causal structure
Causal structure refers to the relationships between variables that indicate cause-and-effect dynamics. In AI, understanding causal structure is critical for developing models that can infer implications and make predictions based on interventions.
- Causal Discovery and Inference through Next-Token Prediction
- CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
- Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
- Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
- Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
- StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
- Structural Causal Bandits under Markov Equivalence
- When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions