Tootfinder

How Reinforcement Learning After Next-Token Prediction Facilitates Learning
Nikolaos Tsilivis, Eran Malach, Karen Ullrich, Julia Kempe
https://arxiv.org/abs/2510.11495 https://

How Reinforcement Learning After Next-Token Prediction Facilitates Learning
Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the next-token in a sequence, with reinforcement learning algorithms. We introduce a framework to study the success of this paradigm, and we theoretically expose the optimization mechanisms by which reinforcement learning improves over next-token prediction in this setting. We study learning from mixture distributions of s…

n-report-Projekt: Wie KI die Sprache von Schülerinnen und Schülern verändert
Beim Begutachten der Schülerbeiträge des diesjährigen n-report-Wettbewerbs merkte unsere Redakteurin auf. Wendungen glichen sich frappant – und dem KI-Sprech.

Bucs rookie WR Tez Johnson confused why he received MVP chants before learning they were for Baker Mayfield

https://www.cbssports.com/nfl/news/bucs-ro

"Europa wird im Digitalen nur souverän sein, wenn es seine eigene Rolle richtig versteht: nicht als Festung, nicht als Kopie amerikanischer Tech-Konzerne, sondern als Gestalter industriellen Deep Techs, als Produzent von Präzision, Energieeffizienz und strategischen Technologien, die niemand ersetzen kann. Souveränität wäre dann nicht das Pathos des Ausnahmezustands, sondern die Nüchternheit der Gestaltungskraft." @…

Die verwechselte Souveränität – Warum Europa im Digitalen nicht herrschen, sondern handeln lernen muss - ichsagmal.com
Souveränität ist zu einem Wort geworden, das in Europa auf jeder Bühne erklingt: auf dem Digitalgipfel in Berlin, in vertraulichen Runden in Brüssel, in Ministerreden und Strategiepapiersätzen, die klingen wie Durchhalteformeln einer verunsicherten Moderne. Doch je häufiger der Begriff ertönt, desto leerer wirkt er. Fragt man genauer nach, heißt es beschwichtigend: Natürlich ist nicht Autarkie … Die verwechselte Souveränität – Warum Europa im Digitalen nicht herrschen, sondern ha…

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Yansong Wang, Qihui Lin, Junjie Huang, Tao Jia
https://arxiv.org/abs/2510.09129 https://

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, w…

Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): II. A Physics-Informed Machine Learning Method for 3D Solar Photosphere Reconstruction
Kai E. Yang, Xudong Sun, Lucas A. Tarr, Jiayi Liu, Peter Sadowski, S. Curt Dodds, Matthias Rempel, Sarah A. Jaeggli, Thomas A. Schad, Ian Cunnyngham, Yannik Glaser, Linnea Wolniewicz
https://…

Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): II. A Physics-Informed Machine Learning Method for 3D Solar Photosphere Reconstruction
Inferring the three-dimensional (3D) solar atmospheric structures from observations is a critical task for advancing our understanding of the magnetic fields and electric currents that drive solar activity. In this work, we introduce a novel, Physics-Informed Machine Learning method to reconstruct the 3D structure of the lower solar atmosphere based on the output of optical depth sampled spectropolarimetric inversions, wherein both the fully disambiguated vector magnetic fields and the geometri…

Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning
Dominik Urbaniak, Alejandro Agostini, Pol Ramon, Jan Rosell, Ra\'ul Su\'arez, Michael Suppa
https://arxiv.org/abs/2510.09254

Obstacle Avoidance using Dynamic Movement Primitives and Reinforcement Learning
Learning-based motion planning can quickly generate near-optimal trajectories. However, it often requires either large training datasets or costly collection of human demonstrations. This work proposes an alternative approach that quickly generates smooth, near-optimal collision-free 3D Cartesian trajectories from a single artificial demonstration. The demonstration is encoded as a Dynamic Movement Primitive (DMP) and iteratively reshaped using policy-based reinforcement learning to create a di…

Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
Nges Brian Njungle, Eric Jahns, Luigi Mastromauro, Edwin P. Kayang, Milan Stojkov, Michel A. Kinsy
https://arxiv.org/abs/2510.09985

Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
Machine learning has become a crucial part of our lives, with applications spanning nearly every aspect of our daily activities. However, using personal information in machine learning applications has sparked significant security and privacy concerns about user data. To address these challenges, different privacy-preserving machine learning (PPML) frameworks have been developed to protect sensitive information in machine learning applications. These frameworks generally attempt to balance desi…

Investigating the Impact of Rational Dilated Wavelet Transform on Motor Imagery EEG Decoding with Deep Learning Models
Marco Siino, Giuseppe Bonomo, Rosario Sorbello, Ilenia Tinnirello
https://arxiv.org/abs/2510.09242

Investigating the Impact of Rational Dilated Wavelet Transform on Motor Imagery EEG Decoding with Deep Learning Models
The present study investigates the impact of the Rational Discrete Wavelet Transform (RDWT), used as a plug-in preprocessing step for motor imagery electroencephalographic (EEG) decoding prior to applying deep learning classifiers. A systematic paired evaluation (with/without RDWT) is conducted on four state-of-the-art deep learning architectures: EEGNet, ShallowConvNet, MBEEG\_SENet, and EEGTCNet. This evaluation was carried out across three benchmark datasets: High Gamma, BCI-IV-2a, and BCI-I…

What Do Temporal Graph Learning Models Learn?
Abigail J. Hayes, Tobias Schumacher, Markus Strohmaier
https://arxiv.org/abs/2510.09416 https://arxiv.org/pdf…

What Do Temporal Graph Learning Models Learn?
Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability of benchmark results, noting issues with commonly used evaluation protocols and the surprising competitiveness of simple heuristics. This contrast raises the question of which properties of the underlying graphs temporal graph learning models actually use to f…