Study shows discrete diffusion transformers with beam search can factor semiprimes
A new arXiv paper reports that transformers trained with discrete denoising diffusion and decoded via guided test-time beam search can learn to recover semiprime factorizations, with scaling laws characterizing performance.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-10 05:00 · arXiv cs.LG
Semiprime Factorization with Discrete Diffusion and Beam Search: Scaling Laws