Reasoning with Continuous Latent Diffusion
Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce Latent Flow Reasoning Models (LFRMs), an ELF-based training and inference recipe. Our experiments show that accurate decoding alone does not ensure strong reasoning performance. We therefore learn compact representations from multiple layers of a strong autoregressive teacher.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
