Elliot Creager

Welcome to my humble homepage!

I am the director of the Socially Embedded Machine Intelligence (SEMI) lab, where my research focuses on building reliable and equitable AI systems that promote user data autonomy. Located in Waterloo’s Faculty of Engineering, my research group takes an interdisciplinary approach to developing socially beneficial AI technology.

I am always looking for motivated students at all levels to help me realize this vision. I draw inspiration from many disciplines (from deep learning to sociology and beyond) in order train researchers who are not only technically proficient, but who think holistically and critically about the social impacts of their work. More information about how to join SEMI can be found here.

SEMI lab members

Ahmed Osman (Co-op)
Alisha Anat (Co-op, URA)
Catherine Jin (Co-op, URA)
Deacon Sham (URA)
Joshua Hill (Co-op, URA)
Ambreesh Parthasarathy (MASc)
Brandon Jaipersaud (MASc)
Rebecca Ma (MASc)
Soudeh Nilforoushan (PhD)
Ali Falahati (Research Associate)
Jin Sol Kim (Postdoc)

former students

Huy Trinh (MASc ‘26)
Rushabh Solanki (MASc ‘25)
Yuhao Chen (Co-op ‘25)
Chloe Nguyen (Ugrad ‘25)
Violetta Bilynska (Intern ‘24)

news

Aug 18, 2026	I served as Area Chair for NeurIPS 2026.
Jul 29, 2026	The AI Readiness for Organizations Lab (where I am a faculty affiliate) has launched at the University of Waterloo.
Jul 16, 2026	“Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms” was accepted to AIES 2026.
Jun 25, 2026	I facilitated the CRAFT session “Closing the Gap Between Algorithmic Collective Action Research and LGBTQIA2S+ Community Needs” CRAFT session at FAccT 2026.
May 30, 2026	Our panels “From RAGs to Informational Riches: Using a Context-Based LLM to Inform Policymaking for Facial Recognition Systems” and “Co-designing Research Tools for Effective Regulation: Using Context-Based LLMs to Bridge Policymaking Knowledge Gaps” were accepted to 4S 2026.
May 25, 2026	I gave an invited talk at the Data and Model Protection in Generative AI Workshop at the 2026 Canadian Conference on Artificial Intelligence.
Apr 13, 2026	I served as an Area Chair for FAccT 2026.
Apr 9, 2026	Huy Trinh has completed his Master’s!
Apr 2, 2026	SEMI has received a CIFAR/CAISI AI Catalyst Grant supporting our project “Democratic alignment of large language models (LLMs) through economic theory: relative preferences and strategic coordination”
Mar 26, 2026	I am serving as an Area Chair and Ethics Reviewer for ICML 2026.
Mar 2, 2026	“Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy” was accepted to FAccT 2026.
Feb 12, 2026	“Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework” was accepted to EACL 2026 as an oral presentation (top 24%).
Dec 5, 2025	The Workshop on Algorithmic Collective Action is taking place at NeurIPS 2025 in San Diego.
Nov 24, 2025	Rushabh Solanki, SEMI’s first graduate student, has completed his Master’s!
Nov 20, 2025	I was recognized as a Top 10% Area Chair of NeurIPS 2025.
Oct 18, 2025	I am speaking at a Youth Tech Labs event in Waterloo.
Jul 4, 2025	Our proposed Workshop on Algorithmic Collective Action was accepted to NeuRIPS 2025! The one-day workshop will take place December 6 or 7 in San Diego.
Jun 30, 2025	“Transformers Don’t In-Context Learn Least Squares Regression”, led by SEMI ugrad Joshua Hill, was accepted as an oral presentation at the ICML 2025 Workshop on Reliable and Responsible Foundation Models (Update: the recorded talk is available on SlidesLive)
Jun 6, 2025	“Out of Sight, Out of Mind: Problems Perpetuated by Training on Facial Images Collected by De Facto Consent”, led by SEMI ugrad Chloe Nguyen, was accepted as an oral presentation at the IEEE ETHICS 2025 student track.
Jun 2, 2025	I am serving as Area Chair for NeurIPS 2025
May 17, 2025	Grant proposal “Fostering Sustainable and Equitable Worker-AI Collaboration Through Algorithmic Collective Action” with Hanlin Li was awarded a University of Texas Global Research 2025 Seed Grant.
May 9, 2025	Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy is available as a preprint.
May 6, 2025	Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework is available as a preprint.
Mar 14, 2025	“Algorithmic Collective Action Directed at Fair and Private Learning Algorithms” was accepted as a spotlight presentation at CPI GradConf 2025.
Jan 30, 2025	I am serving as Area Chair for ICML 2025
Oct 14, 2024	Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm was accepted to the NeurIPS 2024 Workshop on Regulatable ML!
Oct 9, 2024	Show, Don’t Tell: Uncovering Implicit Character Portrayal using LLMs was accepted to the NeurIPS 2024 Workshop on Creativity and Generative AI!
Jun 13, 2024	I gave a talk on model adaptation and data coordination as part of the Waterloo.AI Seminar Series
May 23, 2024	I was awarded a CIFAR AI Catalyst Grant to work with Golnoosh Farnadi on Algorithmic Auditing.
May 1, 2024	Two papers accepted at ICML 2024: Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making and Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift!
Apr 11, 2024	I am hiring a postdoc (jointly supervised Laleh Seyyed-Kalantari) to investigate the internal representations of foundation models.
Mar 15, 2024	I gave an invited guest lecture at Laleh Seyyed-Kalantari’s “AI Fairness and Debiasing” course (York University).
Mar 14, 2024	I gave an invited guest lecture at Nisarg Shah’s “Mathematical Foundations of Algorithmic Fairness” course (University of Toronto).
Dec 14, 2023	I led (along with Stephen Pfohl) a roundtable discussion at the NeurIPS 2023 Workshop on Algorithmic Fairness Through the Lens of Time.
Nov 13, 2023	I gave an invited talk at the lab meeting of Prof. Golnoosh Farnadi
Nov 10, 2023	I gave an invited talk at the workshop on “Forging a Path: Causal Inference and Data Science for Improved Policy”, hosted by the University of Toronto’s Data Science Institute
Oct 30, 2023	“Remembering to Be Fair: On Non-Markovian Fairness in Sequential Decision Making” (preprint forthcoming) was accepted to the NeurIPS 2023 Workshop on Algorithmic Fairness Through the Lens of Time!
Sep 1, 2023	I have joined University of Waterloo as an Assistant Professor.
Aug 21, 2023	After passing my final oral examination (external thesis defense), I have now completed my PhD!
Jul 19, 2023	I will be joining University of Waterloo’s Department of Electrical and Computer Engineering as an Assistant Professor this fall!
Jul 13, 2023	SurfsUp was accepted to ICCV 2023!
Jul 10, 2023	I gave an invited talk at Vector Institute’s Machine Learning Security and Privacy Workshop.
Jun 22, 2023	I attended the SRI’s Absolutely Interdisciplinary conference in Toronto.
Jun 19, 2023	“Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift” (preprint forthcoming) was accepted to the ICML 2023 Workshop on Spurious Correlations, Invariance, and Stability!
Jun 16, 2023	I attended FAccT 2023 in Chicago.
May 31, 2023	I passed my department thesis examination, where I successfully defended my thesis “Robust Machine Learning by Transforming and Augmenting Imperfect Training Data”.
Apr 27, 2023	I gave an invited talk at the Mila reading group DEFirst, which studies fairness and explainability in information retrieval.
Apr 24, 2023	I served as panelist for an event on “Generative AI and the future of education” hosted by SRI and OISE.
Apr 13, 2023	SurfsUp, a neural fluid simulator that can generalize OOD by simulating how fluids interact with novel surfaces, is available as a preprint.
Feb 25, 2023	I discussed the ethics of AI research with Grade 12 students as a panelist for Pursue STEM.
Feb 2, 2023	I attended the annual Algorithmic Fairness meeting at the Simons Institute in NYC
Dec 5, 2022	I co-presented the tutorial Algorithmic Fairness: at the Intersections at NeurIPS 2022
Nov 17, 2022	I gave an invited talk (“Methods for Counterfactual Data Augmentation in RL”) at Vector Institute.
Nov 7, 2022	I was named as a “Top Reviewer” of NeurIPS 2022 papers
Nov 6, 2022	I am now on the job market! Searching for faculty, industry and post-doc positions…
Sep 14, 2022	“MoCoDA: Model-based Counterfactual Data Augmentation” was accepted to NeurIPS 2022
Sep 2, 2022	I will be co-presenting the NeurIPS 2022 tutorial “Algorithmic Fairness: at the Intersections” alongside Golnoosh Farnadi and Q. Vera Liao