Bethia Sun
Hi! My name is Bethia. I’m a first year Computer Science and Engineering MPhil student at UNSW Sydney, advised by Yang Song and Maurice Pagnucco. Previously, I completed a dual B.S at the same institution in Mathematics and Computer Science.
I am driven by the core belief that computational models of intelligence should go beyond optimising arbitrary performance metrics and instead, aim to enhance cognitive plausibility. My research primarily focuses on building cognitively plausible models of intelligence grounded in theoretical formalism and mathematical rigor, and draws inspiration from a wide range of fields, including cognitive science, developmental psychology, and the philosophy of mind. Some keywords are: computational cognitive science, neurocompositional computing, tensor product representations, learning as Bayesian program induction, intrinsic curiosity, empiricism vs nativism, developmental psychology, causality, embodied learning. For a more detailed overview of the interests driving my current work and how they fit together, please see the interests section.
Outside of AI research, I enjoy literature and film, indulging my layperson’s interest in astronomy/cosmology (a manifestation of my teenage existential angst perhaps…?), snorkelling, and trying to confirm that the Skinnerian resposnse exists in my feline child.
I’m always happy to discuss a variety of random topics, so feel free to reach out if you’re interested in having a chat!
news
Oct 04, 2024 | I will be attending NeurIPS in-person this year. Please come say hi at my poster, or feel free to reach out if you’re Canada/US-based and would like to chat! |
---|---|
Sep 25, 2024 | I am excited to announce my first ever work, Soft Tensor Product Representations for Fully Continuous, Compositional Visual Representations, has been accepted at NeurIPS 2024! Thank you to my advisors for being supportive throughout. |
Aug 28, 2024 | I am on leave until the start of 2025. |