Tech News
← Home  ·  All topics

World Models

14 GoKawiil briefs on this topic

Physicl raises $10M seed round led by Inovia Capital for robot simulation tech

Physicl, founded by Alex de Vigan, has raised $10 million in seed funding from Inovia Capital. The startup repurposes technology originally built at de Vigan's prior company, nfinite, which created 3D product renderings for e-commerce, to generate realistic physics-based simulations for training robots and world models.

Google unveils Gemini 4 Carbon and Genie 4 AI models

Google announced Gemini 4 Carbon, a new large language model aimed at cybersecurity professionals for detecting and patching software vulnerabilities, which it says outperforms its own Gemini 4 Argon and OpenAI's GPT-6 Astra on benchmarks. The company also released Genie 4, a world model that simulates physical environments and now supports audio like background noise and dialogue. Both models remain restricted: Gemini 4 Carbon is limited to select cybersecurity experts while Genie 4 has a waitlist, with no public release date confirmed.

Google DeepMind launches Genie 4 world model with audio and live scene editing

Google DeepMind released Genie 4 in research preview, a world model that generates photorealistic, interactive simulated environments with synchronized audio including music, ambient sound, and dialogue. Users can edit scenes mid-simulation, such as changing weather or camera angles, and the model can maintain a consistent scene for up to two minutes, twice as long as its predecessor Genie 3. Gemini now acts as a planning layer that directs Genie 4's visual generation, including an experiment where it broke down robotics tasks for real-time simulation.

Google DeepMind tests Genie 4 world model with industry partners

Google DeepMind is running trusted-tester programs for Genie 4, an experimental AI world model that generates photorealistic, interactive simulations with native audio and real-time steering. Testers from film, journalism, education, gaming and engineering are trying it for tasks like pre-visualizing film scenes, turning archival photos into explorable environments, and rapidly prototyping game concepts.

Rivian acquires UK startup Third Dimension to boost self-driving simulation

Rivian has acquired Third Dimension, a London-based startup that uses AI to convert images and video into 3D world models, for an undisclosed sum. The 15-person team, founded in 2024 by Tolga Kart and Piotr Sokólski and previously focused on gaming applications, will join Rivian's autonomy and AI division under James Philbin and shift entirely to automated-driving work.

Beacon outlines plan to build 'Company World Models' for strategic decisions

Beacon, which aims to bring AI into the real economy, described two paths for growing its portfolio companies: deploying task-specific 'Digital Employees' for jobs like sales, support, or bookkeeping, and developing what it calls Company World Models (CWM) — AI systems meant to make higher-level strategic decisions about what a business and its digital workers should be doing. The company says far fewer teams are working on this second, more ambitious category than on digital-employee agents.

Debate grows over leadership's role as AI agents take over corporate operations

A commentary piece examines how corporate AI systems—agents, ontologies, and world models tied to ERPs and CRMs—are increasingly optimizing company operations. The author references Mustafa Suleyman's prediction that AI could eliminate most white-collar jobs within 12 months, prompting questions about what leadership means once such automated systems are in place.

AMD to Acquire Fei-Fei Li's World Labs for $8.2 Billion

AMD has agreed to buy World Labs, the startup founded by AI researcher Fei-Fei Li, in a stock deal valued at roughly $8.2 billion, making it AMD's second-largest acquisition. World Labs builds 'world models' that simulate 3D physical environments for robotics and other embodied AI systems. Li will join AMD as chief scientist and executive vice president once the deal closes later this year, with World Labs operating separately from AMD's chip business until then.

Startup Worldmodeldata Turns Video Game Controller Data Into AI Training Sets

British startup Worldmodeldata, advised by AI researcher Yann LeCun, is packaging controller inputs and gameplay footage from video game studios into datasets meant to train 'world models'—AI systems designed to understand physical cause and effect. The company positions itself as a broker that curates this data for AI labs, rather than collecting it directly from its own gaming platforms.

Developer trains JEPA-based world model to select Squirtle in Pokémon Red

An independent AI researcher trained a small JEPA-variant world model called LeWorldModel, running locally on a consumer RTX 3080 Ti GPU, to play the opening sequence of the 1996 Game Boy title Pokémon Red. The model learned to plan a sequence of button presses that navigated Professor Oak's lab and selected Squirtle as the starter Pokémon.

World Model Startups AMI Labs and World Labs Stay Quiet on Commercial Plans

At the All In conference, AMI Labs co-founder Michael Rabbatt declined to detail his company's product roadmap for its spatial-intelligence 'world model' technology, saying only that AMI will discuss plans 'when we're ready.' World Labs, maker of the Marble platform, has shown demos in gaming, media and CGI but has not clarified a clear commercial direction, and even data supplier Physicl's CEO Alex de Vigan says he doesn't know exactly how his company's data is being used.

AI researcher Danijar Hafner builds agents that plan in unfamiliar environments

Danijar Hafner, a 31-year-old AI researcher named to MIT Technology Review's 35 Innovators Under 35 list, runs a quiet San Francisco startup filled with humanoid robots suspended from racks. He has spent years refining world-model-based agents by testing them against video games, and is now moving that work from simulations into physical robots operating in real environments.