covrl-variational-reasoning

【效率与协作】Enhance language model reasoning through coupled sampling from prior (question-only) and posterior (answer-conditioned) distributions. Construct composite distribution mixing both at token level using hybrid sampling. Combine reconstruction term, selective NLL loss, and KL regularization. Achieve 12.4% improvement over base model and 2.3% over compar…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准