Yunong Liu
MSCS Student at Stanford University
I am a Master's student in Computer Science at Stanford University, advised by Jiajun Wu.
I am working closely with Juan Carlos Niebles, Manling Li, Weiyu Liu and Cristobal Eyzaguirre on projects including grounding 4D assembly instructions in internet videos and tracking emergence in video generation models.
I received my BEng in Electronics and Computer Science from the University of Edinburgh (joint degree with Honors). During my time there, I was fortunate to work with Bonnie Webber and Xixian Liao on natural language processing research. Professor Webber is a role model for me, inspiring me with her unwavering passion and dedication to the field.
I also spent a wonderful semester and summer at the University of Texas at Austin for my exchange program and summer research internship, where I worked with Dhiraj Murthy on misinformation detection.
🎭 Fun fact: I have a twin sister who works in a completely different field - museology! It's fascinating how we've taken such divergent paths in our careers.
I am actively looking for a PhD position starting from Fall 2025. :> Feel free to check my resume or reach out to me at [email protected]!Research Interests
- Generative Models: Emergence and control in video generation models, temporal consistency in video generation
- Visual Prompting: Investigating emergent behaviors and controllability in generative models through visual prompting
- 4D Grounding: 4D grounding and spatial-temporal alignment between 3D models and real-world videos
- Self-Supervised Learning: Self-supervised representation learning for video understanding
Publications
Tracking Emergence in Video Generation Models
Cristobal Eyzaguirre*, Yunong Liu*, Stefan Stojanov, Adrien Gaidon, Juan Carlos Niebles, Jiajun Wu (*Alphabetically)
Discovered video diffusion models' emergent ability to track objects without explicit training. Developed novel intervention-based framework revealing models' implicit understanding of physical dynamics.
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
Yunong Liu, Cristobal Eyzaguirre, Manling Li, Shubh Khanna, Juan Carlos Niebles, Vineeth Ravi, Saumitra Mishra, Weiyu Liu*, Jiajun Wu*.
Created first dataset aligning real-world assembly videos with 3D models and instruction manuals. Developed methods for dense spatio-temporal correspondences in unconstrained videos.
COVID-19 Misinformation Detection: Machine-Learned Solutions to the Infodemic
Yunong Liu*, Nikhil Kolluri*, Dhiraj Murthy.
(*equal contribution)Developed hybrid framework combining machine learning with crowdsourced annotations to combat COVID-19 misinformation. Developed systematic comparison framework across classical models (SVM, LR, BNB) and pre-trained models (BERT, RoBERTa, XLNet) on 7 dataset combinations.
Selected Fun Course Projects
EMo-Mask: Emotional Controllable Motion Generation
Course Project on CS348I Computer Graphics in the Era of AI (2024 Winter)
Project PageJust Dance Everywhere
Best Course Project on EE379K Introduction to Computer Vision Course (2022 Spring) at UT Austin
Project PageRendered Scene of 3rd Floor at Gates Building
Course Project on CS 148: Introduction to Computer Graphics and Imaging (2024 Autumn)
Project PageReinforcement Learning in Marrakech Game
Course Project on AA 228/CS 238: Decision Making under Uncertainty (2024 Autumn)
Awards
- UT Austin Cockrell School of Engineering Fellowship (Declined), Apr 2023
- Turing Scheme Funding, January 2022
- Leadership in Student Opportunities Edinburgh Award, July 2021
- 1st Year Class Medal, awarded to the top overall student in 1st year Electronics and Electrical Engineering Discipline at University of Edinburgh, July 2020
Industry Experience
Student Tech Intern, Semiconductor Manufacturing Anomaly Detection
NXP Semiconductors, Tianjin, China | May 2021 - Aug 2021
- Created validation methodology integrating domain knowledge with statistical confidence measures.
- Designed adaptive thresholding mechanism to handle process variations across production lines.
- Implemented ensemble detection system combining unsupervised learning methods (Isolation Forest, One-Class SVM)
Deep Learning Intern, Wind Farm Performance AI Optimization
Zhineng Technology, Beijing, China | Aug 2021 - Sep 2021
- Helped on developing a framework combining LIDAR measurements with multi-spectral satellite imagery for wind pattern analysis.
- Designed and validated forecasting system integrating physical models with learned spatial-temporal features
Other Experience
Research Assistant - NLP Project
University of Edinburgh | July 2022 - Jan 2023
Worked with Prof Bonnie Webber on discourse relation analysis:
- Investigated relationships between non-canonical syntax (preposing) and discourse relations using large language models
- Developed mask-filling tasks with BERT to analyze implicit discourse relations
- Achieved quantitative evidence for syntactic effects on relation prediction
Helped with a publication in EACL 2024.
Academic Leadership
University of Edinburgh | 2022 - 2023
- Teaching Demonstrator, InfBase (Sep 2022 - Jan 2023)
- Provided tutoring for year-1 and year-2 students in various Computer Science courses
- Programme Representative (Sep 2022 - June 2023)
- Collected and coordinated weekly feedback from 3rd year E&EE students
- Served as liaison between students and faculty for curriculum improvements
- Global Buddies Program Mentor (Sep 2021 - June 2022)
- Provided guidance and support for incoming international students
Volunteer Work
-
Sri Lanka Wildlife Conservation Society (SLWCS) | Jul 2019 - Aug 2019
- Developed strategies to mitigate human-elephant conflicts
- Conducted community outreach and education programs
My Purr-fect Companions
Mewomewo
DoB: October 1, 2012
Role: The Elegant Lady
Superpowers: Tsundere Queen Cleanliness Lover Fearless Explorer
Mewomewo is the queen of the house since 2012. She acts cool but secretly loves attention. She's super brave, except when it comes to mess. You'll often see her checking if the house is clean and tidy.
Xiaopang (Little Fat)
DoB: July 17, 2014
Role: The Cuddly Foodie
Superpowers: Cuddle Expert Food Lover Master of Stealth (when scared)
Xiaopang, our big bundle of love, joined us in 2014. His name means "little fat", but really, he's just extra cuddly! He loves snuggles and treats equally. He might get scared easily, but his heart is as big as his appetite.