Article Component Showcase
A complete writing and design sample: every current article component, several supported structures, and copyable Markdown for each effect.
Article componentsRead more
Research
Toward a Foundation Model of World Dynamics
World Dynamics
We are exploring models that connect observations, causal structure and temporal change to reason about how real systems evolve.
Read moreMore research
Andrey: Discovering Causal Structure
Andrey explores candidate causal relationships across many variables, helping us investigate what may drive a system and compare competing explanations.
Causal IntelligenceRead more
Simons: Learning Across Time
Simons explores shared representations for time-series and tabular data, with a focus on learning how systems evolve across different settings.
Foundation ModelsRead more
From Forecasts to Interventions
A forecast describes a possible outcome. We explore what additional structure and evidence are needed to reason about how an action could change it.
Causal ReasoningRead more
Learning from Real-World Feedback
When an outcome differs from a prediction, what should a model learn? We explore feedback that preserves the context of observations, assumptions and actions.
Learning LoopsRead more
Evaluating Beyond Forecast Accuracy
We explore how to evaluate temporal models beyond a single forecast score, including their behavior under uncertainty and changing conditions.
EvaluationRead more
Making Uncertainty Explicit
We explore how temporal models can distinguish plausible futures and explain what remains unknown about a changing system.
UncertaintyRead more
Learning Across Systems and Scales
Which patterns of change can transfer between systems? We investigate shared temporal representations while keeping local conditions and measurement scales visible.
Transfer LearningRead more