95 citations · 243 across the 10 of their papers we have counts for
10 papers
A Sovereign, Open-Source Foundation Model for German and English
Soofi-Team, :, Benedikt Droste +30
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B…
The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
Justinas Zaliaduonis, Patrick Putzky, Till Richter +1
Contrastive learning has become a leading paradigm for self-supervised representation learning, yet the conditions under which it recovers meaningful latent geometry remain incompl…
Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Patrick Putzky, Martin Genzel, Mattes Mollenhauer +3
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibi…
Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation
Martin Genzel, Patrick Putzky, Pengfei Zhao +5
The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitation…
Reconstructing missing seismic data using Deep Learning
Dieuwertje Kuijpers, Ivan Vasconcelos, Patrick Putzky
In current seismic acquisition practice, there is an increasing drive for sparsely (in space) acquired data, often in irregular geometry. These surveys can trade off subsurface inf…
Invert to Learn to Invert
Patrick Putzky, Max Welling
Iterative learning to infer approaches have become popular solvers for inverse problems. However, their memory requirements during training grow linearly with model depth, limiting…
i-RIM applied to the fastMRI challenge
Patrick Putzky, Dimitrios Karkalousos, Jonas Teuwen +4
We, team AImsterdam, summarize our submission to the fastMRI challenge (Zbontar et al., 2018). Our approach builds on recent advances in invertible learning to infer models as pres…
Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
Warren R. Morningstar, Laurence Perreault Levasseur, Yashar D. Hezaveh +6
We present a machine learning method for the reconstruction of the undistorted images of background sources in strongly lensed systems. This method treats the source as a pixelated…
Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
Warren R. Morningstar, Yashar D. Hezaveh, Laurence Perreault Levasseur +4
We use convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to estimate the parameters of strong gravitational lenses from interferometric observations. We exp…
Recurrent Inference Machines for Solving Inverse Problems
Patrick Putzky, Max Welling
Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the i…