Search

直接匹配不多,已補上最新動態。

Tag: #grpo3 results

Blockwise Advantages for Multi-Objective RL

Blockwise Advantages for Multi-Objective RL

Introduces Blockwise Advantage Estimation for GRPO in structured generations, assigning per-objective advantages to avoid interference. Uses Outcome-Conditioned Baseline to estimate advantages without nested rollouts. Competitive on math tasks with uncertainty estimation.

ArXiv AIResearchFeb 12#research#grpo#v1
Ox Alpha:神秘模型公開亮相

Ox Alpha:神秘模型公開亮相

Ox Alpha 是一款透過 OpenRouter 與 OpenCode 提供的匿名模型,具備 100 萬 token 上下文、圖片與影片輸入、工具呼叫及免費使用等能力。早期測試顯示其推理與程式設計表現強勁,但開發者、參數量、訓練資料與正式基準排名仍未獲確認。