{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-08-31T19:40:22.779Z","headline":"Runway 发布 Solaris：首个界面世界模型，实时生成操作系统级交互界面","description":"Runway 推出 Solaris，这是其全新界面世界模型（Interface World Models）系列的首个模型。Solaris 能实时逐帧生成应用和网站界面，无需中间代码表示，直接以图像作为交互层，支持视觉化、动态响应和开放式交互。它还可用于训练智能体，使其适应不断变化的界面布局，而非局限于特定训练环境。","url":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","mainEntityOfPage":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","datePublished":"2026-08-31T17:03:47.000Z","dateModified":"2026-08-31T17:03:47.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://runwayml.com/news/research/introducing-solaris","https://aihot.virxact.com/items/cmthhmoi10e71rodmx6wngoz1"],"canonicalUrl":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","directAnswer":{"@type":"Answer","text":"Runway 发布 Solaris，称其为 Interface World Models 系列的首个模型。Solaris 可实时逐帧生成应用和网站界面，以图像作为交互层，并可用于训练智能体适应持续变化的界面布局。","url":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","dateCreated":"2026-08-31T17:03:47.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"Runway：News（网页） source article","url":"https://runwayml.com/news/research/introducing-solaris","datePublished":"2026-08-31T17:03:47.000Z","provider":{"@type":"Organization","name":"Runway：News（网页）","url":"https://runwayml.com/news/research/introducing-solaris"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmthhmoi10e71rodmx6wngoz1","datePublished":"2026-08-31T17:03:47.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmthhmoi10e71rodmx6wngoz1"}}],"aggregationSource":"Runway：News（网页）","originalPublisher":{"name":"Runway：News（网页）","url":"https://runwayml.com/news/research/introducing-solaris"},"geoDeepAnswer":null,"article":{"id":"cmthhmoi10e71rodmx6wngoz1","slug":"cmthhmoi10e71rodmx6wngoz1","url":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","title":"Runway 发布 Solaris：首个界面世界模型，实时生成操作系统级交互界面","title_en":"","summary":"Runway 推出 Solaris，这是其全新界面世界模型（Interface World Models）系列的首个模型。Solaris 能实时逐帧生成应用和网站界面，无需中间代码表示，直接以图像作为交互层，支持视觉化、动态响应和开放式交互。它还可用于训练智能体，使其适应不断变化的界面布局，而非局限于特定训练环境。","source":"Runway：News（网页）","sourceUrl":"https://runwayml.com/news/research/introducing-solaris","aiHotUrl":"https://aihot.virxact.com/items/cmthhmoi10e71rodmx6wngoz1","publishedAt":"2026-08-31T17:03:47.000Z","category":"行业动态","score":72,"selected":true,"articleBody":["Today, we're sharing Solaris : the first model in a new family of AI systems we call Interface World Models . Solaris starts with a question: what happens when an operating system generates apps and websites as you use them?","Every operating system, from early terminals to Linux and macOS, has dictated what's rendered on screen and what happens when a person or program acts on it. Applications get built on top, and stay fixed until someone pushes an update. Solaris instead renders that layer directly. It's a real-time interactive model that generates the interface itself, frame by frame. Every frame is synthesized as you interact, allowing the interface to respond continuously to your actions.","Design is more visual than ever, with pixel-perfect mockups and image models that can generate entire screens that are nearly indistinguishable from finished products. But images don’t run like a website or app. Every piece of software built today still requires a translation: the visual design must first be converted into an intermediate representation (e.g. code) before it can do anything.","That intermediate representation limits what an interface can be, and how it responds to human and agent interaction. Every behavior has to be explicitly defined and implemented ahead of time, so software ships as a lossy compression of the space of possible interactions, frozen before any user arrives. The same translation process also sacrifices visual fidelity. Once a design is reduced to a simplified representation, the interface can respond quickly, but only by giving up much of the richness of the original design.","Solaris handles rendering and interactions jointly, removing many of the tradeoffs we associate with design today. A single world model generates every frame and every response to user input, eliminating the need for an intermediate representation. Because there’s no conversion step, there’s no loss, and the entire frame becomes the interface.","We think Solaris opens up new ways of building websites, apps and other online interfaces. But it’s also a new way to train agents, in much more dynamic environments. Even the best LLMs today struggle to complete：https://arxiv.org/abs/2606.29537 basic computer use tasks, like booking a hotel or ordering groceries. Because text-based models are being trained to use coded interfaces, they tend to learn the specific layout they were trained on, and can’t adapt to a slightly different interface (say, two different hotel websites). By collapsing the space between action and response, Solaris lets agents train against interfaces that are constantly changing, and layouts that may never have existed before.","Solaris brings three new capabilities to software.","First, Solaris is entirely visual. When an image becomes the application itself, there is no need for a second implementation step hidden beneath the visuals that a user sees. Imagine browsing a virtual clothing store where the showroom itself is the interface. Using a single image of yourself as a reference, you can pick up a shirt from a rack, drag it onto yourself to try it on or rearrange the display as naturally as you would in a physical store.","Second, it is alive. Because the application is continuously rendered, it is always evolving rather than waiting for the next user action. Reflections shift with the lighting, and objects respond naturally as they're manipulated. A user can say something as simple as: \"Move the table so I can see how it looks\" or “Change the color of the couch. ” The result is software that feels less like navigating through scripted pages and more like interacting with a living environment.","Finally, it is open-ended. Traditional interfaces are limited to the interactions developers anticipated during development, but Solaris can support entirely different behaviors in the same scene, reacting to user interactions in real-time. This flexibility decouples the interface from predefined workflows, instead leaving the capabilities of the driving world model to determine what is possible.","Solaris turns an interface into an interactive experience rather than a sequence of pages. Instead of selecting options from menus, users interact directly with the scene itself. Building a salad is as simple as dragging ingredients into a bowl, with the interface responding naturally as each ingredient is added.","Digital interfaces are built on two systems, which until now have lived in different worlds.","We've traditionally thought of software interfaces as deterministic programs and world models as generators of visual content. An Interface World Model has to be both at once: a system that understands your intent while continuously rendering an interactive world around it.","Once you try to build one, three engineering challenges immediately appear:","Solaris is our bet that these conceptual and technical barriers can be overcome. We built it with three focuses: real-time interaction, coherence over an entire session and visual quality that holds at 720p.","Solaris builds on our Gen-4.5：https://runwayml.com/research/introducing-runway-gen-4.5 video generation model, which we adapted to (1) understand interaction and (2) respond in real time. It follows the path we opened with GWM-1：https://runwayml.com/research/introducing-runway-gwm-1, our general world model.","Learning interaction. Solaris treats user input as conditioning for the next frame, the same way it treats text or images. The model observes clicks, drags and other interactions as it generates, using them as signals for what comes next. Because the model only ever sees interactions that have already happened (never future ones), it learns the relationship between user actions and visual outcomes. This means that it knows what should happen when something is clicked, dragged or modified, without requiring those interactions to be explicitly programmed.","Running in real time. Standard video diffusion models refine an entire clip over dozens of denoising steps, a process that is far too slow for dynamic user interaction. We converted Solaris into a real-time engine in three stages. First, we taught it to generate frames autoregressively, with each frame depending only on what came before. Next, we distilled the many-step denoising process into just a few steps. Finally, we trained the fast model on its own outputs so visual quality remains stable over long interactions. The result generates frames at interactive speeds while preserving the visual quality of the original teacher model.","Reasoning and rendering. Solaris generates the interface one frame at a time, while a language model determines how that interface evolves. The LLM interprets user requests, decides when interactions should modify the current scene versus transition to a new one, defines the behaviors that make the world feel alive and produces the prompts that guide Solaris as it renders each state. Together, the language model and world model separate reasoning from rendering: one decides what the application should do next, while the other generates how that behavior appears and responds in real time.","Continuous generation. You provide a starting state (e.g. a brand environment or product scene) and the model streams frames in real time. As the user clicks, drags or types, those interactions are incorporated into the next generated frames, and the scene responds in place. There are no predefined screens and no templates to fall back on. Instead, text prompts specify what clicks, drags and other interactions mean in a particular scene.","Redefining the mouse. Once interactions are described in natural language instead of programmed, they no longer have to be fixed in advance. Every object in the scene can become a new kind of tool. Click on a cat, and your next clicks apply its fur color and texture to whatever you touch. Click on a painting, and you might begin drawing in its style.","Earlier, we argued that translating interfaces into an intermediate representation inevitably degrades information. To measure that loss, we tested how faithfully today's multimodal language models can recreate an interface from a screenshot.","To measure this, we evaluated state-of-the-art multimodal language models, including Claude Fable 5, on the task of recreating website interfaces from a single screenshot. We evaluate across a diverse collection of 30 interfaces, ranging from simpler plain webpages to image-heavy webpages and natural images, which evaluate different aspects of visual understanding.","We measure information preservation in two complementary ways. First, structural similarity (SSIM) compares the reconstructed interface to the original in place, capturing how faithfully the visual appearance is reproduced. Second, we compare each region of the original with its most similar region anywhere in the reconstruction using DINOv3 features, measuring whether the underlying visual content survives even when elements move or the layout changes.","Reconstruction fidelity across increasing visual complexity. Even as multimodal language models continue to improve, reconstruction quality consistently degrades as visual complexity increases, revealing the information lost when interfaces are translated through language.","Despite rapid progress in recent years, every language model loses information during reconstruction. Natural images are affected most because rich visual detail cannot be represented accurately in language. As interfaces become more complex, even small changes to text, layout or structure can fundamentally alter how the interface behaves.","Rather than translating an interface into language and reconstructing it again, Solaris operates directly on the visual interface itself. By eliminating the intermediate representation, it preserves the complete visual and semantic state of the interface from the very first frame.","Our reconstruction benchmark measures how much information is lost when an interface is translated into code. We next ask: given the same interface and the same user interaction, which approach produces the better result? Can a coded interface recreate the same sense of a living, responsive environment as an interface generated by an interface world model?","Comparisons. While both systems respond to the same interaction request, Solaris preserves the coherence of the entire scene, producing interactions that feel more natural and physically grounded.","To answer this, we compared Solaris against a state-of-the-art language model (Claude Opus 5). Both systems started from the same image and received the same interaction requests, and we recorded how each responded. We then conducted a user study with 250 participants across 30 interaction examples, collecting nearly 7,500 pairwise judgments. For each comparison, participants answered two questions: “Which result better follows the given instruction?” and “Which behaves more naturally within the scene?”","Participants preferred Solaris on both measures. For following the requested interaction, Solaris was preferred in 61% of comparisons compared to 24% for the coded result, while 13% were rated as equivalent. The difference was even larger for natural behavior, where Solaris was preferred in 71% of comparisons compared to 21% for the coded website, with 6% rated as equivalent.","The second result highlights the broader difference between the two approaches. A coded interface can often reproduce the requested change, but it treats the interaction as an isolated update to the interface. With Interface World Models, because the model already understands how objects, materials and environments behave, it can generate interactions that feel coherent within the scene rather than treating each UI action as an isolated element.","Solaris is strongest at ambient motion, click-and-drag interactions and scene transitions. Several important challenges remain:","These challenges reflect the current frontier of real-time generative models, and we expect them to improve alongside the underlying models themselves.","Solaris is an early step toward a new operating layer, and we see several new interaction patterns emerging.","We expect interface generation to follow the same trajectory as image and video generation: every model generation will become faster, more coherent, more controllable and more capable. The challenges that once made generated interfaces seem impractical now look increasingly like solvable engineering problems.","Solaris is our first Interface World Model, and we're excited to continue exploring what generated software can become, from richer interactions, stronger grounding and longer-lived experiences to entirely new kinds of interfaces that don't exist today. We’re working with key partners to launch Solaris publicly. Fill out the form below to request early access."],"articleImages":[{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/images/sanity/2026/08/082626-solaris-blogpost-thumbnail-2fe8ad11-4846-4ba2-bbbf-a8db3feaa725.png","alt":"Introducing Solaris","afterParagraph":0,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/4fb3347a9d96f294.png"},{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/assets/solaris-eval-reconstruction-strip-1.webp","alt":"A plain product webpage next to reconstructions by GPT-4o, Gemini 2.5 Pro and Fable 5","afterParagraph":21,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/7d17a664dae09f90.webp"},{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/assets/solaris-eval-reconstruction-strip-2.webp","alt":"An image-heavy event poster next to reconstructions by GPT-4o, Gemini 2.5 Pro and Fable 5","afterParagraph":21,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/f262079e0bdb9dcd.webp"},{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/assets/solaris-eval-reconstruction-strip-3.webp","alt":"A natural photo of a kitchen scene next to reconstructions by GPT-4o, Gemini 2.5 Pro and Fable 5","afterParagraph":21,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/554dc5329cc45ec1.webp"},{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/images/sanity/2026/08/image-24-5ae5c80a-9697-4ae5-8b74-b80b857483b2.png","alt":"","afterParagraph":23,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/178d08bb62900236.png"},{"sourceUrl":"https://d3phaj0sisr2ct.cloudfront.net/site/images/sanity/2026/08/image-25-d4f3e428-eecc-4752-b5cd-30b7898ace03.png","alt":"","afterParagraph":29,"url":"/media/articles/cmthhmoi10e71rodmx6wngoz1/bbfbf5f1693b15ba.png"}],"mediaStatus":"ok","articleBodyZh":["今天，我们分享 Solaris：它是我们称为界面世界模型（Interface World Models）的一类新型人工智能系统中的第一个模型。Solaris 从一个问题开始：当操作系统在你使用它时生成应用程序和网站，会发生什么？","从早期终端到 Linux 和 macOS，每一个操作系统都决定了屏幕上显示什么，以及当人或程序进行操作时会发生什么。应用程序建立在其上，并保持固定状态，直到有人推送更新。而 Solaris 则直接渲染这一层。它是一个实时交互模型，逐帧生成界面。每一帧在你交互时合成，使界面能够持续响应你的操作。","设计比以往更加视觉化，拥有像素级精确的模型和能够生成几乎与成品无异的整屏图像模型。但图像无法像网站或应用那样运行。今天构建的每一款软件仍然需要一个转换过程：视觉设计必须先被转换为中间表示（例如代码），才能发挥作用。","这种中间表示限制了界面的功能以及其对人类和智能体交互的响应方式。每一种行为都必须提前明确地定义和实现，因此软件就像可能交互空间的有损压缩，在用户到来之前就被冻结。相同的转换过程同样牺牲了视觉保真度。一旦设计被简化为中间表示，界面能够快速响应，但代价是丢失了原始设计中的很多丰富内容。","Solaris 将渲染和交互联合处理，消除了我们今天在设计中常见的很多折衷。单一的世界模型生成每一帧以及对用户输入的每一次响应，消除了对中间表示的需求。因为没有转换步骤，就不会有损失，整个帧本身就成为界面。","我们认为 Solaris 开辟了构建网站、应用程序和其他在线界面的新方法。但它同样也是训练代理的新方式，适用于更加动态的环境。即便是当今最先进的大型语言模型（LLM）也难以完成：https://arxiv.org/abs/2606.29537 基础的计算机使用任务，例如预订酒店或购买杂货。由于基于文本的模型被训练以使用编码接口，它们往往会学习训练时所使用的特定布局，无法适应略有不同的界面（比如两个不同的酒店网站）。通过缩短动作与反应之间的空间，Solaris 让代理可以在不断变化的界面和可能从未存在过的布局中进行训练。","Solaris 为软件带来了三项新功能。","首先，Solaris 完全以视觉为基础。当图像本身成为应用程序时，就无需在用户所见视觉背后进行第二次实现。想象在浏览一个虚拟服装店时，展厅本身就是界面。使用你自己的单张图像作为参考，你可以从衣架上拿起一件衬衫，将其拖到自己身上试穿，或像在实体店中一样自然地重新排列展示。","其次，它是生动的。由于应用程序是持续渲染的，它总是在演变，而不是等待下一次用户操作。反光随着光线而变化，物体在操作时自然反应。用户可以说一些简单的指令，例如：“移动桌子，这样我可以看看效果”或“改变沙发的颜色。” 结果是软件感觉不再是浏览脚本化页面，而更像是在与一个有生命的环境互动。","最后，它是开放的。传统界面只能实现开发者在开发时预想的交互，但 Solaris 可以在同一场景中支持完全不同的行为，实时响应用户交互。这种灵活性将界面从预定义工作流程中解耦，而是让驱动世界模型的能力决定可能性。","Solaris 将界面变成了一种互动体验，而不仅仅是一系列页面。用户不再仅从菜单中选择选项，而是直接与场景本身进行互动。制作沙拉就像将食材拖入碗中一样简单，每加入一种食材，界面都会自然地做出响应。","数字界面建立在两个系统之上，而这两个系统直到现在一直存在于不同的世界中。","我们传统上认为软件界面是确定性的程序，而世界模型是视觉内容的生成器。一个界面世界模型必须同时具备两者功能：既要理解你的意图，又要持续渲染一个围绕意图的互动世界。","一旦你尝试构建这样一个模型，就会立即出现三个工程挑战：","Solaris 是我们对这些概念性和技术性障碍能够被克服的一种赌注。我们在构建时，专注于三方面：实时交互、整个会话的一致性以及在 720p 下保持的视觉质量。","Solaris 基于我们的 Gen-4.5：https://runwayml.com/research/introducing-runway-gen-4.5 视频生成模型，我们对其进行了调整，使其可以 (1) 理解交互，(2) 实时响应。它沿用了我们在 GWM-1：https://runwayml.com/research/introducing-runway-gwm-1（我们的通用世界模型）中开辟的路径。","学习交互。Solaris 将用户输入视为下一个帧的条件，就像处理文本或图像一样。模型在生成时会观察点击、拖动及其他交互，将其作为下一步动作的信号。由于模型只会看到已经发生的交互（从不看到未来的交互），它可以学习用户操作与视觉结果之间的关系。这意味着它知道在点击、拖动或修改某些内容时应该发生什么，而无需显式编程这些交互。","实时运行。标准的视频扩散模型需要经过几十步去噪处理整个视频片段，这一过程对于动态用户交互来说过于缓慢。我们将 Solaris 转换为实时引擎，共分三阶段。首先，我们让它以自回归方式生成帧，每一帧只依赖于之前的内容。接着，我们将多步骤去噪过程提炼为仅几步。最后，我们在模型自身输出上进行训练，以确保长时间交互中视觉质量保持稳定。最终生成的帧既能达到交互速度，又保留了原始教师模型的视觉质量。","推理与渲染。Solaris 每次生成界面的一帧，同时语言模型决定该界面如何演变。大语言模型解读用户请求，决定交互何时应修改当前场景或转入新场景，定义让世界栩栩如生的行为，并生成指导 Solaris 渲染每一个状态的提示。语言模型与世界模型协作，将推理与渲染分开：一方决定应用程序接下来应该做什么，另一方生成这些行为的实时外观和反应。","连续生成。用户提供初始状态（例如品牌环境或产品场景），模型即时流式生成帧。随着用户点击、拖动或输入，这些交互会被整合到下一帧生成中，场景实时响应。没有预定义的屏幕，也没有备用模板。相反，文本提示指定点击、拖动及其他交互在特定场景中的含义。","重新定义鼠标。一旦交互以自然语言描述，而非通过编程进行，它们就无需事先固定。场景中的每个对象都可以成为一种全新的工具。点击猫咪，你的下一次点击会将它的毛色和质感应用到所触碰的任何物体。点击画作，你可能会开始以其风格绘画。","此前，我们提出将界面翻译为中间表示不可避免会导致信息损失。为了测量这一损失，我们测试了当今多模态语言模型从截图中重建界面的忠实度。","为了衡量这一点，我们评估了最先进的多模态语言模型，包括 Claude Fable 5，在从单张截图重建网站界面任务中的表现。我们在一个包含 30 个不同界面的多样化集合上进行评估，这些界面从简单的纯网页到图片密集型网页及自然图片不等，用于评估视觉理解的不同方面。","我们通过两种互补的方式衡量信息保留情况。首先，结构相似性（SSIM）将重建的界面与原版界面进行对比，以捕捉视觉外观的忠实再现程度。其次，我们使用 DINOv3 特征，将原界面的每个区域与重建中最相似的区域进行比较，测量即使元素移动或布局变化，底层视觉内容是否仍被保留。","随着视觉复杂性的增加，重建的保真度。即使多模态语言模型不断改进，随着视觉复杂性增加，重建质量仍会持续下降，揭示界面通过语言翻译时丢失的信息。","尽管近年来进展迅速，每种语言模型在重建过程中都会丢失信息。自然图片受到的影响最大，因为丰富的视觉细节无法在语言中准确表示。随着界面变得更复杂，即使是文本、布局或结构的微小变化也可能从根本上改变界面的行为。","Solaris 并不是将界面翻译成语言再重建，而是直接在视觉界面本身上操作。通过消除中间表示，它从第一帧开始就保留了界面的完整视觉和语义状态。","我们的重建基准测试衡量了当界面被翻译成代码时信息丢失的程度。接下来我们要问：在相同界面和相同用户交互的情况下，哪种方法能产生更好的结果？一个编码的界面能否重现与由界面世界模型生成的界面相同的生动且响应式的环境感？","比较。虽然两种系统都对相同的交互请求作出响应，但 Solaris 保持了整个场景的一致性，产生的交互更加自然且具有物理基础。","为了回答这个问题，我们将Solaris与最先进的语言模型（Claude Opus 5）进行了比较。两个系统都从同一幅图像开始，并接收相同的交互请求，我们记录了每个系统的响应情况。然后，我们进行了用户研究，涉及250名参与者和30个交互示例，收集了近7,500条成对评价。在每次比较中，参与者回答了两个问题：“哪个结果更好地遵循了给定的指令？”和“哪个在场景中表现得更自然？”","参与者在两个指标上都更倾向于Solaris。在遵循请求的交互方面，Solaris在61%的比较中被偏好，而编码结果为24%，有13%被评为相同。在自然行为方面，差距更大，Solaris在71%的比较中被偏好，而编码网站为21%，有6%被评为相同。","第二个结果突出了两种方法之间的更广泛差异。编码界面往往可以再现请求的更改，但它将交互视为界面的孤立更新。而使用接口世界模型，由于模型已经理解了对象、材料和环境的行为，它可以生成在场景中感觉连贯的交互，而不是将每个UI操作视为孤立元素。","Solaris在环境运动、点击拖拽交互和场景切换方面最具优势。仍存在若干重要挑战：","这些挑战反映了实时生成模型的当前前沿，我们预计它们将随着底层模型自身的改进而得到提升。","Solaris是迈向新操作层的早期一步，我们看到几种新的交互模式正在出现。","我们预计界面生成将遵循与图像和视频生成相同的轨迹：每一代模型生成将变得更快、更连贯、更可控、更强大。曾经让生成界面看似不切实际的挑战，现在越来越像是可解决的工程问题。","Solaris 是我们的第一个界面世界模型，我们很高兴继续探索生成式软件可能的发展，从更丰富的交互、更强的基础和更持久的体验，到今天不存在的全新界面类型。我们正在与关键合作伙伴合作，公开发布 Solaris。请填写下面的表格以申请提前访问。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Runway 发布 Solaris，称其为 Interface World Models 系列的首个模型。Solaris 可实时逐帧生成应用和网站界面，以图像作为交互层，并可用于训练智能体适应持续变化的界面布局。","background":"来源称，现有软件通常需要先将视觉设计转换为代码等中间表示，再实现交互。Solaris 将渲染与交互结合，由模型生成每一帧及对用户输入的响应，取消这一中间转换环节。","viewpoint":"Aioga 判断：Solaris 的核心变化不只是生成界面视觉，而是试图把界面本身变成持续响应的交互层。其价值仍需结合实际使用效果和智能体适应能力进一步观察。","implications":"可能影响：软件界面的构建方式和智能体训练环境都可能出现新的路径，但这不代表传统代码表示会被取代，也不足以证明动态生成界面已经具备稳定的产品化能力。","nextStep":"后续观察：应关注 Solaris 的实际可用范围、交互稳定性、响应质量，以及智能体在不同且持续变化的界面中能否保持可靠完成任务的表现。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-08-31T17:24:23.274Z","sourceHash":"7e7bff9c335a06bf","review":{"approved":true,"groundedness":96,"clarity":93,"duplicationRisk":18,"blockingIssues":[],"notes":["“Aioga 判断”明确标注为观点，未将其冒充为来源事实。","“可能影响”“不代表”“不足以证明”及“后续观察”均使用了适当限定语，未把推测性影响表述为已证实结论。","“以图像作为交互层”可进一步改为“以生成的界面帧作为交互层”，但属于可选措辞优化，不影响审核结论。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","editorial-labels","inference-boundary","low-source-overlap","no-html","independent-ai-review"]}},"tags":["行业动态","Runway：News（网页）"],"translations":{"zh-CN":{"title":"Runway 发布 Solaris：首个界面世界模型，实时生成操作系统级交互界面","summary":"Runway 推出 Solaris，这是其全新界面世界模型（Interface World Models）系列的首个模型。Solaris 能实时逐帧生成应用和网站界面，无需中间代码表示，直接以图像作为交互层，支持视觉化、动态响应和开放式交互。它还可用于训练智能体，使其适应不断变化的界面布局，而非局限于特定训练环境。","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway 发布 Solaris：首个界面世界模型，实时生成操作系统级交互界面 - Aioga AI资讯","description":"Runway 推出 Solaris，这是其全新界面世界模型（Interface World Models）系列的首个模型。Solaris 能实时逐帧生成应用和网站界面，无需中间代码表示，直接以图像作为交互层，支持视觉化、动态响应和开放式交互。它还可用于训练智能体，使其适应不断变化的界面布局，而非局限于特定训练环境。","url":"https://www.aioga.com/news/cmthhmoi10e71rodmx6wngoz1/","articleBody":["今天，我们分享 Solaris：它是我们称为界面世界模型（Interface World Models）的一类新型人工智能系统中的第一个模型。Solaris 从一个问题开始：当操作系统在你使用它时生成应用程序和网站，会发生什么？","从早期终端到 Linux 和 macOS，每一个操作系统都决定了屏幕上显示什么，以及当人或程序进行操作时会发生什么。应用程序建立在其上，并保持固定状态，直到有人推送更新。而 Solaris 则直接渲染这一层。它是一个实时交互模型，逐帧生成界面。每一帧在你交互时合成，使界面能够持续响应你的操作。","设计比以往更加视觉化，拥有像素级精确的模型和能够生成几乎与成品无异的整屏图像模型。但图像无法像网站或应用那样运行。今天构建的每一款软件仍然需要一个转换过程：视觉设计必须先被转换为中间表示（例如代码），才能发挥作用。","这种中间表示限制了界面的功能以及其对人类和智能体交互的响应方式。每一种行为都必须提前明确地定义和实现，因此软件就像可能交互空间的有损压缩，在用户到来之前就被冻结。相同的转换过程同样牺牲了视觉保真度。一旦设计被简化为中间表示，界面能够快速响应，但代价是丢失了原始设计中的很多丰富内容。","Solaris 将渲染和交互联合处理，消除了我们今天在设计中常见的很多折衷。单一的世界模型生成每一帧以及对用户输入的每一次响应，消除了对中间表示的需求。因为没有转换步骤，就不会有损失，整个帧本身就成为界面。","我们认为 Solaris 开辟了构建网站、应用程序和其他在线界面的新方法。但它同样也是训练代理的新方式，适用于更加动态的环境。即便是当今最先进的大型语言模型（LLM）也难以完成：https://arxiv.org/abs/2606.29537 基础的计算机使用任务，例如预订酒店或购买杂货。由于基于文本的模型被训练以使用编码接口，它们往往会学习训练时所使用的特定布局，无法适应略有不同的界面（比如两个不同的酒店网站）。通过缩短动作与反应之间的空间，Solaris 让代理可以在不断变化的界面和可能从未存在过的布局中进行训练。","Solaris 为软件带来了三项新功能。","首先，Solaris 完全以视觉为基础。当图像本身成为应用程序时，就无需在用户所见视觉背后进行第二次实现。想象在浏览一个虚拟服装店时，展厅本身就是界面。使用你自己的单张图像作为参考，你可以从衣架上拿起一件衬衫，将其拖到自己身上试穿，或像在实体店中一样自然地重新排列展示。","其次，它是生动的。由于应用程序是持续渲染的，它总是在演变，而不是等待下一次用户操作。反光随着光线而变化，物体在操作时自然反应。用户可以说一些简单的指令，例如：“移动桌子，这样我可以看看效果”或“改变沙发的颜色。” 结果是软件感觉不再是浏览脚本化页面，而更像是在与一个有生命的环境互动。","最后，它是开放的。传统界面只能实现开发者在开发时预想的交互，但 Solaris 可以在同一场景中支持完全不同的行为，实时响应用户交互。这种灵活性将界面从预定义工作流程中解耦，而是让驱动世界模型的能力决定可能性。","Solaris 将界面变成了一种互动体验，而不仅仅是一系列页面。用户不再仅从菜单中选择选项，而是直接与场景本身进行互动。制作沙拉就像将食材拖入碗中一样简单，每加入一种食材，界面都会自然地做出响应。","数字界面建立在两个系统之上，而这两个系统直到现在一直存在于不同的世界中。","我们传统上认为软件界面是确定性的程序，而世界模型是视觉内容的生成器。一个界面世界模型必须同时具备两者功能：既要理解你的意图，又要持续渲染一个围绕意图的互动世界。","一旦你尝试构建这样一个模型，就会立即出现三个工程挑战：","Solaris 是我们对这些概念性和技术性障碍能够被克服的一种赌注。我们在构建时，专注于三方面：实时交互、整个会话的一致性以及在 720p 下保持的视觉质量。","Solaris 基于我们的 Gen-4.5：https://runwayml.com/research/introducing-runway-gen-4.5 视频生成模型，我们对其进行了调整，使其可以 (1) 理解交互，(2) 实时响应。它沿用了我们在 GWM-1：https://runwayml.com/research/introducing-runway-gwm-1（我们的通用世界模型）中开辟的路径。","学习交互。Solaris 将用户输入视为下一个帧的条件，就像处理文本或图像一样。模型在生成时会观察点击、拖动及其他交互，将其作为下一步动作的信号。由于模型只会看到已经发生的交互（从不看到未来的交互），它可以学习用户操作与视觉结果之间的关系。这意味着它知道在点击、拖动或修改某些内容时应该发生什么，而无需显式编程这些交互。","实时运行。标准的视频扩散模型需要经过几十步去噪处理整个视频片段，这一过程对于动态用户交互来说过于缓慢。我们将 Solaris 转换为实时引擎，共分三阶段。首先，我们让它以自回归方式生成帧，每一帧只依赖于之前的内容。接着，我们将多步骤去噪过程提炼为仅几步。最后，我们在模型自身输出上进行训练，以确保长时间交互中视觉质量保持稳定。最终生成的帧既能达到交互速度，又保留了原始教师模型的视觉质量。","推理与渲染。Solaris 每次生成界面的一帧，同时语言模型决定该界面如何演变。大语言模型解读用户请求，决定交互何时应修改当前场景或转入新场景，定义让世界栩栩如生的行为，并生成指导 Solaris 渲染每一个状态的提示。语言模型与世界模型协作，将推理与渲染分开：一方决定应用程序接下来应该做什么，另一方生成这些行为的实时外观和反应。","连续生成。用户提供初始状态（例如品牌环境或产品场景），模型即时流式生成帧。随着用户点击、拖动或输入，这些交互会被整合到下一帧生成中，场景实时响应。没有预定义的屏幕，也没有备用模板。相反，文本提示指定点击、拖动及其他交互在特定场景中的含义。","重新定义鼠标。一旦交互以自然语言描述，而非通过编程进行，它们就无需事先固定。场景中的每个对象都可以成为一种全新的工具。点击猫咪，你的下一次点击会将它的毛色和质感应用到所触碰的任何物体。点击画作，你可能会开始以其风格绘画。","此前，我们提出将界面翻译为中间表示不可避免会导致信息损失。为了测量这一损失，我们测试了当今多模态语言模型从截图中重建界面的忠实度。","为了衡量这一点，我们评估了最先进的多模态语言模型，包括 Claude Fable 5，在从单张截图重建网站界面任务中的表现。我们在一个包含 30 个不同界面的多样化集合上进行评估，这些界面从简单的纯网页到图片密集型网页及自然图片不等，用于评估视觉理解的不同方面。","我们通过两种互补的方式衡量信息保留情况。首先，结构相似性（SSIM）将重建的界面与原版界面进行对比，以捕捉视觉外观的忠实再现程度。其次，我们使用 DINOv3 特征，将原界面的每个区域与重建中最相似的区域进行比较，测量即使元素移动或布局变化，底层视觉内容是否仍被保留。","随着视觉复杂性的增加，重建的保真度。即使多模态语言模型不断改进，随着视觉复杂性增加，重建质量仍会持续下降，揭示界面通过语言翻译时丢失的信息。","尽管近年来进展迅速，每种语言模型在重建过程中都会丢失信息。自然图片受到的影响最大，因为丰富的视觉细节无法在语言中准确表示。随着界面变得更复杂，即使是文本、布局或结构的微小变化也可能从根本上改变界面的行为。","Solaris 并不是将界面翻译成语言再重建，而是直接在视觉界面本身上操作。通过消除中间表示，它从第一帧开始就保留了界面的完整视觉和语义状态。","我们的重建基准测试衡量了当界面被翻译成代码时信息丢失的程度。接下来我们要问：在相同界面和相同用户交互的情况下，哪种方法能产生更好的结果？一个编码的界面能否重现与由界面世界模型生成的界面相同的生动且响应式的环境感？","比较。虽然两种系统都对相同的交互请求作出响应，但 Solaris 保持了整个场景的一致性，产生的交互更加自然且具有物理基础。","为了回答这个问题，我们将Solaris与最先进的语言模型（Claude Opus 5）进行了比较。两个系统都从同一幅图像开始，并接收相同的交互请求，我们记录了每个系统的响应情况。然后，我们进行了用户研究，涉及250名参与者和30个交互示例，收集了近7,500条成对评价。在每次比较中，参与者回答了两个问题：“哪个结果更好地遵循了给定的指令？”和“哪个在场景中表现得更自然？”","参与者在两个指标上都更倾向于Solaris。在遵循请求的交互方面，Solaris在61%的比较中被偏好，而编码结果为24%，有13%被评为相同。在自然行为方面，差距更大，Solaris在71%的比较中被偏好，而编码网站为21%，有6%被评为相同。","第二个结果突出了两种方法之间的更广泛差异。编码界面往往可以再现请求的更改，但它将交互视为界面的孤立更新。而使用接口世界模型，由于模型已经理解了对象、材料和环境的行为，它可以生成在场景中感觉连贯的交互，而不是将每个UI操作视为孤立元素。","Solaris在环境运动、点击拖拽交互和场景切换方面最具优势。仍存在若干重要挑战：","这些挑战反映了实时生成模型的当前前沿，我们预计它们将随着底层模型自身的改进而得到提升。","Solaris是迈向新操作层的早期一步，我们看到几种新的交互模式正在出现。","我们预计界面生成将遵循与图像和视频生成相同的轨迹：每一代模型生成将变得更快、更连贯、更可控、更强大。曾经让生成界面看似不切实际的挑战，现在越来越像是可解决的工程问题。","Solaris 是我们的第一个界面世界模型，我们很高兴继续探索生成式软件可能的发展，从更丰富的交互、更强的基础和更持久的体验，到今天不存在的全新界面类型。我们正在与关键合作伙伴合作，公开发布 Solaris。请填写下面的表格以申请提前访问。"]},"en":{"title":"Runway Releases Solaris: The First Interface World Model, Real-Time Generation of OS-Level Interactive Interfaces","summary":"Runway has launched Solaris, the first model in its new Interface World Models series. Solaris can generate application and website interfaces frame by frame in real time, without any intermediate code representation, directly using images as the interaction layer. It supports visualization, dynamic responses, and open-ended interactions. It can also be used to train agents to adapt to constantly changing interface layouts, rather than being limited to specific training environments.","category":"Industry","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway Releases Solaris: The First Interface World Model, Real-Time Generation of OS-Level Interactive Interfaces - Aioga AI News","description":"Runway has launched Solaris, the first model in its new Interface World Models series. Solaris can generate application and website interfaces frame by frame in real time, without...","url":"https://www.aioga.com/en/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:21:58.786Z"},"ja":{"title":"Runway、Solaris を発表：初のインターフェースワールドモデル、リアルタイムでOSレベルのインタラクティブインターフェースを生成","summary":"Runway は Solaris を発表しました。これは新しいインターフェースワールドモデル（Interface World Models）シリーズの初のモデルです。Solaris はアプリやウェブサイトのインターフェースをフレームごとにリアルタイムで生成でき、中間コード表現を必要とせず、画像を直接インタラクション層として使用できます。ビジュアル化、動的レスポンス、オープンエンドのインタラクションに対応しており、インテリジェントエージェントのトレーニングにも使用可能で、特定のトレーニング環境に限定されず、変化するインターフェースレイアウトに適応できます。","category":"業界動向","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway、Solaris を発表：初のインターフェースワールドモデル、リアルタイムでOSレベルのインタラクティブインターフェースを生成 - Aioga AIニュース","description":"Runway は Solaris を発表しました。これは新しいインターフェースワールドモデル（Interface World Models）シリーズの初のモデルです。Solaris はアプリやウェブサイトのインターフェースをフレームごとにリアルタイムで生成でき、中間コード表現を必要とせず、画像を直接インタラクション層として使用できます。ビジュアル化、動的レス...","url":"https://www.aioga.com/ja/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:00.140Z"},"ko":{"title":"Runway, Solaris 출시: 최초 인터페이스 월드 모델, 실시간 운영 체제 수준의 인터페이스 생성","summary":"Runway가 Solaris를 발표했습니다. 이는 새 인터페이스 월드 모델(Interface World Models) 시리즈의 첫 번째 모델입니다. Solaris는 중간 코드 표현 없이 애플리케이션과 웹사이트 인터페이스를 실시간으로 프레임 단위로 생성할 수 있으며, 인터랙션 레이어를 이미지로 직접 제공하고, 시각적, 동적 응답 및 개방형 상호작용을 지원합니다. 또한 스마트 에이전트 훈련에 사용되어 특정 훈련 환경에 국한되지 않고 변화하는 인터페이스 레이아웃에 적응할 수 있게 합니다.","category":"업계 동향","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway, Solaris 출시: 최초 인터페이스 월드 모델, 실시간 운영 체제 수준의 인터페이스 생성 - Aioga AI 뉴스","description":"Runway가 Solaris를 발표했습니다. 이는 새 인터페이스 월드 모델(Interface World Models) 시리즈의 첫 번째 모델입니다. Solaris는 중간 코드 표현 없이 애플리케이션과 웹사이트 인터페이스를 실시간으로 프레임 단위로 생성할 수 있으며, 인터랙션 레이어를 이미지로 직접 제공하고, 시각적, 동적...","url":"https://www.aioga.com/ko/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:07.037Z"},"es":{"title":"Runway lanza Solaris: el primer modelo de mundo de interfaz, genera interfaces de sistema operativo en tiempo real","summary":"Runway presenta Solaris, el primer modelo de su nueva serie de modelos de mundo de interfaz (Interface World Models). Solaris puede generar en tiempo real, cuadro por cuadro, interfaces de aplicaciones y sitios web, sin necesidad de una representación intermedia en código, utilizando directamente imágenes como capa de interacción, soportando visualización, respuesta dinámica e interacción abierta. También se puede usar para entrenar agentes inteligentes, permitiéndoles adaptarse a diseños de interfaz en constante cambio, en lugar de estar limitados a entornos de entrenamiento específicos.","category":"Industria","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway lanza Solaris: el primer modelo de mundo de interfaz, genera interfaces de sistema operativo en tiempo real - Aioga Noticias de IA","description":"Runway presenta Solaris, el primer modelo de su nueva serie de modelos de mundo de interfaz (Interface World Models). Solaris puede generar en tiempo real, cuadro por cuadro, inter...","url":"https://www.aioga.com/es/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:05.074Z"},"fr":{"title":"Runway lance Solaris : le premier modèle de monde d'interface, générant en temps réel des interfaces interactives au niveau du système d'exploitation","summary":"Runway présente Solaris, le premier modèle de sa nouvelle série de modèles de monde d'interface (Interface World Models). Solaris peut générer en temps réel, image par image, des interfaces d'applications et de sites web, sans représentation intermédiaire en code, en utilisant directement l'image comme couche d'interaction, avec prise en charge de la visualisation, de la réponse dynamique et de l'interaction ouverte. Il peut également être utilisé pour entraîner des agents afin qu'ils s'adaptent à des dispositions d'interface en constante évolution, plutôt que d'être limités à un environnement d'entraînement spécifique.","category":"Industrie","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway lance Solaris : le premier modèle de monde d'interface, générant en temps réel des interfaces interactives au niveau du système d'exploitation - Aioga Actualités IA","description":"Runway présente Solaris, le premier modèle de sa nouvelle série de modèles de monde d'interface (Interface World Models). Solaris peut générer en temps réel, image par image, des i...","url":"https://www.aioga.com/fr/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:12.400Z"},"de":{"title":"Runway veröffentlicht Solaris: Erstes Interface-Weltmodell, das Betriebssystemebenen-Interaktionsoberflächen in Echtzeit erzeugt","summary":"Runway stellt Solaris vor, das erste Modell seiner neuen Interface-Weltmodell-Serie (Interface World Models). Solaris kann Anwendungen und Website-Oberflächen in Echtzeit Frame für Frame generieren, ohne mittleren Code zu benötigen, direkt als Bildschicht für die Interaktion, unterstützt visuelle Darstellung, dynamische Reaktionen und offene Interaktion. Es kann auch verwendet werden, um Agenten zu trainieren, damit sie sich an sich ständig ändernde Oberflächenlayouts anpassen, anstatt auf bestimmte Trainingsumgebungen beschränkt zu sein.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway veröffentlicht Solaris: Erstes Interface-Weltmodell, das Betriebssystemebenen-Interaktionsoberflächen in Echtzeit erzeugt - Aioga KI-News","description":"Runway stellt Solaris vor, das erste Modell seiner neuen Interface-Weltmodell-Serie (Interface World Models). Solaris kann Anwendungen und Website-Oberflächen in Echtzeit Frame für...","url":"https://www.aioga.com/de/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:11.408Z"},"pt-BR":{"title":"Runway lança Solaris: o primeiro modelo de mundo de interface, gerando em tempo real interfaces de nível de sistema operacional","summary":"Runway lançou Solaris, o primeiro modelo de sua nova série de Modelos de Mundo de Interface (Interface World Models). Solaris consegue gerar quadro a quadro interfaces de aplicativos e sites em tempo real, sem necessidade de representação intermediária em código, usando diretamente imagens como camada de interação, suportando visualização, resposta dinâmica e interação aberta. Ele também pode ser usado para treinar agentes, permitindo que se adaptem a layouts de interface em constante mudança, em vez de se limitar a ambientes de treinamento específicos.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway lança Solaris: o primeiro modelo de mundo de interface, gerando em tempo real interfaces de nível de sistema operacional - Aioga Notícias de IA","description":"Runway lançou Solaris, o primeiro modelo de sua nova série de Modelos de Mundo de Interface (Interface World Models). Solaris consegue gerar quadro a quadro interfaces de aplicativ...","url":"https://www.aioga.com/pt-BR/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:17.034Z"},"ru":{"title":"Runway выпустила Solaris: первая модель мирового интерфейса, создающая операционные интерфейсы в реальном времени","summary":"Runway представила Solaris, первую модель в своей новой серии моделей мирового интерфейса (Interface World Models). Solaris может создавать интерфейсы приложений и веб-сайтов кадр за кадром в реальном времени, без промежуточного кодового представления, напрямую используя изображения в качестве уровня взаимодействия, поддерживает визуализацию, динамическую реакцию и открытое взаимодействие. Также её можно использовать для обучения агентов, чтобы они адаптировались к постоянно меняющимся макетам интерфейсов, а не ограничивались конкретной средой обучения.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway выпустила Solaris: первая модель мирового интерфейса, создающая операционные интерфейсы в реальном времени - Aioga Новости ИИ","description":"Runway представила Solaris, первую модель в своей новой серии моделей мирового интерфейса (Interface World Models). Solaris может создавать интерфейсы приложений и веб-сайтов кадр...","url":"https://www.aioga.com/ru/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:16.531Z"},"ar":{"title":"Runway تصدر Solaris: أول نموذج للعالم الواجهاتي، يولد واجهات تفاعلية على مستوى نظام التشغيل بشكل فوري","summary":"أطلقت Runway Solaris، وهو أول نموذج ضمن سلسلة نماذج العالم الواجهاتي (Interface World Models). يستطيع Solaris توليد واجهات التطبيقات والمواقع إطارًا بإطار بشكل فوري، دون الحاجة إلى أي تمثيل برمجي وسيط، مباشرة كصور لتكون طبقة تفاعلية، ويدعم التفاعل البصري، الاستجابة الديناميكية، والتفاعل المفتوح. يمكن استخدامه أيضًا لتدريب الوكلاء ليتكيفوا مع تغييرات تخطيط الواجهة المستمرة، دون التقيد ببيئة تدريب محددة.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway تصدر Solaris: أول نموذج للعالم الواجهاتي، يولد واجهات تفاعلية على مستوى نظام التشغيل بشكل فوري - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت Runway Solaris، وهو أول نموذج ضمن سلسلة نماذج العالم الواجهاتي (Interface World Models). يستطيع Solaris توليد واجهات التطبيقات والمواقع إطارًا بإطار بشكل فوري، دون الحاجة إلى...","url":"https://www.aioga.com/ar/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:21.264Z"},"hi":{"title":"Runway ने Solaris लॉन्च किया: पहला इंटरफ़ेस वर्ल्ड मॉडल, रीयल-टाइम ऑपरेटिंग सिस्टम स्तर की इंटरेक्टिव इंटरफ़ेस जनरेशन","summary":"Runway ने Solaris लॉन्च किया, जो कि उनके नए इंटरफ़ेस वर्ल्ड मॉडल (Interface World Models) श्रृंखला का पहला मॉडल है। Solaris ऐप और वेबसाइट इंटरफ़ेस को फ्रेम दर फ्रेम रीयल-टाइम में जनरेट कर सकता है, किसी मध्यवर्ती कोड रिप्रेज़ेंटेशन की ज़रूरत नहीं है, सीधे इमेज के रूप में इंटरैक्शन लेयर प्रदान करता है, दृश्यात्मक, गतिशील प्रतिक्रिया और खुला इंटरैक्शन सपोर्ट करता है। यह एजेंट को प्रशिक्षित करने के लिए भी इस्तेमाल किया जा सकता है, जिससे वह बदलती इंटरफ़ेस लेआउट के अनुसार ढल सके, न कि केवल किसी विशिष्ट प्रशिक्षण वातावरण तक सीमित रहे।","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway ने Solaris लॉन्च किया: पहला इंटरफ़ेस वर्ल्ड मॉडल, रीयल-टाइम ऑपरेटिंग सिस्टम स्तर की इंटरेक्टिव इंटरफ़ेस जनरेशन - Aioga AI समाचार","description":"Runway ने Solaris लॉन्च किया, जो कि उनके नए इंटरफ़ेस वर्ल्ड मॉडल (Interface World Models) श्रृंखला का पहला मॉडल है। Solaris ऐप और वेबसाइट इंटरफ़ेस को फ्रेम दर फ्रेम रीयल-टाइम में ज...","url":"https://www.aioga.com/hi/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:21.657Z"},"it":{"title":"Runway lancia Solaris: il primo modello di mondo dell'interfaccia, genera in tempo reale interfacce a livello di sistema operativo","summary":"Runway presenta Solaris, il primo modello della sua nuova serie di modelli di mondo dell'interfaccia (Interface World Models). Solaris può generare in tempo reale interfacce di applicazioni e siti web fotogramma per fotogramma, senza necessità di rappresentazioni intermedie del codice, utilizzando direttamente immagini come livello di interazione, supportando la visualizzazione, le risposte dinamiche e l'interazione aperta. Può anche essere utilizzato per addestrare agenti intelligenti, permettendo loro di adattarsi a layout di interfaccia in continuo cambiamento, invece di limitarsi a un ambiente di addestramento specifico.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway lancia Solaris: il primo modello di mondo dell'interfaccia, genera in tempo reale interfacce a livello di sistema operativo - Aioga Notizie IA","description":"Runway presenta Solaris, il primo modello della sua nuova serie di modelli di mondo dell'interfaccia (Interface World Models). Solaris può generare in tempo reale interfacce di app...","url":"https://www.aioga.com/it/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:27.195Z"},"nl":{"title":"Runway kondigt Solaris aan: het eerste Interface World Model, dat realtime besturingssysteem-niveau interactieve interfaces genereert","summary":"Runway lanceert Solaris, het eerste model in hun nieuwe Interface World Models-serie. Solaris kan realtime applicatie- en website-interfaces frame voor frame genereren, zonder tussenliggende code-representatie, direct als beeld voor de interactielaag, en ondersteunt visualisatie, dynamische respons en open interactie. Het kan ook worden gebruikt om agenten te trainen, zodat ze zich kunnen aanpassen aan voortdurend veranderende interface-indelingen, in plaats van beperkt te zijn tot specifieke trainingsomgevingen.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway kondigt Solaris aan: het eerste Interface World Model, dat realtime besturingssysteem-niveau interactieve interfaces genereert - Aioga AI-nieuws","description":"Runway lanceert Solaris, het eerste model in hun nieuwe Interface World Models-serie. Solaris kan realtime applicatie- en website-interfaces frame voor frame genereren, zonder tuss...","url":"https://www.aioga.com/nl/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:29.612Z"},"tr":{"title":"Runway, gerçek zamanlı işletim sistemi düzeyinde etkileşimli arayüzler üreten ilk arayüz dünya modeli olan Solaris'i piyasaya sürdü","summary":"Runway, yeni Interface World Models serisinin ilk modeli olan Solaris'i piyasaya sürdü. Solaris, gerçek zamanlı olarak gerçek zamanlı kare kare uygulama ve web sitesi arayüzleri oluşturabilir; arabulucu kod temsili olmadan, görüntüleri etkileşim katmanı olarak kullanarak görselleştirme, dinamik yanıt ve açık etkileşimi destekler. Ayrıca, belirli eğitim ortamlarıyla sınırlı kalmadan, sürekli değişen arayüz düzenlerine uyum sağlayarak ajanları eğitmek için de kullanılabilir.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway, gerçek zamanlı işletim sistemi düzeyinde etkileşimli arayüzler üreten ilk arayüz dünya modeli olan Solaris'i piyasaya sürdü - Aioga AI Haberleri","description":"Runway, yeni Interface World Models serisinin ilk modeli olan Solaris'i piyasaya sürdü. Solaris, gerçek zamanlı olarak gerçek zamanlı kare kare uygulama ve web sitesi arayüzleri ol...","url":"https://www.aioga.com/tr/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:38.244Z"},"vi":{"title":"Runway ra mắt Solaris: Mô hình thế giới giao diện đầu tiên, tạo giao diện cấp hệ điều hành theo thời gian thực","summary":"Runway ra mắt Solaris, đây là mô hình đầu tiên trong loạt mô hình thế giới giao diện (Interface World Models) hoàn toàn mới của họ. Solaris có khả năng tạo giao diện ứng dụng và website theo từng khung hình thời gian thực, không cần biểu diễn mã trung gian, sử dụng hình ảnh trực tiếp làm lớp tương tác, hỗ trợ trực quan, phản hồi động và tương tác mở. Nó cũng có thể được dùng để huấn luyện các tác nhân thông minh, giúp chúng thích nghi với bố cục giao diện thay đổi liên tục, thay vì bị giới hạn trong môi trường huấn luyện cụ thể.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway ra mắt Solaris: Mô hình thế giới giao diện đầu tiên, tạo giao diện cấp hệ điều hành theo thời gian thực - Tin tức AI Aioga","description":"Runway ra mắt Solaris, đây là mô hình đầu tiên trong loạt mô hình thế giới giao diện (Interface World Models) hoàn toàn mới của họ. Solaris có khả năng tạo giao diện ứng dụng và we...","url":"https://www.aioga.com/vi/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:35.552Z"},"id":{"title":"Runway Rilis Solaris: Model Dunia Antar Muka Pertama, Menghasilkan Antarmuka Tingkat Sistem Operasi Secara Real-Time","summary":"Runway meluncurkan Solaris, model pertama dari seri model dunia antar muka (Interface World Models) baru mereka. Solaris dapat menghasilkan antarmuka aplikasi dan situs web secara frame-by-frame secara real-time, tanpa memerlukan representasi kode perantara, langsung menggunakan gambar sebagai lapisan interaksi, mendukung visualisasi, respons dinamis, dan interaksi terbuka. Ini juga dapat digunakan untuk melatih agen agar menyesuaikan dengan tata letak antarmuka yang terus berubah, bukan terbatas pada lingkungan pelatihan tertentu.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway Rilis Solaris: Model Dunia Antar Muka Pertama, Menghasilkan Antarmuka Tingkat Sistem Operasi Secara Real-Time - Berita AI Aioga","description":"Runway meluncurkan Solaris, model pertama dari seri model dunia antar muka (Interface World Models) baru mereka. Solaris dapat menghasilkan antarmuka aplikasi dan situs web secara...","url":"https://www.aioga.com/id/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:42.772Z"},"th":{"title":"Runway เปิดตัว Solaris: โมเดลโลกอินเตอร์เฟซตัวแรก ที่สร้างอินเตอร์เฟซระดับระบบปฏิบัติการแบบเรียลไทม์","summary":"Runway เปิดตัว Solaris ซึ่งเป็นโมเดลแรกในซีรีส์โมเดลโลกอินเตอร์เฟซ (Interface World Models) ใหม่ของพวกเขา Solaris สามารถสร้างอินเตอร์เฟซของแอปและเว็บไซต์แบบเฟรมต่อเฟรมแบบเรียลไทม์ โดยไม่ต้องมีการแทนรหัสกลาง ใช้ภาพเป็นชั้นการโต้ตอบโดยตรง รองรับการมองเห็น การตอบสนองแบบไดนามิก และการโต้ตอบแบบเปิด นอกจากนี้ยังสามารถใช้ฝึกผู้ปัญญาประดิษฐ์ให้ปรับตัวเข้ากับการจัดวางอินเตอร์เฟซที่เปลี่ยนแปลงอย่างต่อเนื่อง แทนที่จะจำกัดอยู่ในสภาพแวดล้อมการฝึกเฉพาะ","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway เปิดตัว Solaris: โมเดลโลกอินเตอร์เฟซตัวแรก ที่สร้างอินเตอร์เฟซระดับระบบปฏิบัติการแบบเรียลไทม์ - ข่าว AI Aioga","description":"Runway เปิดตัว Solaris ซึ่งเป็นโมเดลแรกในซีรีส์โมเดลโลกอินเตอร์เฟซ (Interface World Models) ใหม่ของพวกเขา Solaris สามารถสร้างอินเตอร์เฟซของแอปและเว็บไซต์แบบเฟรมต่อเฟรมแบบเรียลไทม์...","url":"https://www.aioga.com/th/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:43.499Z"},"pl":{"title":"Runway wprowadza Solaris: pierwszy model świata interfejsów, generujący w czasie rzeczywistym interfejsy systemu operacyjnego","summary":"Runway wprowadza Solaris, pierwszy model z nowej serii modeli świata interfejsów (Interface World Models). Solaris potrafi generować aplikacje i interfejsy stron internetowych klatka po klatce w czasie rzeczywistym, bez pośredniego kodu, bezpośrednio jako warstwę interaktywną w formie obrazu, obsługując wizualizacje, dynamiczną reakcję i otwartą interakcję. Może być również wykorzystywany do trenowania agentów, aby dostosowywały się do stale zmieniających się układów interfejsu, a nie były ograniczone do określonych środowisk treningowych.","category":"行业动态","source":"Runway：News（网页）","aggregationSource":"Runway：News（网页）","pageTitle":"Runway wprowadza Solaris: pierwszy model świata interfejsów, generujący w czasie rzeczywistym interfejsy systemu operacyjnego - Aioga Wiadomości AI","description":"Runway wprowadza Solaris, pierwszy model z nowej serii modeli świata interfejsów (Interface World Models). Solaris potrafi generować aplikacje i interfejsy stron internetowych klat...","url":"https://www.aioga.com/pl/news/cmthhmoi10e71rodmx6wngoz1/","contentTranslated":true,"sourceHash":"dc20f2d1e7caad04","translatedAt":"2026-08-31T17:22:48.204Z"}},"evidenceTier":"verified-news","reviewStatus":"editorial-selected","indexable":true,"editorialCover":""}}