Scholar
Shengxiang Sun
Google Scholar ID: 4nVa1oIAAAAJ
University of Toronto
robotics
computer vision
machine learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
17
H-index
3
i10-index
0
Publications
4
Co-authors
4
list available
Contact
Email
owen.sun@mail.utoronto.ca
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Models
2025
Cited
0
SAFE: Multitask Failure Detection for Vision-Language-Action Models
2025
Cited
0
Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models
2025
Cited
0
A short Survey: Exploring knowledge graph-based neural-symbolic system from application perspective
2024
Cited
3
Resume (English only)
Academic Achievements
Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision–Language Models (co-first author, under submission)
SAFE: Scalable Failure Estimation for Vision-Language-Action Models, NeurIPS 2025
Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Models, RSS 2025 (co-first author)
General In-Course Scholarship (2022–2025)
Dean’s List (2023–2025)
Summer NSERC Math & Computer Science Research Award (2024)
Research Experience
Collaborating with Prof. Weiyu Liu (University of Utah)
Collaborating with Prof. Florian Shkurti (University of Toronto)
Collaborating with Prof. Lin Shao (National University of Singapore)
Machine Learning Engineer Intern, Loblaw Digital, Toronto, ON, Canada (Jan 2024 – Apr 2024)
Machine Learning Research Intern, New H3C Technologies, Beijing, China (Jul 2023 – Aug 2023)
Background
Final-year Computer Science undergraduate at the University of Toronto
Research spans robotics and 3D computer vision, with a focus on generalizable robot manipulation
Interested in enabling robots to perform complex, long-horizon tasks from simple instructions (e.g., “prepare a dish from this cookbook”)
Approach leverages Foundation Models to learn from vast online human knowledge instead of costly manually collected data
Actively seeking Master’s or PhD positions in Robotics and Computer Vision for Fall 2026
Co-authors
4 total
Shenzhe Zhu
University of Toronto
Lin Shao
National University of Singapore
Chenrui Tie
National University of Singapore
Florian Shkurti
Assistant Professor, Computer Science, University of Toronto
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up