Runway, an AI company, announced on Monday the release of a new model named Solaris. [1]
Solaris is an interface world model that allows users to create interactive websites and digital environments without requiring hard programming knowledge. [2] Researchers introduced Solaris, an interface world model that generates an interactive user interface directly, frame by frame, in response to user actions. [3] The Solaris model works by combining reasoning and rendering, where the model generates the interface frame by frame while a language model determines how the interface evolves. [4]
Users can interact with the generated digital environments by clicking on or dragging elements, which the model treats as conditioning signals to generate additional frames in real-time. [5] Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds. [6] The system combines autoregressive frame generation with few-step distillation and training on the model's own outputs to enable real-time generation while maintaining visual coherence. [7]
Runway's Solaris does not write the interface but generates the next frame after every click, according to the article. [8] The paper identifies interface world models as a step toward a new paradigm for software where interfaces are generated and adapted continuously around user intent. [9]Runway, una empresa de inteligencia artificial, anunció el lunes el lanzamiento de un nuevo modelo llamado Solaris. [1]
Solaris es un modelo de mundo de interfaz que permite a los usuarios crear sitios web interactivos y entornos digitales sin requerir conocimientos sólidos de programación. [2] Los investigadores presentaron Solaris, un modelo de mundo de interfaz que genera directamente una interfaz de usuario interactiva, fotograma a fotograma, en respuesta a las acciones del usuario. [3] El modelo Solaris funciona combinando razonamiento y renderizado, donde el modelo genera la interfaz fotograma a fotograma mientras un modelo de lenguaje determina cómo evoluciona la interfaz. [4]
Los usuarios pueden interactuar con los entornos digitales generados haciendo clic o arrastrando elementos, lo que el modelo trata como señales de condicionamiento para generar fotogramas adicionales en tiempo real. [5] Solaris trata las interacciones del ratón como señales de condicionamiento y sintetiza autorregresivamente el estado visual resultante a velocidades interactivas. [6] El sistema combina la generación autorregresiva de fotogramas con destilación de pocos pasos y entrenamiento en las propias salidas del modelo para permitir la generación en tiempo real manteniendo la coherencia visual. [7]
Solaris de Runway no escribe la interfaz, sino que genera el siguiente fotograma después de cada clic, según el artículo. [8] El documento identifica los modelos de mundo de interfaz como un paso hacia un nuevo paradigma de software donde las interfaces se generan y adaptan continuamente en torno a la intención del usuario. [9]
Proof9 sources · 3 publishers
What this stands on
Runway, an AI company, announced on Monday the release of a new model named Solaris. · CNET
Solaris is an interface world model that allows users to create interactive websites and digital environments without requiring hard programming knowledge. · CNET
Researchers introduced Solaris, an interface world model that generates an interactive user interface directly, frame by frame, in response to user actions. · arXiv.org
The Solaris model works by combining reasoning and rendering, where the model generates the interface frame by frame while a language model determines how the interface evolves. · CNET
Users can interact with the generated digital environments by clicking on or dragging elements, which the model treats as conditioning signals to generate additional frames in real-time. · CNET
Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds. · arXiv.org
The system combines autoregressive frame generation with few-step distillation and training on the model's own outputs to enable real-time generation while maintaining visual coherence. · arXiv.org
Runway's Solaris does not write the interface but generates the next frame after every click, according to the article. · medium.com
The paper identifies interface world models as a step toward a new paradigm for software where interfaces are generated and adapted continuously around user intent. · arXiv.org
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Thursday, September 3, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world3 publishers reported the events across 3 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.