Oriel — AI & technology worth noticing, every day.

WorldFoundry: Towards Unified Infrastructure for World Intelligence

Paper · https://arxiv.org/abs/2611.10771

Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a generative world model as a predictive dynamical system that maintains a persistent, history-conditioned representation of an environment, updates that representation in response to actions or interventions, and generates temporally coherent trajectories that reflect outcomes under observed and counterfactual interventions. From this definition, we derive an intelligence-oriented framework spanning perceptual grounding, persistent state modeling, controllable transformation, dynamics-aware prediction, and closed-loop interaction. We present WorldFoundry, open-source infrastructure for reproducible inference and evaluation across video, 3D and 4D, embodied action, and interactive world systems. WorldFoundry unifies model and benchmark discovery, runtime and asset preparation, execution orchestration, artifact management, and interactive visualization, while modality-specific adapters preserve native inputs, execution semantics, output representations, and evaluation protocols. Explicit manifests, durable artifact contracts, and evidence-aware scorecards separate execution readiness from evaluative claims, making each claim traceable to its supporting artifacts. The catalog contains 270 model entries, 74 benchmarks, and 62 registered metric entries, with readiness and execution evidence recorded separately. WorldFoundry enables reproducible comparison of persistent, controllable dynamics across heterogeneous systems, advancing the field from perceptual synthesis toward measurable world intelligence.

First seen by Oriel on .

AI summary

WorldFoundry is open-source infrastructure for reproducibly running and evaluating world models, with a framework focused on persistent state, controllable dynamics, and interaction rather than visual plausibility alone.

  • The paper defines a generative world model as a history-conditioned predictive system that updates with actions and produces coherent outcomes for observed and counterfactual interventions.
  • Its framework covers perceptual grounding, persistent state modeling, controllable transformation, dynamics-aware prediction, and closed-loop interaction.
  • WorldFoundry supports video, 3D and 4D, embodied action, and interactive world systems through modality-specific adapters that preserve native execution and evaluation protocols.
  • The catalog includes 270 model entries, 74 benchmarks, and 62 metric entries; readiness evidence is tracked separately from evaluative claims.
  • Explicit manifests, durable artifact contracts, and evidence-aware scorecards make evaluation claims traceable to supporting artifacts.

#world models #generative models #benchmarking #embodied ai

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 55, latest observation ; +5 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 2, latest observation ; +1 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2611.10771https://arxiv.org/abs/2611.10771 Read discussion