Related changes
Enter a page name to see changes on pages linked to or from that page. (To see members of a category, enter Category:Name of category). Changes to pages on your Watchlist are in bold.
List of abbreviations:
- N
- This edit created a new page (also see list of new pages)
- m
- This is a minor edit
- b
- This edit was performed by a bot
- (±123)
- The page size changed by this number of bytes
27 April 2026
|
|
N 08:05 | Searching for Activation Functions/paper/zh 2 changes history +66,138 [DeployBot (2×)] | |||
|
|
08:05 (cur | prev) +1 DeployBot talk contribs (Batch translate Searching for Activation Functions/paper unit 22 → zh) | ||||
| N |
|
07:36 (cur | prev) +66,137 DeployBot talk contribs (Clear fuzzy flag) | |||
|
|
N 08:05 | Searching for Activation Functions/paper/es 2 changes history +73,024 [DeployBot (2×)] | |||
|
|
08:05 (cur | prev) −8 DeployBot talk contribs (Batch translate Searching for Activation Functions/paper unit 1 → es) | ||||
| N |
|
07:34 (cur | prev) +73,032 DeployBot talk contribs (Batch translate Searching for Activation Functions/paper unit 68 → es) | |||
|
|
N 08:04 | Deep & Cross Network for Ad Click Predictions/paper 2 changes history +56,641 [DeployBot (2×)] | |||
|
|
08:04 (cur | prev) −739 DeployBot talk contribs ([deploy-bot] Page updated via CLI) Tag: content-generation | ||||
| N |
|
07:08 (cur | prev) +57,380 DeployBot talk contribs ([deploy-bot] Raw reproduction of arxiv:1708.05123) Tag: content-generation | |||
| N 07:59 | Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/zh diffhist +10,091 DeployBot talk contribs (Batch translate Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts unit 4 → zh) | ||||
| N 07:58 | Searching for Activation Functions/zh diffhist +11,287 DeployBot talk contribs (Batch translate Searching for Activation Functions unit 8 → zh) | ||||
| N 07:58 | Searching for Activation Functions/es diffhist +13,438 DeployBot talk contribs (Batch translate Searching for Activation Functions unit 30 → es) | ||||
| N 07:58 | Language Modeling with Gated Convolutional Networks/zh diffhist +9,880 DeployBot talk contribs (Batch translate Language Modeling with Gated Convolutional Networks unit 11 → zh) | ||||
| N 07:58 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/zh diffhist +10,010 DeployBot talk contribs (Batch translate Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer unit 35 → zh) | ||||
| N 07:58 | Dropout: A Simple Way to Prevent Neural Networks from Overfitting/zh diffhist +10,392 DeployBot talk contribs (Batch translate Dropout: A Simple Way to Prevent Neural Networks from Overfitting unit 6 → zh) | ||||
| N 07:58 | Language Modeling with Gated Convolutional Networks/paper/es diffhist +59,256 DeployBot talk contribs (Batch translate Language Modeling with Gated Convolutional Networks/paper unit 76 → es) | ||||
|
|
N 07:58 | Decoupled Weight Decay Regularization/paper/zh 2 changes history +63,862 [DeployBot (2×)] | |||
|
|
07:58 (cur | prev) −38 DeployBot talk contribs (Batch translate Decoupled Weight Decay Regularization/paper unit 143 → zh) | ||||
| N |
|
07:33 (cur | prev) +63,900 DeployBot talk contribs (Batch translate Decoupled Weight Decay Regularization/paper unit 71 → zh) | |||
| N 07:58 | Deep & Cross Network for Ad Click Predictions/paper/es diffhist +57,323 DeployBot talk contribs (Batch translate Deep & Cross Network for Ad Click Predictions/paper unit 33 → es) | ||||
| N 07:58 | Deep & Cross Network for Ad Click Predictions/zh diffhist +8,506 DeployBot talk contribs (Batch translate Deep & Cross Network for Ad Click Predictions unit 6 → zh) | ||||
| N 07:58 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/es diffhist +11,640 DeployBot talk contribs (Batch translate Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer unit 17 → es) | ||||
| N 07:37 | Deep & Cross Network for Ad Click Predictions/es diffhist +9,907 DeployBot talk contribs (Batch translate Deep & Cross Network for Ad Click Predictions unit 10 → es) | ||||
| N 07:36 | Decoupled Weight Decay Regularization/es diffhist +12,933 DeployBot talk contribs (Batch translate Decoupled Weight Decay Regularization unit 10 → es) | ||||
| N 07:36 | Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/paper/zh diffhist +45,262 DeployBot talk contribs (Batch translate Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/paper unit 57 → zh) | ||||
| N 07:35 | Deep & Cross Network for Ad Click Predictions/paper/zh diffhist +50,672 DeployBot talk contribs (Batch translate Deep & Cross Network for Ad Click Predictions/paper unit 30 → zh) | ||||
| N 07:35 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/paper/es diffhist +136,895 DeployBot talk contribs (Batch translate Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/paper unit 22 → es) | ||||
| N 07:35 | Decoupled Weight Decay Regularization/paper/es diffhist +72,518 DeployBot talk contribs (Batch translate Decoupled Weight Decay Regularization/paper unit 35 → es) | ||||
| N 07:33 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/paper/zh diffhist +124,432 DeployBot talk contribs (Batch translate Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/paper unit 240 → zh) | ||||
| N 07:33 | Language Modeling with Gated Convolutional Networks/paper/zh diffhist +52,512 DeployBot talk contribs (Batch translate Language Modeling with Gated Convolutional Networks/paper unit 81 → zh) | ||||
| N 07:30 | Dropout: A Simple Way to Prevent Neural Networks from Overfitting/paper/es diffhist +75,665 DeployBot talk contribs (Batch translate Dropout: A Simple Way to Prevent Neural Networks from Overfitting/paper unit 132 → es) | ||||
| N 07:29 | Dropout: A Simple Way to Prevent Neural Networks from Overfitting/paper/zh diffhist +60,895 DeployBot talk contribs (Batch translate Dropout: A Simple Way to Prevent Neural Networks from Overfitting/paper unit 101 → zh) | ||||
| N 07:29 | Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/paper/es diffhist +58,838 DeployBot talk contribs (Batch translate Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/paper unit 23 → es) | ||||
| N 07:14 | Decoupled Weight Decay Regularization diffhist +11,779 DeployBot talk contribs ([deploy-bot] Claude-authored from arxiv:1711.05101) | ||||
| N 07:10 | Deep & Cross Network for Ad Click Predictions diffhist +9,423 DeployBot talk contribs ([deploy-bot] Claude-authored from arxiv:1708.05123) | ||||
| N 07:10 | Decoupled Weight Decay Regularization/paper diffhist +70,712 DeployBot talk contribs ([deploy-bot] Raw reproduction of arxiv:1711.05101) | ||||
|
|
N 06:58 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer/paper 2 changes history +135,995 [DeployBot (2×)] | |||
|
|
06:58 (cur | prev) 0 DeployBot talk contribs ([deploy-bot] Fix broken file ref: moe-bigpicture2.eps→.png (file is PNG)) Tag: content-generation | ||||
| N |
|
06:53 (cur | prev) +135,995 DeployBot talk contribs ([deploy-bot] Raw reproduction of arxiv:1701.06538) Tag: content-generation | |||
| N 06:56 | Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer diffhist +10,980 DeployBot talk contribs ([deploy-bot] Claude-authored from arxiv:1701.06538) | ||||
| N 06:53 | Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts diffhist +11,262 DeployBot talk contribs ([deploy-bot] Claude-authored from https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) | ||||
| N 06:52 | Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts/paper diffhist +54,289 DeployBot talk contribs ([deploy-bot] Claude-authored from https://dl.acm.org/doi/pdf/10.1145/3219819.3220007) | ||||
| N 06:50 | Language Modeling with Gated Convolutional Networks diffhist +10,955 DeployBot talk contribs ([deploy-bot] Claude-authored from arxiv:1612.08083) | ||||
| N 06:50 | Searching for Activation Functions diffhist +12,469 DeployBot talk contribs ([deploy-bot] Claude-authored from arxiv:1710.05941) | ||||
| N 06:49 | Searching for Activation Functions/paper diffhist +71,613 DeployBot talk contribs ([deploy-bot] Raw reproduction of arxiv:1710.05941) | ||||
| N 06:46 | Incorporating Nesterov Momentum into Adam/paper/es diffhist +13,551 DeployBot talk contribs (Batch translate Incorporating Nesterov Momentum into Adam/paper unit 10 → es) | ||||
| N 06:45 | MTGR: Industrial-Scale Generative Recommendation Framework in Meituan/paper/zh diffhist +51,788 DeployBot talk contribs (Batch translate MTGR: Industrial-Scale Generative Recommendation Framework in Meituan/paper unit 120 → zh) | ||||
| N 06:44 | MTGR: Industrial-Scale Generative Recommendation Framework in Meituan/paper/es diffhist +61,263 DeployBot talk contribs (Batch translate MTGR: Industrial-Scale Generative Recommendation Framework in Meituan/paper unit 28 → es) | ||||
| N 06:44 | Language Modeling with Gated Convolutional Networks/paper diffhist +57,973 DeployBot talk contribs ([deploy-bot] Raw reproduction of arxiv:1612.08083) | ||||
| N 06:43 | A Theoretically Grounded Application of Dropout in Recurrent Neural Networks/paper/es diffhist +137,966 DeployBot talk contribs (Batch translate A Theoretically Grounded Application of Dropout in Recurrent Neural Networks/paper unit 51 → es) | ||||
| N 06:43 | A Theoretically Grounded Application of Dropout in Recurrent Neural Networks/paper/zh diffhist +127,197 DeployBot talk contribs (Batch translate A Theoretically Grounded Application of Dropout in Recurrent Neural Networks/paper unit 25 → zh) | ||||
| N 06:41 | Incorporating Nesterov Momentum into Adam/paper/zh diffhist +11,590 DeployBot talk contribs (Batch translate Incorporating Nesterov Momentum into Adam/paper unit 6 → zh) | ||||
| N 06:40 | Dropout: A Simple Way to Prevent Neural Networks from Overfitting/es diffhist +12,207 DeployBot talk contribs (Batch translate Dropout: A Simple Way to Prevent Neural Networks from Overfitting unit 13 → es) | ||||
| N 06:39 | Incorporating Nesterov Momentum into Adam/zh diffhist +9,606 DeployBot talk contribs (Batch translate Incorporating Nesterov Momentum into Adam unit 9 → zh) | ||||
| N 06:38 | MTGR: Industrial-Scale Generative Recommendation Framework in Meituan/zh diffhist +11,555 DeployBot talk contribs (Batch translate MTGR: Industrial-Scale Generative Recommendation Framework in Meituan unit 4 → zh) | ||||