Joshua Engels

Orcid: 0009-0008-6907-2236

According to our database1, Joshua Engels authored at least 21 papers between 2021 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Training on Documents About Monitoring Leads to CoT Obfuscation.
CoRR, May, 2026

Building Production-Ready Probes For Gemini.
CoRR, January, 2026

2025
CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search.
CoRR, July, 2025

Simple Mechanistic Explanations for Out-Of-Context Reasoning.
CoRR, July, 2025

The Singapore Consensus on Global AI Safety Research Priorities.
CoRR, June, 2025

Decomposing The Dark Matter of Sparse Autoencoders.
Trans. Mach. Learn. Res., 2025

The Geometry of Concepts: Sparse Autoencoder Feature Structure.
Entropy, 2025

Dense SAE Latents Are Features, Not Bugs.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Scaling Laws For Scalable Oversight.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Low-Rank Adapting Models for Sparse Autoencoders.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Efficient Dictionary Learning with Switch Sparse Autoencoders.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Not All Language Model Features Are One-Dimensionally Linear.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

PECANN: Parallel Efficient Clustering with Graph-Based Approximate Nearest Neighbor Search.
Proceedings of the 3rd Conference on Applied and Computational Discrete Algorithms, 2025

2024
Not All Language Model Features Are Linear.
CoRR, 2024

Approximate Nearest Neighbor Search with Window Filters.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Neural Networks on Commodity CPU Hardware.
CoRR, 2023

From Research to Production: Towards Scalable and Sustainable Neural Recommendation Models on Commodity CPU Hardware.
Proceedings of the 17th ACM Conference on Recommender Systems, 2023

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

BOLT: An Automated Deep Learning Framework for Training and Deploying Large-Scale Search and Recommendation Models on Commodity CPU Hardware.
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023

2021
Practical Near Neighbor Search via Group Testing.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021


  Loading...