g2rl-gradient-guided

【效率与协作】Guide LLM exploration through the model's own gradient geometry rather than external signals. Extract sequence-level gradient features measuring how tokens would reshape output distributions. Reward responses introducing novel gradient directions while deemphasizing redundant ones. Achieve orthogonal gradient directions and improved accuracy.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准