projects
Research artifacts, prototypes, and studies that make research questions concrete: build the artifact, study the friction, and keep the figure readable enough that someone can inspect the claim.
What Happened and Why?
A CHI 2026 workshop position paper about trace-guided micro-episodes and in-flow user explanations for product iteration in AI-supported design tools.
What to notice
- Trace data needs user intent.
- Micro-episodes capture why in flow.
HotSpot
A neural SDF optimization framework with a screened Poisson objective for more stable surface reconstruction.
What to notice
- Screened Poisson objectives stabilize SDF optimization.
- Surface reconstruction improves under noisy geometry.
DesignWeaver
A prompt-design workspace that surfaces visual dimensions so novices can make more deliberate product concepts.
What to notice
- Prompts become visible design dimensions.
- Novices compare and iterate deliberately.
Physion
A benchmark for testing whether vision models predict physical scene dynamics the way people do.
What to notice
- Models predict physical scene dynamics.
- Human judgments anchor plausibility.
HCI Spooder-Man
Double rejection, a Steam-style lab meme, and a small door into the nerdy Spooder-Verse.
What to notice
- Academic websites can scaffold remixable play.
- Assets and prompts help others join in.
Vibe-Coding a Research Portfolio
A reflective redesign of this website into a warmer, clearer research portfolio and a reusable design-heuristics guide for students.
What to notice
- Portfolio becomes a research argument.
- Heuristics become reusable design memory.
Not A Good Driver
A playful VRChat world experiment in virtual-world creation, social audience engagement, and AI-assisted prototyping.
What to notice
- VR worlds become social experiments.
- AI-assisted prototypes meet public play.
Context-Aware Encoding for LLMs
A tree-of-thoughts context encoding experiment for improving retrieval and long-document contextual understanding.
What to notice
- Tree structure organizes long context.
- Retrieval becomes easier to inspect.
GraphHSCN
A graph neural network architecture prototype for modeling long-range interactions in structured data.
What to notice
- Graph structure models long-range interactions.
- Prototype explores structured-data reasoning.
Interaction note: card opening pattern inspired by IKEA's PS 2026 collection story; adapted here for an academic project browser.