Zobrazeno 1 - 10
of 2 883
pro vyhledávání: '"A. P. Hutter"'
Autor:
Mallik, Neeratyoy, Janowski, Maciej, Hog, Johannes, Rakotoarison, Herilalaina, Klein, Aaron, Grabocka, Josif, Hutter, Frank
Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws that guides subsequent research.
Externí odkaz:
http://arxiv.org/abs/2411.07340
Autor:
Zalevskyi, Vladyslav, Sanchez, Thomas, Roulet, Margaux, Lajous, Hélène, Verdera, Jordina Aviles, Hutter, Jana, Kebiri, Hamza, Cuadra, Meritxell Bach
Fetal brain tissue segmentation in magnetic resonance imaging (MRI) is a crucial tool that supports the understanding of neurodevelopment, yet it faces challenges due to the heterogeneity of data coming from different scanners and settings, and due t
Externí odkaz:
http://arxiv.org/abs/2411.06842
Autor:
Lu, Ting-Yi, Mason, Charlotte A., Mesinger, Andrei, Prelogović, David, Nikolić, Ivan, Hutter, Anne, Gagnon-Hartman, Samuel, Tang, Mengtao, Qin, Yuxiang, Kakiichi, Koki
Ionized bubble sizes during reionization trace physical properties of the first galaxies. JWST's ability to spectroscopically confirm and measure Lyman-alpha (Ly$\alpha$) emission in sub-L* galaxies opens the door to mapping ionized bubbles in 3D. Ho
Externí odkaz:
http://arxiv.org/abs/2411.04176
Autor:
Talbot, William, Nubert, Julian, Tuna, Turcan, Cadena, Cesar, Dümbgen, Frederike, Tordesillas, Jesus, Barfoot, Timothy D., Hutter, Marco
Accurate, efficient, and robust state estimation is more important than ever in robotics as the variety of platforms and complexity of tasks continue to grow. Historically, discrete-time filters and smoothers have been the dominant approach, in which
Externí odkaz:
http://arxiv.org/abs/2411.03951
Autor:
Bagajo, Joshua, Schwarke, Clemens, Klemm, Victor, Georgiev, Ignat, Sleiman, Jean-Pierre, Tordesillas, Jesus, Garg, Animesh, Hutter, Marco
Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion policies trained
Externí odkaz:
http://arxiv.org/abs/2411.02189
Autor:
Strangmann, Tobias, Purucker, Lennart, Franke, Jörg K. H., Rapant, Ivo, Ferreira, Fabio, Hutter, Frank
As the landscape of large language models expands, efficiently finetuning for specific tasks becomes increasingly crucial. At the same time, the landscape of parameter-efficient finetuning methods rapidly expands. Consequently, practitioners face a m
Externí odkaz:
http://arxiv.org/abs/2411.01195
Autor:
Arango, Sebastian Pineda, Janowski, Maciej, Purucker, Lennart, Zela, Arber, Hutter, Frank, Grabocka, Josif
Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles of neural n
Externí odkaz:
http://arxiv.org/abs/2410.19889
Navigating efficiently to an object in an unexplored environment is a critical skill for general-purpose intelligent robots. Recent approaches to this object goal navigation problem have embraced a modular strategy, integrating classical exploration
Externí odkaz:
http://arxiv.org/abs/2410.19697
Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time, researchers
Externí odkaz:
http://arxiv.org/abs/2410.17787
Reinforcement learning (RL) often necessitates a meticulous Markov Decision Process (MDP) design tailored to each task. This work aims to address this challenge by proposing a systematic approach to behavior synthesis and control for multi-contact lo
Externí odkaz:
http://arxiv.org/abs/2410.13817