ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation
Zijian "Jason" Ding
PhD Candidate
5th-year PhD candidate at University of Maryland, College Park.
8+ years of research in Human-Centered AI, 5+ years in Generative Models.
20+ publications at CHI, C&C, EMNLP, CSCW, UIST, IUI.
Towards AI as Colleagues: Multi-Agent System Improves Structured Professional Ideation
A multi-agent system that enhances structured professional ideation by enabling AI to act as collaborative colleagues.
SpatialBalancing: Designing an LLM-Powered Spatial Externalization Interface for Iterative Science Communication Writing
A co-writing tool combining spatial visualization with LLMs to balance scientific accuracy and narrative engagement in science communication.
kexue-fu
StreetDesignAI: A Multi-Persona Evaluation System for Inclusive Infrastructure Design
A multi-persona evaluation system enabling transportation designers to assess cycling infrastructure through diverse cyclist perspectives.
CareerPooler: AI-Powered Metaphorical Pool Simulation Improves Experience and Outcomes in Career Exploration
A GenAI-powered system using a pool-table metaphor to simulate career development as spatial and narrative interaction.
Towards Direct Intent Manipulation: Drag-Based Research Ideation, Evaluation and Evolution
Frontend Diffusion: Empowering Self-Representation of Junior Researchers and Designers with Agentic Workflows
Agentic workflows that empower junior researchers and designers to create self-representational frontends.
The Diagram is like Guardrails: Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation
An interactive shared representation that structures GenAI-assisted hypotheses exploration using diagram-based guardrails.
Can AI Prompt Humans? Multimodal Agents Prompt Players' Game Design Ideas
Multimodal agents that prompt players to generate game design ideas, exploring whether AI can effectively prompt humans.
