Apple Machine Learning Research(RSS)·· 23 天前AI 评分46
Apple 提出 TS-DFM:用能量罗盘引导少步离散流匹配蒸馏
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
AI 导读
Apple 研究团队提出 Trajectory-Shaped Discrete Flow Matching(TS-DFM),用轻量级能量罗盘在训练中评估并筛选中间步骤,替代离散流匹配的盲目随机跳跃,且不增加推理成本。在 170M 参数语言模型上,8 步学生模型困惑度比 1024 步教师模型低 32%,速度快 128×。
整理与数据来源:AIHOT
来源:Apple Machine Learning Research(RSS) · machinelearning.apple.com