In Summary, I am...
academically astute.
Details
Details
research oriented.
📄 Research Papers
Abstract
In this thesis, A novel computational support system for analogical innovation is proposed that employs the cognitive mechanisms for chunking and recombination as mediums of interaction. Chunking involves identifying and extracting meaningful chunks or segments from a design problem into interactive tiles called magnets, while recombination involves combining these magnets to generate insightful questions that elicit divergent thinking.
To evaluate the effectiveness of the system, a within-subjects study involving 23 participants was conducted, comparing the proposed interface with a baseline. The study found that using chunking and recombination as interactive mechanisms helped prevent premature rejection of useful analogical leads, resulting in 4 times fewer ignored analogical leads. Participants were also found to make 12 times fewer changes to their decisions, given a minor increment in processing time in the order of 1.5 minutes.
Overall, these results suggested that our proposed intervention is an effective tool for facilitating the selection of beneficial analogies, fostering analogical innovation through computational support.
Zijian Ding, Arvind Srinivasan, Stephen MacNeil, and Joel Chan. 2023.
https://doi.org/10.48550/arXiv.2302.12832
Objective
Cross-domain analogical reasoning, a challenging creative ability, has received limited systematic exploration in the context of Large Language Models (LLMs). This paper investigates LLMs' potential to augment cross-domain analogical reasoning.
Contribution
Performed rigorous Qualitative coding for 200+ analogies to understand and make sense of the reformulation behaviours amongst participants, keeping track of what details were added or changed to the understanding of the design problem.
Frequent analogical reformulations, primarily adding information, positively correlated with helpfulness ratings. This suggests that LLMs can augment cross-domain analogical reasoning by generating analogical reformulations that are helpful to humans.
📽️ Research Presentations
Early Explorations
Prior to arriving at the current iteration of the stick-and-ball representation, ideated and tested different ways tennis data can be represented.
These representations also resulted in an early prototype that allowed for a matrix-like interactions
However, complex shot-by-shot analysis was difficult, hence, we explored a variation of our first approach of creating chord courts.
About the Client
The significant growth of University of Maryland's School of Information Science, has prompted the undergraduate iSchool advising committee to address the challenges and explore ways to enhance the advising process as they anticipate the addition of three more undergraduate programs.
Discovering the Disconnect
Following several hours of Affinity mapping, I built an identity model with the goal of finding crucial insights into the tensions that affected the iSchool advising workflow.
Through identity modelling, I uncovered that there was a mismatch between student and advisors' expectations.
startup tested.
🧑🏻💻 Industrial Internships
The Idea
Given the dynamic nature of a typical API surface, with every new addition, a page might need to be added, each with its own composition before being built.
This prototype instead defines a interface schema over the existing API surface to create a dynamic build-time code generator that automagically adds pages as the APIs change. The following are some screenshots.
Building to Empower
As an undergraduate, I worked on various projects during this role. I designed the logo and branding assets for a software called "GetMe Hub" and provided input to improve the application interface design for a user-friendly shopping experience. Additionally, I created marketing assets like flyers, pitch decks, and social media posts. Furthermore, I built a responsive, API-driven dashboard single-page application (SPA) to display usage metrics.
GetMe Hub's ambitious initiative of empowering small vendors to have an online presence, struck a chord with me.
🎒 Academic Internships
community driven.
🔥 Personal Projects
💡 Notable Contributions
tech curious.
The following are all things technology currently on my radar, categorised by exploration status and sorted by confidence in working with them.
🍳 Techniques
These are some Paradigms and Workflows of Software Design and Development I'm familiar with or curious to adopt.👆 Tap the card for more
🍳 Techniques
These are some Paradigms and Workflows of Software Design and Development I 🧭 explore and 🔬 experiment to become an 🏅 expert in them.
🧰 Tools
These are some tools I'm familiar with or curious to adopt.👆 Tap the card for more
🧰 Tools
These are some tools I 🧭 explore and 🔬 experiment to become an 🏅 expert in them.
🚀 Platforms
These are some platforms I'm familiar with or curious to adopt.👆 Tap the card for more
🚀 Platforms
These are some platforms I 🧭 explore and 🔬 experiment to become an 🏅 expert in them.
💻 Languages and Frameworks
These are some frameworks I'm familiar with or curious to adopt.👆 Tap the card for more
💻 Languages and Frameworks
These are some frameworks I 🧭 explore and 🔬 experiment to become an 🏅 expert in them.