Tag: causal machine learning
Browse our exclusive articles!
Why Safety Probes Detect Liars but Miss Fanatics
Discover why AI safety probes catch deceptive models but fail to detect coherent misaligned fanatics, posing new challenges for AI safety.
GazeQwen: Lightweight Gaze Integration for Video AI
Discover GazeQwen, a lightweight gaze-conditioned model boosting video understanding with efficient LLM modulation and state-of-the-art accuracy.
Simplicity Bias in Neural Networks: A Compression View
Explore how simplicity bias in neural networks is explained through compression and the Minimum Description Length principle for better AI robustness.
Learning Causal Representations with Few Environments
Discover how to learn causal representations effectively with limited environments and finite samples using new finite-sample guarantees.
Physics-Guided Deep Learning for Groundwater Level Prediction
Discover physics-guided deep learning models that predict spatio-temporal groundwater levels accurately at any location for improved water management.