World Models
Tag119 stories
An approach to AI where a system learns an internal simulation of an environment and predicts how it changes under actions. Readers can learn about video and language world models, robotics and simulation use cases, training data requirements, evaluation, and how the research differs from language models.
Inside Large World Model: UC Berkeley Multimodal Model that can Understand 1 Hour Long VideosThis AI Paper Introduces the Diffusion World Model (DWM): A General Framework for Leveraging Diffusion Models as World Models in the Context of Offline Reinforcement learningYann LeCun on X: "Let me clear a *huge* misunderstanding here. The generation of mostly realistic-looking videos from prompts *does not* indicate that a system understands the physical world. GeneratiGeneral World Models: Runway AI Research Starting a New Long-Term Research EffortThe self-supervised goal reaching benchmark introduced in Discovering and Achieving Goals via World ModelsDreaming in Blocks — MineWorld, the Minecraft World ModelWaypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUsWhy AMI Labs’ Alexandre LeBrun won’t call his AI ‘AGI’ or ‘superintelligence’NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical RoboticsThe Download: Claude’s inner workings, and the future of world models