العودة إلى القائمة
📄الأبحاث

Spatula: Exploring On-Demand In-Situ Interfaces and Interaction for Attribute Control

Li B. et al.
2026-07

حول

July 2026 HCI paper introducing Spatula, an LLM-powered system that generates context-aware controls directly on a motion-graphics canvas. Its elastic attribute control space supports progressive discovery, multiple levels of precision, semantic group editing, and new controls on demand.

الملخص

Why Spatula Adds New Signal:

1. In-situ generated controls: Places contextual widgets and direct-manipulation affordances on the creative canvas instead of in a separate chat or side panel
2. Elastic control space: Organizes interface generation around discoverability, resolution, scope, and expandability
3. Fine-grained refinement: Bridges high-level prompting with predictable parameter-level editing of generated content
4. Study-backed design: Reports a comparative user study with 12 participants across four interaction conditions
5. Broader applicability: Demonstrates that the plug-and-play approach can extend from motion graphics to web design and 3D modeling

الوسوم

on-demand-uicreative-toolsdirect-manipulationuser-study

مقالات ذات صلة

📄الأبحاث

Toward Frontier-Quality Declarative UI Generation at Small-Model Cost

September 2026 Harness4GenUI paper studying whether small language models can generate production-oriented A2UI from approved component catalogs. Across task-management and cloud-console domains, the authors compare training-data strategies, model sizes, catalog sizes, cost, latency, binding correctness, and rendered quality.

a2uismall-language-modelssupervised-fine-tuning
بواسطة Yang Y. et al. · 2026-09
اقرأ المزيد
📄الأبحاث

EvoGenUI-Bench: Evaluating Multi-Turn Generative UI Assistants

August 2026 benchmark testing whether LLM assistants can maintain one executable web interface as user requirements evolve. EvoGenUI-Bench contains 150 five-turn tasks across information presentation, stateful interaction, and tool-grounded external state, with browser-based evaluation over screenshots, DOM and source evidence, actor traces, and runtime logs.

generative-uimulti-turnbenchmark
بواسطة Peng Y. et al. · 2026-08
اقرأ المزيد
📄الأبحاث

Maru: Information Architecture for Aligned, Persistent Generative UI

August 2026 HCI paper introducing information architecture as shared state for Generative UI. Maru captures how users partition, order, name, and prioritize information, turns those choices into persistent rules, and applies them across successive interface generations instead of rebuilding structure from each prompt.

generative-uiinformation-architecturepersonalization
بواسطة Kim E. et al. · 2026-08
اقرأ المزيد

مجموعة منتقاة من مصادر Generative UI وGenUI وواجهات AI الديناميكية.

صُنع باستخدام ❤️ من قِبل المجتمع