Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent reasoning offers a compact alternative, but point-valued methods condition re...
Mingyeong Kim, Gyu-Hwung Cho, Juho Lee et al.
· 0 citations