List पर वापस जाएँ
📄Papers

Generative and Malleable User Interfaces with Generative AI

Cao Y. et al.
2025-03

परिचय

CHI 2025 paper user tasks के आधार पर "generative and malleable user interfaces" बनाने के लिए AI इस्तेमाल करने का प्रस्ताव रखता है। Authors ने task-driven data model design किया, जिसमें LLMs user prompts parse करके UI specifications बनाते हैं और फिर उन्हें concrete interfaces से map करते हैं। Experiments दिखाते हैं कि यह method forms और visualizations जैसे interface elements dynamically बना सकती है और users natural language से interfaces बदल सकते हैं।

सारांश

Task-driven UI generation approach:

1. Core Concept: "Malleable" interfaces जिन्हें users natural language से नया आकार दे सकते हैं
2. Data Model: Task-driven architecture जिसमें LLMs user intent समझकर UI specs बनाते हैं
3. Dynamic Elements: Forms, visualizations और interactive components की generation support करता है
4. Natural Language Modification: Users conversational commands से interfaces को iteratively refine कर सकते हैं
5. Specification Mapping: Abstract UI specs को concrete interface implementations से map किया जाता है

मुख्य innovation: Task-centric prompting के जरिए user intent और interface realization के बीच gap को जोड़ता है

Tags

chi-2025malleable-uitask-drivenllm
मूल लेख पढ़ें

मिलते-जुलते लेख

📄Papers

ControlAnything: Generative UI and On-Demand Device Integration in Mixed Reality

November 2026 preprint generating both spatial controls and the connector code for physical devices when a Quest 3 wearer requests them. A coding agent tests connections over hand-written MIDI, Bluetooth, and key-press transports, then returns AR widgets, a per-frame hand program, or both.

generative-uimixed-realitydevice-integration
लेखक Bektur Ryskeldiev · 2026-11-05
और पढ़ें
📄Papers

Interface Quilt: Modifying Applications with Computer Use Agents and Generative UI

November 2026 preprint from Autodesk Research combining computer-use agents and GenUI to build persistent interface patches over existing applications. It recovers controls from rendered pixels, generates new interaction surfaces, and synchronizes them with the underlying app without requiring source code, APIs, or accessibility data.

generative-uicomputer-use-agentsinterface-patches
लेखक Qiu L. et al. · 2026-11-01
और पढ़ें
📄Papers

ABRA: Agent-Bound UI for Human-Agent Communication beyond Chat with Reusable Views

October 2026 EMNLP system demonstration separating reusable graph, table, text, and display views from task-specific interaction meanings. ABRA publishes these bindings as shared canvas state so users and other agents can inspect and invoke task-specific actions.

generative-uishared-canvasesinteraction-semantics
लेखक Kim S. G. and Kim H. · 2026-10-22
और पढ़ें

Generative UI और Intelligent UI resources का curated संग्रह।

बनाया गया ❤️ community द्वारा