
    In proceedings of COLM 2026
    [pdf][code]
  • TabDPT: Scaling Tabular Foundation Models on Real Data
    Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh, Alex Labach, Hamidreza Kamkari, Jesse C. Cresswell, Keyvan Golestan, Guangwei Yu, Anthony L. Caterini, Maksims Volkovs
    In proceedings of NeurIPS 2025
    [pdf]
  • MSc-SQL: Multi-Sample Critiquing Small Language Models for Text-to-SQL Translation
    Satya Krishna Gorti, Ilan Gofman, Zhaoyan Liu, Jiapeng Wu, Noël Vouitsis, Guangwei Yu, Jesse C. Cresswell, Rasa Hosseinzadeh
    Workshop Oral
    In proceedings of NAACL 2025 and NeurIPS 2024 Table Representation Learning Workshop
    [pdf][code]
  • Retrieval & Fine-Tuning for In-Context Tabular Models
    Valentin Thomas*, Junwei Ma*, Rasa Hosseinzadeh, Keyvan Golestan, Guangwei Yu, Maksims Volkovs, Anthony Caterini
    In proceedings of NeurIPS 2024
    [pdf][code]
  • Data-Efficient Multimodal Fusion on a Single GPU
    Spotlight
    Noël Vouitsis*, Zhaoyan Liu*, Satya Krishna Gorti*, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, Maksims Volkovs
    In proceedings of CVPR 2024
    [pdf][code]
  • TabPFGen - Tabular Data Generation with TabPFN
    Workshop Best Paper Runner-Up
    Junwei Ma, Apoorv Dankar, George Stein, Guangwei Yu, Anthony Caterini
    In proceedings of NeurIPS 2023 Table Representation Learning Workshop
    [pdf]
  • Session-based Recommendation with Transformers
    Yichao Lu, Zhaolin Gao, Zhaoyue Cheng, Jianing Sun, Bradley Brown, Guangwei Yu, Anson Wong, Felipe Perez, Maksims Volkovs
    In proceedings of ACM RecSys 2022
    [pdf]
  • X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
    Satya Krishna Gorti*, Noël Vouitsis*, Junwei Ma*, Keyvan Golestan, Maksims Volkovs, Animesh Garg and Guangwei Yu
    In proceedings of CVPR 2022
    [pdf] [code]
  • Context-aware Scene Graph Generation with Seq2Seq Transformers
    Yichao Lu*, Himanshu Rai*, Jason Chang*, Boris Knyazev, Guangwei Yu, Shashank Shekhar, Graham W. Taylor and Maksims Volkovs
    In proceedings of ICCV 2021
    [pdf] [code]
  • Multi-view scene graph generation in videos
    Yichao Lu*, Cheng Chang*, Himanshu Rai*, Guangwei Yu, Maksims Volkovs
    In proceedings of CVPR2021 International Challenge on Activity Recognition (ActivityNet) Workshop
    [pdf]
  • Weakly Supervised Action Selection Learning in Video
    Junwei Ma*, Satya Krishna Gorti*, Maksims Volkovs and Guangwei Yu
    In proceedings of CVPR 2021
    [pdf] [code]
  • Guided Similarity Separation for Image Retrieval
    Oral
    Chundi Liu, Guangwei Yu, Cheng Chang, Himanshu Rai, Junwei Ma, Satya Krishna Gorti and Maksims Volkovs
    In proceedings of NeurIPS 2019
    [pdf] [code]
  • Cross-Class Relevance Learning for Temporal Concept Localization
    1st Place YouTube-8M Video Understanding Challenge (2019)
    Junwei Ma*, Satya Krishna Gorti*, Maksims Volkovs, Ilya Stanevich and Guangwei Yu
    In proceedings of ICCV 2019 Workshop on YouTube-8M Large-Scale Video Understanding
    [pdf][workshop][challenge]
  • Learning Effective Visual Relationship Detector on 1 GPU
    1st Place Open Images Visual Relationship Challenge (2019)
    Yichao Lu*, Cheng Chang*, Himanshu Rai*, Guangwei Yu, and Maksims Volkovs
    ICCV 2019 Workshop on Open Images Challenge
    [pdf][workshop]
  • Explore-Exploit Graph Traversal for Image Retrieval
    Cheng Chang*, Guangwei Yu*, Chundi Liu and Maksims Volkovs
    In proceedings of CVPR 2019
    [pdf] [code]
  • DropoutNet: Addressing Cold Start in Recommender Systems
    Maksims Volkovs, Guangwei Yu and Tomi Poutanen
    In proceedings of NIPS 2017
    [pdf] [code]
  • Content-based Neighbor Models for Cold Start in Recommender Systems
    1st Place ACM RecSys Challenge (2017)
    Maksims Volkovs, Guangwei Yu and Tomi Poutanen
    In proceedings of ACM RecSys 2017
    [pdf]
  • Effective Latent Models for Binary Feedback in Recommender Systems
    Maksims Volkovs and Guangwei Yu
    In proceedings of SIGIR 2015
    [pdf]
Thesis

  • Characterizing SBP-SAT Operators for CFD Application
    Guangwei Yu, supervised by D. W. Zingg
    The second-derivative PDEs with variable-coefficient model the full Navier-Stokes equations which are the governing equations in computational fluid dynamics (CFD). Investigation of the accuracy of summation-by-parts operators for second-derivatives with variable-coefficients using numerical simulation found that error reduction of up to 70% can be achieved for this class of problem with optimized parameters.
    [pdf]