UniSim is a product for learning interactive, real-world simulators. It simulates the behavior of humans, robots, and other types of interactive agents through generative modeling, producing realistic experiences. UniSim can be used for creating controllable content in games and movies, as well as training agents in simulations that can be directly deployed to the real world. UniSim is trained using diverse datasets to mimic the visual results of high-level commands and low-level control. It can be used to train high-level visual language planners and low-level reinforcement learning strategies, demonstrating significant transfer effects in the real world. UniSim can also be applied to other types of intelligent tasks, such as video captioning and detection models. Through UniSim, users can perform long-term planning, reinforcement learning, and decision optimization.