arXiv subjects

Jörg Franke

Publications and source records attributed to Jörg Franke.

10 recordsLinked to original sources

arXiv2026

Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss

We study the scaling behavior of learning rate and batch size in pretraining dense large language models on English-prevalent corpora. Beyond scaling jointly optimal learning rates and batch sizes, we investigate their marginal evolution with model capacity and data scale and develop a model that captures these relationships. As we employ a Warmup-Stable-Decay learning rate schedule, we further investigate the gains from learning rate annealing over a broad range of hyperparameters settings, models and data budgets, and whether the optimal learning rate and batch size transfer between the stable and decay phases. Finally, we characterize the dependence of loss on model capacity and dataset size, evaluating recently proposed scaling forms that explicitly model their interaction. We find these approaches particularly effective at capturing both undertraining and overtraining regimes across our experiments. This study establishes a first baseline and scaling procedure for the development of future OpenEuroLLM models. We open-source the complete collection of pretraining runs used in this study.

cs.LG↗

arXiv2026

MotionDLO: Hybrid Event- and Frame-Based Tracking of Deformable Linear Objects

Reliably tracking moving deformable linear objects (DLOs) while simultaneously ensuring robustness, accuracy, and temporally consistent state estimation remains a fundamental challenge in robot perception. We introduce MotionDLO, a real-time tracking framework specifically designed to overcome these limitations in temporal continuity and latency. The method exploits the high temporal resolution and sparsity of event-based cameras and combines segmentation with the Coherent Point Drift (CPD) algorithm under the principles of Motion Coherence Theory. This integration enables temporally consistent shape estimation while maintaining a low computational overhead. Existing event-based tracking methods are typically computationally efficient but exhibit reduced accuracy compared to frame-based approaches, or alternatively compromise event sparsity to achieve competitive performance. To resolve this trade-off, we propose a hybrid event- and frame-based tracking architecture that preserves the complementary strengths of both sensing modalities. The event stream ensures high-frequency motion updates, while frame-based information stabilizes spatial accuracy and object identity. We demonstrate that the proposed framework reliably associates DLO instances across video sequences, enabling robust perception for robotic manipulation tasks. Experimental results validate real-time performance at 12 ms update rates and accurate shape tracking with an point-to-curve error as measurement of accuracy of up to 0.43 mm, supporting dynamic path adaptation during manipulation. The source code and demonstration datasets are publicly available.

cs.RO↗

arXiv2026

Practitioner Motives to Use Different Hyperparameter Optimization Methods

Programmatic hyperparameter optimization (HPO) methods, such as Bayesian optimization and evolutionary algorithms, are highly sample-efficient in identifying optimal hyperparameter configurations for machine learning (ML) models. However, practitioners frequently use less efficient methods, such as grid search, which can lead to under-optimized models. We suspect this behavior is driven by a range of practitioner-specific motives. Practitioner motives, however, still need to be clarified to enhance user-centered development of HPO tools. To uncover practitioner motives to use different HPO methods, we conducted 20 semi-structured interviews and an online survey with 49 ML experts. By presenting main goals (e.g., increase ML model understanding) and contextual factors affecting practitioners' selection of HPO methods (e.g., available computer resources), this study offers a conceptual foundation to better understand why practitioners use different HPO methods, supporting development of more user-centered and context-adaptive HPO tools in automated ML.

cs.LG↗

arXiv2025

Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison

We introduce open-sci-ref, a family of dense transformer models trained as research baselines across multiple model (0.13B to 1.7B parameters) and token scales (up to 1T) on 8 recent open reference datasets. Evaluating the models on various standardized benchmarks, our training runs set establishes reference points that enable researchers to assess the sanity and quality of alternative training approaches across scales and datasets. Intermediate checkpoints allow comparison and studying of the training dynamics. The established reference baselines allow training procedures to be compared through their scaling trends, aligning them on a common compute axis. Comparison of open reference datasets reveals that training on NemoTron-CC HQ consistently outperforms other reference datasets, followed by DCLM-baseline and FineWeb-Edu. In addition to intermediate training checkpoints, the release includes logs, code, and downstream evaluations to simplify reproduction, standardize comparison, and facilitate future research.

cs.LG↗

arXiv2024

MyoGestic: EMG Interfacing Framework for Decoding Multiple Spared Degrees of Freedom of the Hand in Individuals with Neural Lesions

Restoring limb motor function in individuals with spinal cord injury (SCI), stroke, or amputation remains a critical challenge, one which affects millions worldwide. Recent studies show through surface electromyography (EMG) that spared motor neurons can still be voluntarily controlled, even without visible limb movement . These signals can be decoded and used for motor intent estimation; however, current wearable solutions lack the necessary hardware and software for intuitive interfacing of the spared degrees of freedom after neural injuries. To address these limitations, we developed a wireless, high-density EMG bracelet, coupled with a novel software framework, MyoGestic. Our system allows rapid and tailored adaptability of machine learning models to the needs of the users, facilitating real-time decoding of multiple spared distinctive degrees of freedom. In our study, we successfully decoded the motor intent from two participants with SCI, two with spinal stroke , and three amputees in real-time, achieving several controllable degrees of freedom within minutes after wearing the EMG bracelet. We provide a proof-of-concept that these decoded signals can be used to control a digitally rendered hand, a wearable orthosis, a prosthesis, or a 2D cursor. Our framework promotes a participant-centered approach, allowing immediate feedback integration, thus enhancing the iterative development of myocontrol algorithms. The proposed open-source software framework, MyoGestic, allows researchers and patients to focus on the augmentation and training of the spared degrees of freedom after neural lesions, thus potentially bridging the gap between research and clinical application and advancing the development of intuitive EMG interfaces for diverse neural lesions.

cs.HC↗

arXiv2024

Fast Optimizer Benchmark

In this paper, we present the Fast Optimizer Benchmark (FOB), a tool designed for evaluating deep learning optimizers during their development. The benchmark supports tasks from multiple domains such as computer vision, natural language processing, and graph learning. The focus is on convenient usage, featuring human-readable YAML configurations, SLURM integration, and plotting utilities. FOB can be used together with existing hyperparameter optimization (HPO) tools as it handles training and resuming of runs. The modular design enables integration into custom pipelines, using it simply as a collection of tasks. We showcase an optimizer comparison as a usage example of our tool. FOB can be found on GitHub: https://github.com/automl/FOB.

cs.LG↗

arXiv2023

Non-Sequential Ensemble Kalman Filtering using Distributed Arrays

This work introduces a new, distributed implementation of the Ensemble Kalman Filter (EnKF) that allows for non-sequential assimilation of large datasets in high-dimensional problems. The traditional EnKF algorithm is computationally intensive and exhibits difficulties in applications requiring interaction with the background covariance matrix, prompting the use of methods like sequential assimilation which can introduce unwanted consequences, such as dependency on observation ordering. Our implementation leverages recent advancements in distributed computing to enable the construction and use of the full model error covariance matrix in distributed memory, allowing for single-batch assimilation of all observations and eliminating order dependencies. Comparative performance assessments, involving both synthetic and real-world paleoclimatic reconstruction applications, indicate that the new, non-sequential implementation outperforms the traditional, sequential one.

stat.ML↗

arXiv2023

A Digital Twin to overcome long-time challenges in Photovoltaics

The recent successes of emerging photovoltaics (PV) such as organic and perovskite solar cells are largely driven by innovations in material science. However, closing the gap to commercialization still requires significant innovation to match contradicting requirements such as performance, longevity and recyclability. The rate of innovation, as of today, is limited by a lack of design principles linking chemical motifs to functional microscopic structures, and by an incapacity to experimentally access microscopic structures from investigating macroscopic device properties. In this work, we envision a layout of a Digital Twin for PV materials aimed at removing both limitations. The layout combines machine learning approaches, as performed in materials acceleration platforms (MAPs), with mathematical models derived from the underlying physics and digital twin concepts from the engineering world. This layout will allow using high-throughput (HT) experimentation in MAPs to improve the parametrization of quantum chemical and solid-state models. In turn, the improved and generalized models can be used to obtain the crucial structural parameters from HT data. HT experimentation will thus yield a detailed understanding of generally valid structure-property relationships, enabling inverse molecular design, that is, predicting the optimal chemical structure and process conditions to build PV devices satisfying a multitude of requirements at the same time. After motivating our proposed layout of the digital twin with causal relationships in material science, we discuss the current state of the enabling technologies, already being able to yield insight from HT data today. We identify open challenges with respect to the multiscale nature of PV materials and the needed volume and diversity of data, and mention promising approaches to address these challenges.

cond-mat.mtrl-sci↗

arXiv2018

Robust and Scalable Differentiable Neural Computer for Question Answering

Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments. The differentiable neural computer (DNC), a memory-augmented neural network, is designed as a general problem solver which can be used in a wide range of tasks. But in reality, it is hard to apply this model to new tasks. We analyze the DNC and identify possible improvements within the application of question answering. This motivates a more robust and scalable DNC (rsDNC). The objective precondition is to keep the general character of this model intact while making its application more reliable and speeding up its required training time. The rsDNC is distinguished by a more robust training, a slim memory unit and a bidirectional architecture. We not only achieve new state-of-the-art performance on the bAbI task, but also minimize the performance variance between different initializations. Furthermore, we demonstrate the simplified applicability of the rsDNC to new tasks with passable results on the CNN RC task without adaptions.

cs.CL↗

arXiv2015

$^4$He sample probe for combined microwave and dc transport measurements

Combined microwave and dc electrical transport measurements at low temperatures represent a valuable experimental method in many research areas. In particular, when samples are conventional superconductors, a typical experiment requires a combination of helium temperatures, a wide range of magnetic fields, and the utilization of coaxial lines along with the usual dc wiring. We report on the general design features and the microwave performance of a custom-made low-temperature sample probe, with a measurement bandwidth tested from dc to 20 GHz. Equipped with 6 coaxial cables, a heater, Hall and temperature sensors, the probe fits into a d32 mm shaft. We present our setup, analyze its microwave performance, and describe two representative experiments enabled by this system. The proposed setup will be essential for a systematic study of the dc and ac response of the vortex dynamics in nanopatterned superconductors subject to combined dc and microwave stimuli. Besides, it will be valuable for the investigation of a broad class of nonlinear stochastic systems where a combination of dc and high-frequency ac driving in a wide temperature range is necessary.

cond-mat.supr-con↗