Skip to content
Hot eventLive

ReCal:面向在线策略蒸馏恢复的校准式结构化剪枝方法

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv Computation and Language 发布一手论文,提出 ReCal(Recovery-Aware Calibration)。该方法是一种即插即用的结构化剪枝方法,通过在剪枝前调整校准,提升剪枝后推理语言模型在在线策略蒸馏(OPD)中的恢复效果。目前公开信息仅包含该论文摘要,尚未见后续实验验证或第三方复现报道。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Computation and Language
    ReCal:面向在线策略蒸馏恢复的校准式结构化剪枝方法

    论文提出 ReCal(Recovery-Aware Calibration),一种即插即用方法,通过在剪枝前调整校准来提升剪枝后推理语言模型的在线策略蒸馏(OPD)恢复效果。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.