Professional

Microsoft

Summer 2022 - Research Data Scientist Intern

• Replicated Imagen and built a demo website for analysis.

O'Reilly Publishing

Summer 2021 - Technical Reviewer

• Reviewed "Learning Algorithms" for technical correctness and clarity.

Google

Summer 2018 - Software Engineering Intern

• Constructed map reduce pipelines for data analysis to improve ads targeting.
• Designed and implemented clustering approach for improving ads targeting.

Microsoft

Fall 2017 - Research Intern

• Disambiguating statement structured as fact from those structured as opinion.
• Built a ranking system to show semantically similar statements to a query.

Google

Summer 2017 - Software Engineering Intern

• Improved advertisement platform DoubleClick’s recommendation system by implementing feature to automatically name customer entities.
• Used Java and Dart, built comprehensive tests and a configurable design.

Silicon Labs

Summer 2016 - Software Engineering Intern

• Built a fuzz-testing engine to test the security of the Thread protocol stack using Java.
• Developed internal plugin to test cache-performance of a micro-chip using C.

Imagitas

Summer 2015 - Software Engineering Intern

• Developed deployment scripts.
• Improved automatic test framework.

---

Publications

Conferences and Journals

1. Charles Lovering*, Jessica Forde*, George Konidaris, Ellie Pavlick, Michael Littman. Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex. Neurips, 2022. (*Equal contribution.)
2. Charles Lovering*, Jessica Forde*, Ellie Pavlick, Michael Littman. Where, When & Which Concepts Does AlphaZero Learn? AAAI, RLG Workshop, 2022. (*Equal contribution.)
3. Charles Lovering, Rohan Jha, Tal Linzen, Ellie Pavlick. Predicting Inductive Biases of Pre-Trained Models. ICLR, 2021. Github.
4. Rodica Neamtu, Ramoza Ahsan, Cuong Dinh Tri Nguyen, Charles Lovering, Elke A. Rundensteiner, and Gabor Sarkozy. "A General Approach For Supporting Time Series Matching using Multiple-Warped Distances." IEEE Transactions on Knowledge and Data Engineering (2020).
5. Charles Lovering, Anqi Lu, Cuong Nguyen, Huyen Nguyen, David Hurley, Emmanuel Agu. Fact or Fiction: ACM CSCW 2018.
6. Rodica Neamtu, Ramoza Ahsan, Elke Rundensteiner, Gabor Sarkozy, Eamonn Keogh, Cuong Nguyen, Charles Lovering: Generalized Dynamic Time Warping. IEEE International Conference on Data Engineering (ICDE) 2018.
7. Neamtu, R., Ahsan, R., Lovering, C., Nguyen, C., Rundensteiner, E., & Sarkozy, G. (2017, May). Interactive Time Series Analytics Powered by ONEX. In Proceedings of the 2017 ACM International Conference on Management of Data (pp. 1595-1598). ACM.
8. Nguyen, C., Lovering, C., & Neamtu, R. Ranked Time Series Matching by Interleaving Similarity Distances. 4th Workshop on Advances in Software and Hardware for Big Data to Knowledge Discovery 2017. IEEE Big Data 2017.

PrePrints

1. Scao, Teven Le, et al. "BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.". arXiv preprint arXiv:2211.05100 (2022).
2. Rohan Jha, Charles Lovering, Ellie Pavlick. Does Data Augmentation Improve Generalization in NLP? 2020. PREPRINT.
3. Charles Lovering, Ellie Pavlick. Self-play for Data Efficient Language Acquisition. 2020. PREPRINT.

Unpublished Work

• Interpretable Reinforcement Learning: Reimplementation of attention-based reinforcement learning.
• Listicles: A dataset drawn extracted from online listicles.

Posters

1. Rohan Jha, Charles Lovering, Ellie Pavlick. Do Adversarial Counterexamples help Generalization? New York Symposium for Natural Language Processing (2019).
2. Charles Lovering, Ellie Pavlick. Emergent Communication with Selfplay. New York Symposium for Natural Language Processing (2019).
3. Charles Lovering, Jake Whitehill. Why did they cite that? New England Machine Learning Day (NEML) 2018.
4. Cuong Nguyen, Charles Lovering. Ranked Time Series Matching by Interleaving Similarity Distances. New England Database Day (NEDB) 2018. MIT.
5. Charles Lovering, Cuong Nguyen. INSIGHT. Interactive Time Series Analytics System. MIT IEEE Undergraduate Conference for Research 2016.

---

Academics

Doctorate, 2018+ (Brown) - Natural Language Understanding

I am pursuing my PhD at Brown University (2018) working with Professor Pavlick.

Masters, 2017-18 (WPI) - Natural Language Understanding

Working with my master thesis advisor Professor Whitehill we developed machine learning models to find (extract) evidence for claims made in academic papers.

Undergraduate, 2016-18 (WPI) - Time Series Analysis

We developed a series of theoretical frameworks for time series analysis and search. We further implemented efficient systems demonstrating these concepts