WorldFoundry | A Unified Inference and Evaluation Framework for World Models
WorldFoundry is an open-source infrastructure that unifies inference and evaluation for generative world models. It supports video generation, interactive worlds, 3D/4D representations, and embodied models through a unified workflow with TUI, CLI, and Studio interfaces. The framework integrates a growing collection of state-of-the-art models and currently includes 58 benchmarks.
ScalingOpt is a professional platform dedicated to large-scale deep learning optimization, promoting verifiable and scalable algorithms. It aggregates cutting-edge optimizers, provides benchmark analysis, visualization demos, curated literature, and educational tutorials. The community-driven project aims to foster collaboration and advance research in optimization methodology. We welcome contributions and feedback. Your engagement and GitHub stars are greatly appreciated.
