HuggingPapers· @HuggingPapers · X·· 23 小时前AI 评分
Fold2Reason：蛋白质折叠训练提升推理能力
Fold2Reason：蛋白质折叠训练提升广泛推理能力 在 FoldingCorpus 上进行后训练，将 10 个推理基准的宏平均准确率从 45.09% 提升至 48.33%，结构预测能力提升 2.7–3.5 倍。
Fold2Reason: training on protein folding improves broad reasoning
Post-training on FoldingCorpus raises macro-average accuracy from 45.09% to 48.33% across 10 reasoning benchmarks, with 2.7–3.5× better structure prediction.
来源：HuggingPapers · x.com