Jörg Franke
@jkhfranke
Followers
83
Following
40
Statuses
22
PhD student in the ML Lab @UniFreiburg @AutoML_org Co-Organizer of https://t.co/uSIYXwihre - Core Deep Learning Research with some applications in bio.
Freiburg im Breisgau, Germany
Joined September 2015
🧵5/5 - We also show performance benefits in experiments with ImageNet, image segmentation, finetuning, or LLM pretraining. Come discuss with us at NeurIPS: 📍 East Exhibit Hall A-C 🎯 Poster #2803 ⏰ Thu Dec 12, 11am-2pm PST Or check our paper:
0
0
0
RT @riccardograzzi: LLMs can now track states, finally matching this cat! And we prove it. But how? 🧵👇 1/ Paper:
0
17
0
RT @gklambauer: Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues Forget my earlier post, this is the cool one! :) Ana…
0
22
0
Our newest work: the Probabilistic Transformer We enhanced a Transformer with a hierarchical latent distribution to model ambiguities and achieved SOTA in RNA folding and molecule design 🥳
2
3
15
If you are interested in our the NeurIPS Meetup about "Machine Learning With Quantum Computers", please join us here:
0
0
1
RT @FrankRHutter: Exciting news: following a series of 8 AutoML workshops at ICML, we will hold the 1st International Conference on AutoML…
0
79
0
RT @FrankRHutter: Our #metalearning workshop at #NeurIPS2021 got accepted! Amazing speakers: Carlo Ciliberto, @rosemary_ke, @Luke_Metz, @Mi…
0
10
0
The recording from our last Meetup about the Success Story of Large Language Models is now on YouTube available:
0
0
3
Our next / Meetup at 20.05.2021 is on "A Brief Overview of the Success Story of Large Language Models" presented by @TimoDenk! Please feel free to join us:
0
1
1
In our weekly paper discussion group, we start a new track on deep learning for audio modelling: Feel free to join us!
0
1
2
We finalized the camera-ready version of our recent ICLR paper on sample-efficient AutoRL (SEARL) and updated it on arXiv:
0
2
10
Our next climate paper discussion is on the "Attribution of extreme weather and climate‐related events". Please feel free to join us!
0
0
0
On Thursday, in our next climate paper discussion, we care about climate model simulations again and discuss "Sea-ice-free Arctic during the Last Interglacial supports fast future loss". Please feel free to join us:
0
0
0
Today we discuss "Taking climate model evaluation to the next level". If you are interested in climate models, please feel free to joins us:
0
0
1