Jev 接入驾驶模拟器实现实时驾驶
作者将 Jev 连接到驾驶模拟器的原始控制接口,并展示其在模拟环境中实时驾驶的画面,强调实时响应而非逐帧生成视频。
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