world-models

[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.

EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory

A high-performance, universal serving framework for any-to-any models.

Implementation of a transformer for reinforcement learning using `x-transformers`

Implementation of the world model architecture for self driving out of Wayve