causal representation learning
Causal representation learning focuses on identifying and modeling causal relationships in data, helping to distinguish between correlation and causation, and aiming to enhance decision-making and generalization in AI systems.
- CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization
- Causal Climate Emulation with Bayesian Filtering
- CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
- Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
- Counterfactual Implicit Feedback Modeling
- Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
- LLM Interpretability with Identifiable Temporal-Instantaneous Representation
- Measure-Theoretic Anti-Causal Representation Learning
- Reward-oriented Causal Representation Learning
- Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
- The third pillar of causal analysis? A measurement perspective on causal representations