We propose a causal interpretation of self-attention in the Transformer neural network
architecture. We interpret self-attention as a mechanism that estimates a structural equation …

Deep Learning models have shown success in a large variety of tasks by extracting
correlation patterns from high-dimensional data but still struggle when generalizing out of …

In the rapidly evolving landscape of artificial intelligence multi-modal large language models
are emerging as a significant area of interest. These models which combine various forms of …

We present a constraint-based algorithm for learning causal structures from observational
time-series data, in the presence of latent confounders. We assume a discrete-time …

Driven by empirical risk minimization, machine learning algorithm tends to exploit subtle
statistical correlations existing in the training environment for prediction, while the spurious …

In the rapidly evolving landscape of artificial intelligence, multi-modal large language
models are emerging as a significant area of interest. These models, which combine various …

Abstract Machine learning approaches are widely studied in the production prediction of
CBM wells after hydraulic fracturing, but rarely used in practice due to the low generalization …

Visual attention does not always capture the essential object representation desired for
robust predictions. Attention modules tend to underline not only the target object but also the …

With the advent of universal function approximators in the domain of reinforcement learning,
the number of practical applications leveraging deep reinforcement learning (DRL) has …

Abstract Testing for Conditional Independence (CI) is a fundamental task for causal
discovery but is particularly challenging in mixed discrete-continuous data. In this context …