Understanding AI systems' inner workings is critical for ensuring value alignment and safety.
This review explores mechanistic interpretability: reverse-engineering the computational …

While Transformers have enabled tremendous progress in various application settings, such
architectures still trail behind traditional symbolic planners for solving complex decision …

Recent work has suggested that certain neural network architectures-particularly recurrent
neural networks (RNNs) and implicit neural networks (INNs) are capable of logical …

Despite their remarkable success in language modeling, transformers trained to predict the
next token in a sequence struggle with long-term planning. This limitation is particularly …

The emergence of seemingly similar representations across tasks and neural architectures
suggests that convergent properties may underlie sophisticated behavior. One form of …

To predict how advanced neural networks generalize to novel situations, it is essential to
understand how they reason. Guez et al.(2019," An investigation of model-free planning") …