(英文摘要)Drex open decision models return probability distributions over user-supplied options without autoregressive decoding, using supervised fine-tuning, RLAF, and consistency losses to improve accuracy, robustness, and latency.
点赞 18 · 代码星数 98
理由
- 抱脸 2026-11-06 每日论文点赞 18,当日第 8,只代表关注度。
用法
- 代码:https://github.com/nace-ai/drex-decision-models