Hot eventLive
GRIL:对角线性循环网络实现上下文梯度下降
1 reports1 sources4 hr ago updated
Get the story
AI overview
2026年10月8日,arXiv Neural and Evolutionary Computing 栏目发布论文,提出 Gradient-based Recurrent In-context Learner(GRIL),一种对角线性循环网络(LRNN)。该方法把监督梯度步分解为短窗口叉积写入与下一查询的乘性读出,使线性循环网络能够在循环状态中通过梯度下降进行上下文学习。目前公开信息仅涉及该论文本身,尚未见后续验证或应用报道。
Generated from reports · updated 3 hr ago
LatestOct 8
论文提出GRIL,用短窗口叉积写入与乘性读出分解监督梯度步。Timeline
Follow the coverage from different angles.
Oct 8, 2026
- arXiv · Neural and Evolutionary ComputingGRIL:线性循环网络如何在循环状态中通过梯度下降进行上下文学习
论文提出 Gradient-based Recurrent In-context Learner(GRIL),一种对角线性循环网络(LRNN),把监督梯度步分解为短窗口叉积写入与下一查询的乘性读出。
Heat trend
Current heat 9·Comparable peak 10(Oct 8)·Comparable change over 24 hours –
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.