论文解读
π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
长期助手 | 5.2/10
评估方法
论文解读
Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian
语音识别 | 7.5/10
长期助手 | 5.2/10
语音识别 | 7.5/10