Tiny Recursive Message Passing

Tiny Recursive Message Passing applies recursive transformers and deep supervision to message passing neural networks, achieving high efficiency. The approach yields about 99% test accuracy on Sudoku-Extreme with only 16k parameters, training quickly on modern GPUs or CPUs. It also demonstrates zero‑shot transfer to larger problem instances, outperforming popular neural baselines on N‑queens and Boolean satisfiability with fewer parameters.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms