返回探索

4B Jev风格评判模型在机器人基准上超越27B模型

作者分享利用公开数据和自有配方训练的4B Jev风格评判模型,在RoboPulse、RoboRewardBench及真实机器人部署中击败了多种多模态Jev风格模型(最高27B),并指出专用奖励模型在特定任务上仍占优势。

3/6 How far can public data + our recipe take a 4B Jev-style judge? It beats every multimodal Jev-style model we tested, up to 27B, on RoboPulse, RoboRewardBench and real-robot rollouts. Specialist reward models still win at home: Robo-Dopamine on progress, RoboReward on

4B Jev风格评判模型在机器人基准上超越27B模型 1
· 0 次赞在 X 打开