Emily Jin

Hi — I'm Emily! I recently graduated from Stanford University with a B.S. in Mathematics, and I’m staying for another year to pursue my M.S. in Computer Science.

I am a researcher in the Stanford Vision and Learning Lab (SVL), where I am fortunate to work with Prof. Jiajun Wu on visual reasoning research. In addition, I’ve had the wonderful opportunity to work with Prof. Li Fei-Fei and Prof. Tobias Gerstenberg, on projects that explore different aspects of visual intelligence and their intersections with cognitive science. My research focuses on leveraging structured representations and cognitive insights to develop machines capable of robust, human-like reasoning.

Beyond research, I’m passionate about advancing diversity in tech and have dedicated myself to creating engaging CS experiences for underrepresented communities.

I am actively looking for PhD positions starting in Fall 2025. Feel free to reach out at emilyjin@stanford.edu!

Email / Scholar / Github / LinkedIn

Research

My research interests lie in computer vision and visual reasoning. Inspired by human cognition, I aspire to develop machines that can perceive, understand, and reason about the visual world in ways that mirror human capabilities. In particular, I am interested in learning structured representations and human-like abstractions to enable robustness and generalization, allowing AI systems to tackle complex, real-world visual tasks.

	FactoredScenes: Real-World Scene Generation via Library Learning of Room Structure and Object Pose Prediction Joy Hsu, Emily Jin, Jiajun Wu, Niloy Mitra, Under Review at CVPR, 2025
	Predicate Hierarchies Improve Few-Shot State Classification Emily Jin, Joy Hsu, Jiajun Wu, Under Review at ICLR, 2025
	MARPLE: A Benchmark for Long-Horizon Inference Emily Jin, Zhuoyi Huang, Jan-Philipp Fränken, Weiyu Liu, Hannah Cha, Erik Brockbank, Sarah A. Wu, Ruohan Zhang, Jiajun Wu, Tobias Gerstenberg To appear at NeurIPS Datasets and Benchmarks Track, 2024 project page / pdf / code
	Whodunnit? Inferring What Happened From Multimodal Evidence Sarah A. Wu, Erik Brockbank, Hannah Cha, Jan-Philipp Fränken, Emily Jin, Zhuoyi Huang, Weiyu Liu, Ruohan Zhang, Jiajun Wu, Tobias Gerstenberg CogSci, 2024 preprint / pdf / poster / code
	Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI Emily Jin, Jiaheng Hu, Zhuoyi Huang, Ruohan Zhang, Jiajun Wu, Li Fei-Fei, Roberto Martín-Martín NeurIPS GenPlan Workshop & NeurIPS ALOE Workshop, 2023 paper / poster / code
	Modeling Dynamic Environments with Scene Graph Memory Andrey Kurenkov, Michael Lingelbach, Tanmay Agarwal, Emily Jin, Chengshu Li, Ruohan Zhang, Li Fei-Fei, Jiajun Wu, Silvio Savarese Roberto Martín-Martín ICML*, 2023 project page / paper / code
	MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing Zelun Luo, Zane Durante, Linden Li, Wanze Xie, Ruochen Liu, Emily Jin, Zhuoyi Huang, Lun Yu Li, Ruohan Zhang, Jiajun Wu, Juan Carlos Niebles, Ehsan Adeli Li Fei-Fei, NeurIPS Datasets and Benchmarks Track, 2022 project page / paper / code

Teaching & Outreach

As a young woman in STEM, I am incredibly grateful for the diverse opportunities, inspiring mentors, and inclusive communities that have supported me over the years. These experiences fuel my passion for empowering others through teaching and outreach. Here are some of the most meaningful experiences I have had:

Stanford CS 157. Introduction to Logic.
Course Assistant, Fall 2024.

Stanford AI4ALL. A summer program designed to ignite students' passion for AI by exposing them to cutting-edge advancements in the field —- just as it sparked my own interest when I attended it in high school.
Program Manager, 2020-Present.

AIHacks. Southern California's first all-female high school hackathon.
Founder and Executive Director, 2019-2020
Media: Spectrum News / Los Angeles Daily News

Website source from Jon Barron.