←
Daniel Klotz8,529 posts
Daniel Klotz avatar

Daniel Klotz

@ido87

🏷️ ml + earth @ UFZ & Google 🔬 measuring what the models can and can’t.

◷ Joined August 2008▧ 797 Photos and videos
Andreas Auer avatar
⟳ Daniel Klotz retweeted
Andreas Auer@AndAuer·2 Jun 2025

We’re excited to introduce TiRex — a pre-trained time series forecasting model based on an xLSTM architecture.

Post attachment
Kajetan Schweighofer avatar
⟳ Daniel Klotz retweeted
Kajetan Schweighofer@kschweig_·21 Oct 2024

Deep Ensembles are widely used to improve the performance of Deep Learning models. But beware, they can have profound impact on group fairness ⚖️ We analyzed why it happens and what can be done about it 🧵👇

Post attachment
Mohit Anand avatar
⟳ Daniel Klotz retweeted
Mohit Anand@mohitanand·21 Aug 2024

Thrilled to share my second PhD paper in Environmental Research Letters! While most focus on spring preconditioning, our study reveals the impact of winter conditions on summer vegetation across the entire Northern Hemisphere. Read more: twtr.to/824hX

the Water Institute avatar
⟳ Daniel Klotz retweeted
the Water Institute@water_institute·18 Jul 2024

Inside WaterResearch - Issue 19: Dive into the performance of various models on the #GreatLakes—a region with complex transboundary datasets, diverse climatic and land use conditions, and immense socio-economic importance to both the USA and Canada. bit.ly/3y3izNM

Post attachment
Claus avatar
⟳ Daniel Klotz retweeted
Claus@ClausHofm·15 May 2024

Really excited to announce Energy-based Hopfield Boosting. 🎉 Hopfield Boosting advances the state-of-the-art in OOD detection. 🚀 Our new energy function allows a model to focus on hard training examples close to the decision boundary between in-distribution and OOD samples. 🧵

0:10
Sepp Hochreiter avatar
⟳ Daniel Klotz retweeted
Sepp Hochreiter@HochreiterSepp·8 May 2024

I am so excited that xLSTM is out. LSTM is close to my heart - for more than 30 years now. With xLSTM we close the gap to existing state-of-the-art LLMs. With NXAI we have started to build our own European LLMs. I am very proud of my team. arxiv.org/abs/2405.04517

Sepp Hochreiter avatar
⟳ Daniel Klotz retweeted
Sepp Hochreiter@HochreiterSepp·8 May 2024

Today we published xLSTM. It is so exciting. I am very proud of my team: @maxmbeck,@KorbiPoeppel,@AndAuer, @MarkusSpanring, O. Prudnikova,@m_k_kopp,@gklambauer,@jo_brandstetter arxiv.org/abs/2405.04517

Tim Duignan avatar
⟳ Daniel Klotz retweeted
Tim Duignan@TimothyDuignan·7 May 2024

I think neural network potentials are the most important scientific tool of the next decade. The ability to simulate systems at the molecular scale starting from nothing but quantum mechanics will be transformative for a vast range of problems throughout biology and chemistry 1/n

The Potential of #Neural Network Potentials A perspective from Timothy Duignan @TimothyDuignan @Griffith_Uni 🔓 Open access in ACS Physical Chemistry Au 👉 go.acs.org/8zg

Post attachment
Günter Klambauer avatar
⟳ Daniel Klotz retweeted
Günter Klambauer@gklambauer·8 May 2024

xLSTM: Extended Long Short-Term Memory The famous LSTM nets are improved by exponential gates and matrix-memory with covariance update. Strong results on large-scale language modeling. P: arxiv.org/abs/2405.04517

Post attachment