Focal Interest
Focal Interest

User interface

  1. Cerebra: Aligning Implicit Knowledge in Interactive SQL Authoring
    Cerebra aligns implicit knowledge between users and LLMs during SQL authoring by retrieving context from historical scripts and supporting iterative refinement.
  2. .plan-26-10: Streaming TESSERA working, biodiversity action papers, and FPL takes off
    Browser-based streaming interface for satellite embeddings demonstrates client-side geospatial analysis, raising programming paradigm questions for Earth observation workflows.
  3. SmartUI: Human-in-the-Loop Editable Interface Generation through Semantic Structures
    SmartUI enables human-in-the-loop UI generation through Figma integration, using structured semantic representations for editable, iterative design with 0.93 structure consistency.
  4. Beyond the Conversational Paradigm: Models, Design Principles, and Tools for Advancing the Spectrum of Human-LLM Interaction
    Explore how LLM interfaces extend beyond conversations to integrate graphical elements. Research reveals user preferences vary by task, expertise, and context, enabling adaptive hybrid interface.
  5. Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI
    Neural transparency interface for LLM chatbot design enabling users to anticipate model behaviors through mechanistic interpretability visualization of behavioral trait vectors.
  6. No Code, No Cloud: On-Device Mockup-to-Code with Lightweight Vision-Language AI
    Lightweight on-device vision-language model generating HTML from design mockups without cloud infrastructure, supporting private prototyping with 235M parameters achieving competitive results.
  7. AI jewelry platform enabled custom design, chat, and live pricing
    Full-stack e-commerce platform integrating generative AI for custom jewelry design, conversational intelligence with live commodity pricing, and real-time market data for heritage jewelry retailers.