... | @@ -41,15 +41,23 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim |
... | @@ -41,15 +41,23 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim |
|
|
|
|
|
## Next Meeting
|
|
## Next Meeting
|
|
|
|
|
|
### 28 November 2022
|
|
### 23 January 2023: LAION-5B: An open large-scale dataset for training next generation image-text models
|
|
|
|
Jenia Jitsev, Mehdi Cherti
|
|
|
|
|
|
Please note that we move this meeting by one week (28 instead of 21)
|
|
VC: https://zoom.us/j/98911612832?pwd=ZHVtbUorVDFNaWVkSnZMWEVscEVQUT09 <br>
|
|
|
|
Meeting ID: 989 1161 2832<br>
|
|
|
|
Passcode: 435699<br>
|
|
|
|
|
|
* VC: https://zoom.us/j/93317283997?pwd=SjZQZDNrbWFrT1hzNE43aEhKRVo1Zz09<br>
|
|
Our work on validating language-vision learning by collecting large-scale text-image LAION-5B dataset and training various scale CLIP models, evaluating those on different downstream tasks like zero-shot classification, won Outstanding Paper Award at NeurIPS 2022. Work was performed at Scalable Learning & Multi-Purpose AI Lab (Mehdi Cherti & Jenia Jitsev) in collaboration with LAION, UC Berkeley, TU Darmstadt, TU München, University of Washington, Allen AI Institute.<br>
|
|
Meeting ID: 933 1728 3997<br>
|
|
|
|
Passcode: 059545
|
|
|
|
|
|
|
|
### Reservoir Computing and Beyond
|
|
We present LAION-5B, an open, publically available dataset of 5.8B image-text pairs and validate it by reproducing results of training state-of-the-art CLIP models of different scale.<br>
|
|
|
|
|
|
|
|
Paper: https://openreview.net/forum?id=M3Y74vmsMcY
|
|
|
|
|
|
|
|
|
|
|
|
## Past Meetings
|
|
|
|
|
|
|
|
### 28 November 2022: Reservoir Computing and Beyond
|
|
|
|
|
|
[Claudio Gallicchio](https://sites.google.com/site/cgallicch/), Università di Pisa <br>
|
|
[Claudio Gallicchio](https://sites.google.com/site/cgallicch/), Università di Pisa <br>
|
|
claudio.gallicchio@unipi.it
|
|
claudio.gallicchio@unipi.it
|
... | @@ -65,8 +73,6 @@ Reservoir Computing is an appealing methodology to design deep neural networks f |
... | @@ -65,8 +73,6 @@ Reservoir Computing is an appealing methodology to design deep neural networks f |
|
|
|
|
|
**Invitation and moderation**: Elisabeth Pfaehler(IAS-8)
|
|
**Invitation and moderation**: Elisabeth Pfaehler(IAS-8)
|
|
|
|
|
|
## Past Meetings
|
|
|
|
|
|
|
|
### 17 October 2022
|
|
### 17 October 2022
|
|
|
|
|
|
**Hybrid format**
|
|
**Hybrid format**
|
... | @@ -486,4 +492,4 @@ A training schedule using filter pruning and orthogonal reinitialization |
... | @@ -486,4 +492,4 @@ A training schedule using filter pruning and orthogonal reinitialization |
|
|
|
|
|
|
|
|
|
---
|
|
---
|
|
last change: 28.11.2022 sw |
|
last change: 14.12.2022 sw |
|
\ No newline at end of file |
|
\ No newline at end of file |