Назад к списку
💡Кейсы

Runway Solaris: Interfaces Generated Frame by Frame

Runway
2026-08-31

О материале

Runway's August 2026 research announcement presents an Interface World Model that generates interface frames in response to clicks, drags, and typing. A language model guides scene behavior while a distilled video model renders the interaction, exploring runtime GenUI beyond generated code or component catalogs.

Краткое содержание

Generating Interaction Directly in Pixels:

1. Action-conditioned rendering: Past user inputs condition subsequent frames, with natural-language prompts defining interaction behavior
2. Real-time architecture: Combines autoregressive frame generation, few-step distillation, and training on the model's own outputs
3. Reported evaluation: Runway compares screenshot reconstruction and collects pairwise interaction judgments from 250 participants across 30 examples; these are vendor-reported studies, not evidence of general task reliability
4. Research limits: Stable text, verified grounding, long-session coherence, accessibility, and software integration remain unresolved; the page invites early-access requests

Теги

generative-uiinterface-world-modelspixel-based-uireal-time-interactionruntime-ui
Открыть сайт

Похожие материалы

💡Кейсы

Google Tabletop: Collaborative Tools Generated for Groups

Google Labs' November 11, 2026 announcement introduces shared spaces that turn links, files, ideas, and prompts into interactive planning tools. Groups can use generated itineraries, polls, expense splitters, and tournament brackets together in real time, making this a case of collaborative use of generated applications.

generative-uicollaborative-toolsruntime-ui
от Roman Nurik, Google Labs · 2026-11-11
Открыть сайт
💡Кейсы

Google Maps in AI Studio: Prompt-to-App Geospatial Interfaces

Google's November 9, 2026 launch connects AI Studio's app generation to Maps Platform. Geospatial prompts configure relevant capabilities and demo credentials, producing live interactive map previews for store locators, route planners, and 3D tours. This is a design-time interface generation case backed by real location services.

generative-uidesign-time-uigoogle-ai-studio
от Abinaya Selvam and Mike Taylor-Cai, Google · 2026-11-09
Открыть сайт
💡Кейсы

Kaltura Dynamic UI: Multimedia Interfaces for Conversational Agents

Kaltura's November 5, 2026 announcement describes conversational agents assembling videos, presentations, galleries, and quizzes as dialogue evolves. This enterprise GenUI case combines avatar conversations with interfaces grounded in organizational content, adapting the presentation to a user's questions and progress.

generative-uiconversational-agentsmultimedia
от Kaltura · 2026-11-05
Открыть сайт

Подборка ресурсов по Generative UI, Intelligent UI, GenUI и генеративным интерфейсам.

Сделано с ❤️ сообществом