causal reasoning
Causal reasoning in AI refers to the ability of models to identify and infer causal relationships between variables, rather than merely correlational associations. It involves understanding how changes in one variable can directly affect another and is crucial for tasks such as decision making and prediction in uncertain environments.
- A Counterfactual Semantics for Hybrid Dynamical Systems
- A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
- Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
- CF-VLM：CounterFactual Vision-Language Fine-tuning
- Causal Discovery and Inference through Next-Token Prediction
- Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration
- Causally Reliable Concept Bottleneck Models
- Cyclic Counterfactuals under Shift–Scale Interventions
- Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
- Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
- MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
- Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
- PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions
- Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering
- Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
- Simulating Society Requires Simulating Thought
- The third pillar of causal analysis? A measurement perspective on causal representations
- Two Causally Related Needles in a Video Haystack