World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation. However, existing world models are confined to specific scenarios such as gaming or driving, limiting their ability to capture the complexity of general world…
The main features of jeffwang987/worlddreamer are: Embodied World Models, Video Generation.
Open-source alternatives to jeffwang987/worlddreamer include: agibottech/ewmbench — Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models. ai-forever/kandinskyvideo. aidanscannell/dcmpc — This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous… ailab-cvc/videocrafter — Videocrafter is a latent diffusion model designed for AI video synthesis. It functions as both a text-to-video and… aim-uofa/gendef. 20robo/raenwm — Paper | Models (Coming Soon).
Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
This repository is the official implementation of DC-MPC, presented in "Discrete Codebook World Models for Continuous Control" at ICLR 2025. DC-MPC is a model-based reinforcement learning algorithm demonstrating the strengths of learning a discrete latent space with discrete codebook encodings.
