← Search

Matteo Forasassi

2 accepted papers

2026

Prototype Transformer: Towards Language Model Architectures Interpretable by Design

ICML 2026poster

While state-of-the-art language models (LMs) surpass the vast majority of humans in certain domains, their reasoning remains largely opaque, reducing trust and risking deception and hallucination. In this work, we introduce the Prototype Transformer (ProtoT)—an autoregressive LM architecture that re…

Cited by 0SourceScholar
2026

Towards the Training of Deeper Predictive Coding Neural Networks

ICML 2026poster

Predictive coding networks are neural models that perform inference through an iterative energy minimization process. While effective in shallow architectures, they suffer significant performance degradation beyond five to seven layers. In this work, we show that this degradation is caused by expone…

Cited by 5SourceScholar