3 papers
cs.CL2026
The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
Bohang Sun, Max Zhu, Francesco Caso +5
Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tok…
cs.LG2025
Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
Cassidy Ashworth, Pietro Liò, Francesco Caso
Deep learning models have proven enormously successful at using multiple layers of representation to learn relevant features of structured data. Encoding physical symmetries into t…
cs.LG2025
Entropy-Lens: Uncovering Decision Strategies in LLMs
Riccardo Ali, Francesco Caso, Christopher Irwin +1
In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability litera…