I am a PhD candidate at the University of Toronto Department of Computer Science, doing research as part of the Vector Institute for AI. My research is currently focused on how discrete and recombinable concepts and skills can emerge in learning systems, particularly in the context of library learning systems.
The world is welcome to contact me at:
I look forwards to hearing from you!
My research interest is in how discrete and recombinable concepts and skills can emerge in learning systems; my current line of work focuses on library learning, i.e., tool creation. Given a system (typically an LLM) that solves a stream of tasks (e.g., by generating Python code), the question is whether we can learn reusable and composable tools (e.g., well designed, non-trivial, reusable Python functions). More broadly, I am interested in the larger problem of library learning for program synthesis, and how hierarchical skills can be built up over time.
Other research interests include multi-modal representations of text and vision, and model evaluation. I have done research measuring compositional generalization to new combinations of textual and visual primitives, as well as research into the evaluation of generative dialogue agents.
Library Learning Doesn’t: The Curious Case of the Single-Use “Library”
[paper, code]
Ian Berlot-Attwell, Frank Rudzicz, Xujie Si
Accepted to the 4th MATH-AI workshop at NeurIPS 2024
Attribute Diversity Determines the Systematicity Gap in VQA
[paper]
Ian Berlot-Attwell, A. Michael Carrell, Kumar Krishna Agrawal, Yash Sharma, Naomi Saphra
Accepted to EMNLP 2024
Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric [paper, code]
Ian Berlot-Attwell, Frank Rudzicz
Published: ConvAI Workshop at ACL 2022
Awarded best PhD Oral Presentation at UofT Graduate Language Research Day 2021
Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP [paper, code]
John Chen, Ian Berlot-Attwell, Xindi Wang, Safwan Hossain, Frank Rudzicz
Published: ClinicalNLP Workshop at EMNLP 2020
Awarded Best Short Paper at ClinicalNLP
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation [paper, code]
Kaustubh Dhole et al.
Published: NEJLT Vol. 9 No. 1, 2023
Neuro-Symbolic VQA: A review from the perspective of AGI desiderata [paper]
Ian Berlot-Attwell
arXiv preprint 2021
On the Use of Linguistic Features for the Evaluation of Generative Dialogue Systems [paper]
Ian Berlot-Attwell, Frank Rudzicz
arXiv preprint 2021
It has been my pleasure and privilege to serve as a sole course instructor at the University of Toronto.
Winter 2024 - CSC303: Social & Information networks, course website
University of Toronto, Department of Computer Science
Winter 2023 - CSC303: Social & Information networks, course website
University of Toronto, Department of Computer Science
Winter 2022 - CSC303: Social & Information networks, course website
University of Toronto, Department of Computer Science
Winter 2021 - CSC303: Social & Information networks, course website
University of Toronto, Department of Computer Science
Summer 2021 - CSC148: Introduction to Computer Science
University of Toronto, Department of Computer Science
Delivered tutorials, held office hours, monitored discussion board.
Summer 2020 - CSC148: Introduction to Computer Science
University of Toronto, Department of Computer Science
Prep-TA position, developing new programming assignments
Winter 2020 - CSC303: Social & Information networks, course website
University of Toronto, Department of Computer Science
Delivered tutorial mini-lectures, and performed grading.
I enjoy reading about methods to improve human learning and reasoning. Some methods include the use of computerized tools for learning, overcoming flaws in human reasoning through deliberate self reflection and training, and self-improvement through reflecting upon habits and developing new ones. In fiction, I tend towards science fiction or satirical fantasy (such as the works of Sir Terry Pratchett and J. Zachary Pike)
I also enjoy designing and building functioning machines and scale models out of Lego, which I have exhibited at Lego fan conventions. I sing, (passably) play the recorder, and can never say no to a game of Dungeons & Dragons :)
