LingAo Xiao

Fix some links and types, add bulky downloader

1

1. [EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis](https://arxiv.org/abs/1905.05934) W -> F 2. [Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning](https://arxiv.org/abs/1611.05128) F -> W Add bulky downloader which allows to automatically...

Windows bootstrap fails

1

- I have no clue what happened. - `esy install` returns `info install 0.6.11 (using package.json)` and seems fine But when I run `esy bootstrap`, it is stopped by the...

 并集 (Union) 交集 (intersection)

 - No idea why it happens - I ran it on **Windows 11**

Vim cursor block disappears in mono space format

1

Vim cursor disappears while touching mono space in the editing mode after rendering. - This is an example of `monospace` - words surrounded by ` `` ` My own **guessing**:...

Specifying the `limit` of query in Aim UI

5

## 🚀 Feature ### Motivation Querying entire database is extremely slow on devices with poor CPUs. Also, I notice that runs are successfully matched at the very beginning of the...

Cannot reproduce the classification result of TimesNet

4

> 大家好，我初步对比了一下我们实验代码与TSLib之间的差别，主要变化在learning rate strategy，我们在整理算法库的时候额外增加了learning rate decay的过程，但是这一设计会降低模型训练的波动性，对于一些数据量较小的数据集反而不友好，因此我们在最近的commit中已经去掉了这一过程（https://github.com/thuml/Time-Series-Library/commit/1c7f843aee8ce75e758d45f0bd10c02516e36a92 ），我这边测试是可以复现结果的，请大家再次尝试 As mentioned in the [issue](https://github.com/thuml/Time-Series-Library/issues/321#issuecomment-2227175691), I add the following two lines from [commit:1c7f843](https://github.com/thuml/Time-Series-Library/commit/1c7f843aee8ce75e758d45f0bd10c02516e36a92). However, I am still not able to reproduce the result....