Josh Engels

Bio Image


I am currently a first year EECS PhD student at MIT, where I am grateful to be advised by Max Tegmark. Broadly, I am interested in understanding neural networks from the ground up through the lens of interpretability, with an eventual goal of using these insights to ensure powerful AI systems are robust and safe. Starting in the fall, I will be supported by the NSF Graduate Research Fellowship Program.

Earlier in my PhD, I had the pleasure of working with Julian Shun on building high performance algorithms, with a focus on approximate nearest neighbor search. I also previously spent two enjoyable years working at ThirdAI, where we built a sparse machine learning engine from scratch.


Not All Language Model Features Are Linear.
Joshua Engels*, Isaac Liao*, Eric J. Michaud, Wes Gurnee, and Max Tegmark.
Preprint | Code | Twitter

Approximate Nearest Neighbor Search with Window Filters.
Joshua Engels, Benjamin Landrum, Shangdi Yu, Laxman Dhulipala, and Julian Shun.
To appear at ICML 2024.
Preprint | Code

PECANN: Parallel Efficient Clustering with Graph-Based Approximate Nearest Neighbor Search.
Shangdi Yu, Joshua Engels, Yihao Huang, and Julian Shun.
Preprint | Code

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries.
Joshua Engels, Benjamin Coleman, Vihan Lakshman, and Anshumali Shrivastava
NeurIPS 2023.
Paper | Code | Blog Post

BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware.
Nicholas Meisburger, Vihan Lakshman, Benito Geordie, Joshua Engels, David Torres Ramos, Pratik Pranav, Benjamin Coleman, et al.
CIKM 2023.

From Research to Production: Towards Scalable and Sustainable Neural Recommendation Models on Commodity CPU Hardware.
Anshumali Shrivastava, Vihan Lakshman, Tharun Medini, Nicholas Meisburger, Joshua Engels, David Torres Ramos, Benito Geordie, et al.
RecSys 2023.

Practical Near Neighbor Search via Group Testing.
Joshua Engels*, Benjamin Coleman*, and Anshumali Shrivastava
NeurIPS 2021: Spotlight talk - top 3%
Paper | Talk | Code

Missed one! How ballot layout and visual task strategy can interact to produce voting errors.
Joshua Engels, Xianni Wang, Michael D. Byrne
International Conference on Cognitive Modeling 2020.
Paper | Talk | Code | Blog Post

* indicates equal contribution

Blog Posts

Bananagrams is NP-complete
Have you ever wondered if Bananagrams is NP-complete? No? Well I think it is, and I’ll prove it!...

What is Set-of-Vector Search?
The set-of-vector search problem is an exciting and unexplored research problem. In our recent paper, we develop DESSERT,...

Simulating Voter Errors with ACT-R
Badly designed ballots may not seem like a pressing problem, but they have already swung multiple elections. For...