Core Francisco Park
Ph.D. Candidate at Harvard Physics
corefranciscopark@g.harvard.edu
Cambridge, MA, USA
Hi! I’m Core Francisco Park (pronounced Corae), I am a 6th year graduate student at Harvard Physics.
Currently, I work on understanding AI systems using carefully designed experiments. For the last few month I’ve been running experiments with synthetic data to understand compositional generalization and in-context learning.
In the past, I worked on developing reliable and deployable ML tools and methods for the physical sciences. I define reliable and deployable in a more specific way than “good accuracy”:
- Reliable: The model should allow an uncertainty estimate.
- Deployable: The model should end up actually getting used instead of being archived after publication.
Given these principles, I worked on different real data problems with ML and statistics, ranging from studies of a brain smaller than a grain of salt to cosmic volumes and from theoretical studies to practical ones.
Feel free to ask me anything! -Core
latest news
Sep 27, 2024 | Our paper: “Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space” is accepted to NeurIPS 2024 as a Spotlight! |
---|---|
Jul 03, 2024 | Tunadorable made a video about our paper: “Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space” |
Jul 02, 2024 | I gave a talk about our project diff4stats at EAS 2024: “Probabilistic Completion of Astrophysical Fields for Robust Statistics with Diffusion Models” |
Jun 27, 2024 | Our paper “Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space” from our project concept_learning is on arxiv. |
Jun 20, 2024 | I gave a talk about our project vdm4cdm_3d at the AstroAI Workshop 2024: “3D probabilistic reconstruction of the local dark matter from galaxies” |