Tootfinder

Eine beeindruckende Persönlichkeit: Benjamin Ferencz, der 27jährige Chefankläger in den Nürnberger Prozessen
Sehenswertes Interview!
#Empfehlung
https…

Nürnberger Prozesse: »Es war, als hätte ich in die Hölle geschaut«
Benjamin Ferencz war 27, als er bei den Nürnberger Prozessen die Anklage vortrug. Vor fünf Jahren erinnerte er sich im Video, wie er in KZs ermittelte und mit einem der Massenmörder vor dessen Hinrichtung sprach. Ferencz ist inzwischen gestorben.

Was kann man in #Nürnberg machen, wenn man zwei bis drei Stunden Zeit hat? Habt ihr Hinweise?

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Neil C. Janwani, Varun Madabushi, Maegan Tucker
https://arxiv.org/abs/2510.11542 https…

NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning
Reinforcement learning (RL) has emerged as a powerful method to learn robust control policies for bipedal locomotion. Yet, it can be difficult to tune desired robot behaviors due to unintuitive and complex reward design. In comparison, offline trajectory optimization methods, like Hybrid Zero Dynamics, offer more tuneable, interpretable, and mathematically grounded motion plans for high-dimensional legged systems. However, these methods often remain brittle to real-world disturbances like exter…

#TGIQF: Das Quiz rund um die deutsche bemannte Raumfahrt
In den vergangenen vier Jahrzehnten flogen mehrere Männer und endlich auch eine Frau aus Deutschland ins All. Wir blicken in einem Quiz zurück. Machen Sie mit!

«But hegemony is fragile – it must be reinforced and modified through continued reassertion of power. […] AI automates this reinforcement – the WEIRD values of the texts that build this new form of intelligence are not just common sense, they are how the machine knows how to answer questions and produce text…»
Really enjoyed @…'s notes on "Gramsci’s Nightmare: AI, Platform Power and the Automation of Cultural Hegemony"
https://ethanzuckerman.com/2025/12/05/gramscis-nightmare-ai-platform-power-and-the-automation-of-cultural-hegemony/

Retrocedamos solo un año, hasta 1983, cuando R.E.M. publicaba su primer larga duración (antes habían publicado el EP Chronic Town). ¡Cómo no la iban a romper en los círculos universitarios y underground con este discazo que aún sigue sonando fresco y original!
Murmur
#REM #NowPlaying

DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems
Yuanjun Dai, Keqiang He, An Wang
https://arxiv.org/abs/2510.08522 https://

DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems
Existing batch size selection approaches in dis- tributed machine learning rely on static allocation or simplistic heuristics that fail to adapt to heterogeneous, dynamic computing environments. We present DYNAMIX, a reinforcement learning framework that formulates batch size optimization as a sequen- tial decision-making problem using Proximal Policy Optimiza- tion (PPO). Our approach employs a multi-dimensional state representation encompassing network-level metrics, system-level resource uti…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[8/14]:
- From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement...
David Dinucu-Jianu, Jakub Macina, Nico Daheim, Ido Hakimi, Iryna Gurevych, Mrinmaya Sachan

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/14]:
- OrbitZoo: Multi-Agent Reinforcement Learning Environment for Orbital Dynamics
Alexandre Oliveira, Katarina Dyreby, Francisco Caldas, Cl\'audia Soares

Robot Learning: A Tutorial
Francesco Capuano, Caroline Pascal, Adil Zouitine, Thomas Wolf, Michel Aractingi
https://arxiv.org/abs/2510.12403 https://arxiv.…

Robot Learning: A Tutorial
Robot learning is at an inflection point, driven by rapid advancements in machine learning and the growing availability of large-scale robotics data. This shift from classical, model-based methods to data-driven, learning-based paradigms is unlocking unprecedented capabilities in autonomous systems. This tutorial navigates the landscape of modern robot learning, charting a course from the foundational principles of Reinforcement Learning and Behavioral Cloning to generalist, language-conditione…