Ruth Fong

I am a teaching professor (Lecturer) in the Department of Computer Science at Princeton University.

Teaching. I primarily teach COS 126 (intro CS) and COS 324 (intro ML).

Research. My research focuses on human-centered AI and spans the fields of machine learning, computer vision, and human-computer interaction (HCI). Specifically, I study how people understand, trust, and work with AI and how AI can leveraged well in different domains (e.g. education). At Princeton, I lead the Looking Glass Lab and frequently collaborate with the Visual AI Lab and Princeton HCI.

Background. I completed my PhD in the Visual Geometry Group at the University of Oxford, where I was advised by Andrea Vedaldi and funded by the Rhodes Trust and Open Philanthropy. Also at Oxford, I earned a Masters in Neuroscience, where I worked with Rafal Bogacz, Ben Willmore, and Nicol Harper. I received a Bachelors in Computer Science at Harvard University, where I worked with David Cox and Walter Scheirer.

Email | CV | Bio | Google Scholar | GitHub

Hello! 👋

Research/IW/thesis advising. I am excited to work with Princeton students! If you are a...

Princeton undergraduate student interested in doing an IW, a senior thesis, and/or research with me, please first read this doc with a list of preferred IW topics and my philosophy on IW. If one of the topics interests you, please email me your (1) CV, (2) transcript, and (3) a short description of what you might be interested in working on (I also have a few project ideas I can suggest). I am particularly excited about helping students from underrepresented groups have a positive and successful first research experience. For lists of other potential IW/thesis advisors...
- For a list of most AIML faculty members in the COS department, see here.
- For a list of all COS faculty who are available for IW/thesis advising, see here.
Princeton graduate student interested in working or collaborating with me, please reach out via email.
non-Princeton student (including prospective applicants) interested in working with me, there's no need to email; I unfortunately am not accepting non-Princeton students at this time.

Other Princeton things. Engaging with students is one of my favorite parts of the job. If you'd like to reach me about other Princeton-related things (e.g. participating in a student event, grabbing a meal), shoot me an email!

News 🗞

I am excited to participate in the NJ AI Hub's Faculty Futures AI Studio (Fall 2026) as a fellow and facilitator for the "AI in Technical Frontiers" track. official announcement
Our SIGCSE 2026 short paper, "Characterizing the Relationship Between Generative AI, Student Behavior, and Learning Outcomes in Upper-Level CS Education: A Case Study in an Undergraduate Machine Learning Course," earned 1st Place at ACM Student Research Competition Grand Finals 🏆! Congrats to Anha Khan and our co-authors 🎉! paper | LinkedIn post | award announcement
Our CHI 2023 paper, "Help Me Help the AI": Understanding How Explaiinability Can Support Human-AI Interaction, received an honorable mention award 🏆! Congrats to Sunnie S. Y. Kim and our co-authors 🎉! arXiv | program link
My PhD thesis on "Understanding Convolutional Neural Networks" can be found here. For those with less experience, all chapters except chapters 3-6 were written with accessibility in mind.

Looking Glass Lab 👤

Members

Fatiha Haider Diya Hundiwala Yousef Kassem Harsidak Singh Anha Khan

Collaborators

Romina Mahinpei Prof. Victoria Dean Prof. Maryam Hedayati Prof. Manoel Horta Ribeiro Prof. Lydia T. Liu Prof. Vikram V. Ramaswamy

[image attribution]

Awards

Anha Khan et al., 1st Place at ACM Student Research Competition Grand Finals, 2026.
Anha Khan et al., 1st Place at SIGCSE ACM Student Research Competition, 2026.
Ruth Fong, Victoria Dean, and Vikram Ramaswamy, Princeton 250th Anniversary Fund for Innovation in Undergraduate Education Award, 2026.
Ruth Fong, Victoria Dean, and Vikram Ramaswamy, Princeton AI Lab Seed Award, 2026.
Ruth Fong, Princeton Engineering Council Teaching Award, 2025.
Ruth Fong, Princeton Keller Center Summer Course Development Award, 2025.
Ruth Fong and Vikram Ramaswamy, Princeton SEAS Innovation Award, 2024.
Sunnie S. Y. Kim et al., CHI Honorable Mention Paper Award, 2023.
Devon Ulrich, Tau Beta Pi, 2023.
Alexis Sursock, Sigma Xi, 2023.
Indu Panigrahi, Sigma Xi, 2023.
Indu Panigrahi, Outstanding Computer Science Senior Thesis Prize, 2023.
Indu Panigrahi, NSF Graduate Fellowship Award Honorable Mention, 2023.
Indu Panigrahi, Computing Research Association (CRA) Outstanding Undergraduate Research Award Nominee, 2022.
Indu Panigrahi, Outstanding Independent Work Award, 2022.
Indu Panigrahi, Princeton Research Day Orange & Black Undergraduate Presentation Award, 2022.
Ruth Fong and Olga Russakovsky, Open Philanthropy AI Alignment Award, 2022.
Ruth Fong and Olga Russakovsky, Princeton SEAS Innovation Award (Project X Fund), 2022.
Ruth Fong, Open Philanthropy AI Fellowship, 2018.
Ruth Fong, Rhodes Scholarship, 2015.

Alumni

Anha Khan '26 and Jennifer Yan '27, UCAs (summer 2026), Reimagining Machine Learning Education in the Modern Era of AI.
Anha Khan '26, senior thesis, Pedagogically Constrained LLM Use and Learning Outcomes in an Undergraduate Machine Learning Course (started CS MS at Princeton in 2026).
Alex Tao '25, UCA (summer 2025), Learning to Learn: Redesigning Reinforcement Learning for COS 324.
Indu Panigrahi '23 *25, master's thesis (co-advised with Parastoo Abtahi), Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations (started CS PhD at UIUC in 2025).
Rawand Aziz '25, senior thesis, Estimating Displacement via Nighttime Satellite Imagery.
Matthew Barrett '25, senior thesis, SPADE: A Synthetic Paired Dataset for Specular-Diffuse Video Decomposition.
Emilio Chan '25, senior thesis, Handwritten Chinese Character Error Correction for Beginner Chinese Students.
Ben Wachspress '25, senior thesis, InvesigHate: Explainability and Robustness of Hate Speech Detection Models.
Adam Kelch '24, IW (spring 2023), Extending Feature Visualization Methods to Text-To-Image Generative AI Models
Sai Rachumalla '24, IW (spring 2023), Evaluating Concept-based Visual Explanations
Creston Brooks '23, senior thesis, Optimizations towards AI-based Travel Recommendation (started CS MS at Princeton in 2023).
Alexis Sursock '23, senior thesis, Stravl: The World's First Large-Scale, AI-based Travel Designer.
Indu Panigrahi '23, senior thesis, A Semi-supervised Model for Fine-grain, Serial Image Instance Segmentation (started CS MS at Princeton in 2023).
Devon Ulrich '23, senior thesis, Investigating the Fairness of Computer Vision Models for Medical Imaging.
Rohan Jinturkar '23, senior thesis (co-advised with Olga Russakovsky), Why Did The Model Fail? Empowering Non-Experts to Explore Computer Vision Models through Interactive Dialogue.
Icey Siyi '24 and Fatima Zohra Boumhaout '24, research (summer 2022), Interactive Perturbation Visualization Tool.
Frelicia Tucker '22, senior thesis, The Virtual Black Hair Experience: Evaluating Hairstyle Transform Generative Adversarial Networks on Black Women.
Vedant Dhopte '22, senior thesis, Holistically Interpreting Deep Neural Networks via Channel Ablation.

Research 🧪

See Google Scholar for the most updated list of papers.

* denotes equal contribution; ^ denotes peer-reviewed, non-archival work (e.g. accepted to non-archival workshop).

	AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education Romina Mahinpei, Victoria Dean, Ruth Fong, Lydia T. Liu, Manoel Horta Ribeiro arXiv, 2026 arXiv \| code \| bibtex Through a randomized field experiment in an undergraduate machine learning course, we find that showing TAs AI-drafted feedback increases how often (and how much) feedback they give students, without reducing its perceived usefulness.
	Characterizing the Relationship Between Generative AI, Student Behavior, and Learning Outcomes in Upper-Level CS Education: A Case Study in an Undergraduate Machine Learning Course Anha Khan, Romina Mahinpei, Maryam Hedayati, Victoria Dean, Ruth Fong SIGCSE TS (ACM Student Research Competition [SRC]), 2026 (1st Place at SRC 🏆) paper \| LinkedIn post \| bibtex We design and study a custom LLM chatbot used by students in an introductory machine learning course to evaluate the effect of generative AI on student behavior and learning outcomes.
	Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations Indu Panigrahi, Sunnie S. Y. Kim, Amna Liaqat, Rohan Jinturkar, Olga Russakovsky, Ruth Fong, Parastoo Abtahi CHI Extended Abstracts (Late-Breaking Work), 2025 paper \| project page \| bibtex We study how end-users leverage and perceive interactive computer vision explanations.
	Interactive Visual Feature Search Devon Ulrich and Ruth Fong CVPR Workshop on Computer Vision for XAI (CV4XAI), 2024 arXiv \| code \| bibtex We present an interactive visualization tool that allows you to perform a reverse image search for similar image regions using intermediate activations.
	Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández FAccT, 2023 arXiv \| project page \| bibtex We study how end-users trust AI in a real-world context. Concretely, we describe multiple aspects of trust in AI and how human, AI, and context-related factors influence each.
	UFO: A Unified Method for Controlling Understandability and Faithfulness Objectives in Concept-based Explanations for CNNs Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky arXiv, 2023 arXiv \| bibtex We introduce a novel concept-based explanation framework for CNNs: UFO, which is a method for controlling the understandability and faithfulness of concept-based explanations using well-defined objective functions for the two qualities.
	Improving Data-Efficient Fossil Segmentation via Model Editing Indu Panigrahi, Ryan Manzuk, Adam Maloof, Ruth Fong CVPR Workshop on Learning with Limited Labelled Data for Image and Video Understanding, 2023 arXiv \| bibtex We explore how to improve a model for segmenting coral reef fossils by first understanding its systematic failures and second ``editing'' the model to mitigate said failures.
	"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández CHI, 2023 (Honorable Mention award 🏆) arXiv \| supp \| 30-sec video \| 10-min video \| bibtex We explore how explainability can support human-AI interaction by interviewing 20 end-users of a real-world AI application. Specifically, we study (1) what XAI needs people have, (2) how people intend to use XAI explanations, and (3) how people perceive existing XAI methods.
	Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Salience, and Human Capability Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky CVPR, 2023 arXiv \| bibtex We analyze three commonly overlooked factors in concept-based explanations, (1) the choice of the probe dataset, (2) the saliency of concepts in the probe dataset, (3) the number of concepts used in explanations, and make suggestions for future development and analysis of concept-based interpretability methods.
	Gender Artifacts in Visual Datasets Nicole Meister, Dora Zhao, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky ICCV, 2023 arXiv \| project page \| bibtex We demonstrate the pervasive-ness of gender artifacts in popular computer vision datasets (e.g. COCO and OpenImages). We find that all of the following (and more) are gender artifacts: the mean value of color channels (i.e. mean RGB), the pose and location of people, and most co-located objects.
	ELUDE: Generating Interpretable Explanations via a Decomposition into Labelled and Unlabelled Features Vikram V. Ramaswamy, Sunnie S. Y. Kim, Nicole Meister, Ruth Fong, Olga Russakovsky arXiv, 2022 arXiv \| bibtex We present ELUDE, a novel explanation framework that decomposes a model's prediction into two components: 1. using labelled, semantic attributes (e.g. fur, paw, etc.) and 2. using an unlabelled, low-rank feature space.
	HIVE: Evaluating the Human Interpretability of Visual Explanations Sunnie S. Y. Kim, Nicole Meister, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky ECCV, 2022 arXiv \| project page \| extended abstract \| code \| 2-min video \| bibtex We introduce HIVE, a novel human evaluation framework for diverse interpretability methods in computer vision, and develop metrics that measure achievement on two desiderata for explanations used to assist human decision making: (1) Explanations should allow users to distinguish between correct and incorrect predictions. (2) Explanations should be understandable to users.
	Interactive Similarity Overlays^ Ruth Fong, Alexander Mordvintsev, Andrea Vedaldi, Chris Olah VISxAI, 2021 interactive article \| code \| bibtex We introduce a novel interactive visualization that allows machine learning practitioners and researchers to easily observe, explore, and compare how a neural network perceives different image regions.
	On Compositions of Transformations in Contrastive Self-Supervised Learning Mandela Patrick, Yuki M. Asano, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, and Andrea Vedaldi ICCV, 2021 arXiv \| code \| bibtex We give transformations the prominence they deserve by introducing a systematic framework suitable for contrastive learning. SOTA video representation learning by learning (in)variances systematically.
	Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning Iro Laina, Ruth Fong, and Andrea Vedaldi NeurIPS, 2020 arxiv \| supp \| bibtex We introduce two novel human evaluation metrics for quantifying for evaluating the interpretability of clusters discovered via self-supervised methods. We also outline how to partially approximate one of the metrics using a group captioning model.
	Debiasing Convolutional Neural Networks via Meta Orthogonalization^ Kurtis Evan David, Qiang Liu, and Ruth Fong NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Interpretability (AFCI), 2020 arxiv \| supp \| poster \| bibtex We introduce a novel paradigm for debiasing CNNs by encouraging salient concept vectors to orthogonal to class vectors in the activation space of an intermediate CNN layer (e.g., orthogonalizing gender and oven concepts in conv5).
	Contextual Semantic Interpretability Diego Marcos, Ruth Fong, Sylvain Lobry, Rémi Flamary, Nicolas Courty, and Devis Tuia ACCV, 2020 arxiv \| supp \| code \| bibtex We introduce an interpretable-by-design machine vision model that learns to sparse groupings of interpretable concepts and demonstrate the utility of our novel architecture on scenicness prediction.
	There and Back Again: Revisiting Backpropagation Saliency Methods Sylvestre-Alvise Rebuffi, Ruth Fong, Xu Ji, and Andrea Vedaldi CVPR*, 2020 arxiv \| code \| bibtex @InProceedings{rebuffi_cvpr_2020, author = {Rebuffi, Sylvestre-Alvise and Fong, Ruth and Ji, Xu and Vedaldi, Andrea}, title = {There and Back Again: Revisiting Backpropagation Saliency Methods}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020} } We outline a novel framework that unifies many backpropagation saliency methods. Furthermore, we introduce NormGrad, a saliency method that considers the spatial contribution of the gradients of convolutional weights. We also systematically study the effects of combining saliency maps at different layers. Finally, we introduce a class-sensitivity metric and a meta-learning inspired technique that can be applied to any saliency method to improve class sensitivity.
	Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims Miles Brundage, Shahar Avin, Jasmine Wang, Haydn Belfield, Gretchen Krueger, … , Ruth Fong, et al. arXiv*, 2020 arxiv \| project page \| bibtex This report suggests various steps that different stakeholders can take to make it easier to verify claims made about AI systems and their associated development processes. The authors believe the implementation of such mechanisms can help make progress on one component of the multifaceted problem of ensuring that AI development is conducted in a trustworthy fashion.
	Understanding Deep Networks via Extremal Perturbations and Smooth Masks Ruth Fong, Mandela Patrick, and Andrea Vedaldi ICCV, 2019 (Oral) arxiv \| supp \| poster \| code (TorchRay) \| 4-min video \| bibtex @InProceedings{fong_iccv_2019, author = {Fong, Ruth and Patrick, Mandela and Vedaldi, Andrea}, title = {Understanding Deep Networks via Extremal Perturbations and Smooth Masks}, booktitle = {The IEEE International Conference on Computer Vision (ICCV)}, year = {2019} } We introduce extremal perturbations, an novel attribution method that highlights "where" a model is "looking." We improve upon Fong and Vedaldi, 2017 by separating out regularization on the size and smoothness of a perturbation mask from the attribution objective of learning a mask that maximally affects a model's output; we also extend our work to intermediate channel representations.
	Occlusions for Effective Data Augmentation in Image Classification Ruth Fong and Andrea Vedaldi ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models, 2019 paper \| bibtex \| code (coming soon) @InProceedings{fong_iccv_workshop_2019, author = {Fong, Ruth and and Vedaldi, Andrea}, title = {Occlusions for Effective Data Augmentation in Image Classification}, booktitle = {ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models}, year = {2019} } We introduce a simple paradigm based on batch augmentation for leveraging input-level occlusions (both stochastic and saliency-based) to improve ImageNet image classification. We also demonstrate the necessary of batch augmentation and quantify the robustness of different CNN architectures to occlusion via ablation studies.
	Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks Ruth Fong and Andrea Vedaldi CVPR, 2018 (Spotlight) arxiv \| supp \| bibtex \| code \| 4-min video \| slides @InProceedings{fong_cvpr_2018, author={Fong, Ruth and Vedaldi, Andrea}, title={Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks}, booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month={July}, year={2018} } Investigating how human-interpretable visual concepts (i.e., textures, objects, etc.) are encoded across hidden units of a convolutional neural network (CNN) layer as well as across CNN layers.
	Using Human Brain Activity to Guide Machine Learning Ruth Fong, Walter Scheirer, and David Cox Scientific Reports, 2018 arxiv \| supp \| Harvard thesis \| bibtex We introduce a biologically-informed machine learning paradigm for object classification that biases models to better match the learned, internal representations of the visual cortex.
	Interpretable Explanations of Black Box Algorithms by Meaningful Perturbation Ruth Fong and Andrea Vedaldi ICCV, 2017 arxiv \| supp \| bibtex \| code \| book chapter (extended) \| chapter bibtex We developed a theoretical framework for learning "explanations" of black box functions like CNNs as well as saliency methods for identifying "where" a computer vision algorithm is looking.

Theses 🎓

	Understanding Convolutional Neural Networks Ruth Fong (advised by Andrea Vedaldi) Ph.D. Thesis This is a "thesis-by-staples", so the novel parts are the non-paper chapters (i.e. all chapters except chapters 3-6), which I wrote with accessibility in mind (e.g., the ideal reader is a motivated undergraduate or graduate student looking to learn more about deep learning and interpretability). The introduction is accessible to a high-school student, and appendices A and B are primers on the relevant math concepts and convolutional neural networks respectively.
	Modelling Blind Single Channel Sound Separation Using Predict Neural Networks Ruth Fong (advised by Ben Willmore and Nicol Harper) M.Sc. Thesis #2 I developed an unsupervised learning paradigm for sound separation using fully connected and recurrent neural networks to predict the future from past cochleagram data.
	Optimizing Deep Brain Stimulation to Dampen Tremor Ruth Fong (advised by Rafal Bogacz) M.Sc. Thesis #1 Tutorial \| Demo \| MATLAB Rayleigh statistics toolbox I developed a computational oscillator model that modeled the tremor-dampening effects of phasic deep brain stimulation and analyzed it on experimental data.
	Leveraging Human Brain Activity to Improve Object Classification Ruth Fong (advised by David Cox and Walter Scheirer) A.B. Thesis Published as Fong et al., Scientific Reports 2018.