Changes

Page history
Update JULAIN Journal Club authored by Susanne Wenzel's avatar Susanne Wenzel
Show whitespace changes
Inline Side-by-side
JULAIN-Journal-Club.md
View page @ 1a2d7162
...@@ -43,20 +43,23 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim ...@@ -43,20 +43,23 @@ The Orga Team is by no means a closed circle, new members are welcome at any tim
## Next Meeting ## Next Meeting
### backlog: ### 19 June 2023 (tbc): Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Zoom link: tbd
paper:
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task <br> Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task <br>
Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg<br> Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg<br>
ICLR2023<br> ICLR2023<br>
https://openreview.net/forum?id=DeG07_TcZvT https://openreview.net/forum?id=DeG07_TcZvT
top 5% notable papers from ICLR 2023
## Past Meetings
### 15 May 2023: Foundation Models for Robustness to Distribution Shifts<br> ### 15 May 2023: Foundation Models for Robustness to Distribution Shifts<br>
author and presenter: Ananya Kumar (Stanford) author and presenter: Ananya Kumar (Stanford)
Zoom link: https://fz-juelich-de.zoom.us/j/92309074898?pwd=YTVDcVNFUE94eGo3OVdCWjVwSlIrQT09<br>
Meeting ID: 923 0907 4898<br>
Passcode: 255128
paper: paper:
* [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.](https://arxiv.org/abs/2202.10054) <br> * [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.](https://arxiv.org/abs/2202.10054) <br>
Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang. International Conference on Learning Representations, (ICLR Oral) 2022. Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, Percy Liang. International Conference on Learning Representations, (ICLR Oral) 2022.
...@@ -69,7 +72,6 @@ When ML systems are deployed, they often face test examples that are different f ...@@ -69,7 +72,6 @@ When ML systems are deployed, they often face test examples that are different f
**Bio:**<br> **Bio:**<br>
Ananya is a final year PhD student at Stanford University advised by Percy Liang and Tengyu Ma. His PhD work focuses on representation learning, foundation models, and reliable machine learning. Ananya is a final year PhD student at Stanford University advised by Percy Liang and Tengyu Ma. His PhD work focuses on representation learning, foundation models, and reliable machine learning.
## Past Meetings
### 17 April 2023: Dendritic modulation enables multitask representation learning in hierarchical sensory processing pathways<br> ### 17 April 2023: Dendritic modulation enables multitask representation learning in hierarchical sensory processing pathways<br>
author and presenter: Willem Wybo, INM-6 author and presenter: Willem Wybo, INM-6
...@@ -538,4 +540,4 @@ A training schedule using filter pruning and orthogonal reinitialization ...@@ -538,4 +540,4 @@ A training schedule using filter pruning and orthogonal reinitialization
--- ---
last change: 12.04.2023 sw last change: 17.5.2023 sw
\ No newline at end of file \ No newline at end of file