Tootfinder

11 Gorgeous Places Americans Can Visit Right Now Without Passport or Immigration Drama https://themodernfield.com/epic-places-americans-visit-without-pass…

11 Gorgeous Places Americans Can Visit Right Now Without Passport or Immigration Drama
Got that travel bug, but your passport is gathering dust? Or maybe you just realized it expired. Don't worry. I've been there. You don't have to put your dreams of an epic getaway on hold.

> „Zlibrusowana” szkoła jest dobra dla dorosłych, a nie dla uczniów. Rozczarowuje zaś, a czasem i krzywdzi, chyba wszystkich po kolei.
https://klubjagiellonski.pl/2025/08/29/librus-a-kryzys-polskiej-szkoly-manifest-o-odbudowie-zaufania/

Hegseth tells troops to resign if they oppose his plan to scrap 'woke' policies and restore warrior ethos (Morgan Phillips/Fox News)
https://www.foxnews.com/politics/hegseth-tells-troops-resign-oppose-his-plan-scrap-woke-policies-restore-warrior-ethos
http://www.memeorandum.com/250930/p84#a250930p84

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
Jan Ole von Hartz, Lukas Schweizer, Joschka Boedecker, Abhinav Valada
https://arxiv.org/abs/2509.24956

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
Generative robot policies such as Flow Matching offer flexible, multi-modal policy learning but are sample-inefficient. Although object-centric policies improve sample efficiency, it does not resolve this limitation. In this work, we propose Multi-Stream Generative Policy (MSG), an inference-time composition framework that trains multiple object-centric policies and combines them at inference to improve generalization and sample efficiency. MSG is model-agnostic and inference-only, hence widely…

In der schwarz-roten Koalition wird über die Streichung von #Pflegegrad 1 diskutiert.
Davon wären rund 861.000 Menschen betroffen. Der niedrigste Pflegegrad umfasst #Unterstützungsleistungen wie Hilfe beim Duschen oder Einkaufen.
Die

Schwarz-rote Koalition diskutiert Abschaffung von Pflegegrad 1
Die schwarz-rote Koalition diskutiert die Abschaffung von Pflegegrad 1. Rund 861.000 Menschen könnten betroffen sein. Erste Ergebnisse im Oktober.

Understanding traffic
I bike to work and to lots of other places because I don't like traffic (and the Boston area has traffic) and I don't like looking for parking.  Lots of other people choose to drive despite the traffic, but almost every single person in traffic complains about traffic.  I don't want to just go with the glib "you ARE traffic", but instead, maybe help people understand what causes traffic congestion and why, because if we don't understand t…

Understanding traffic
I bike to work and to lots of other places because I don’t like traffic (and the Boston area has traffic) and I don’t like looking for parking.  Lots of other people choose to drive des…

#NowPlaying https://youtube.com/playlist?list=PLqyKv1gGH4ZChN9opXAGFSfn6LTPR41mF

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
Ma\"el Macuglia, Paul Friedrich, Giorgia Ramponi
https://arxiv.org/abs/2509.26605 https…

Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement Learning
Deploying reinforcement learning (RL) in robotics, industry, and health care is blocked by two obstacles: the difficulty of specifying accurate rewards and the risk of unsafe, data-hungry exploration. We address this by proposing a two-stage framework that first learns a safe initial policy from a reward-free dataset of expert demonstrations, then fine-tunes it online using preference-based human feedback. We provide the first principled analysis of this offline-to-online approach and introduce…

Curriculum Imitation Learning of Distributed Multi-Robot Policies
Jes\'us Roche, Eduardo Sebasti\'an, Eduardo Montijano
https://arxiv.org/abs/2509.25097 https://

Curriculum Imitation Learning of Distributed Multi-Robot Policies
Learning control policies for multi-robot systems (MRS) remains a major challenge due to long-term coordination and the difficulty of obtaining realistic training data. In this work, we address both limitations within an imitation learning framework. First, we shift the typical role of Curriculum Learning in MRS, from scalability with the number of robots, to focus on improving long-term coordination. We propose a curriculum strategy that gradually increases the length of expert trajectories du…

From Code to Action: Hierarchical Learning of Diffusion-VLM Policies
Markus Peschl, Pietro Mazzaglia, Daniel Dijkman
https://arxiv.org/abs/2509.24917 https://

From Code to Action: Hierarchical Learning of Diffusion-VLM Policies
Imitation learning for robotic manipulation often suffers from limited generalization and data scarcity, especially in complex, long-horizon tasks. In this work, we introduce a hierarchical framework that leverages code-generating vision-language models (VLMs) in combination with low-level diffusion policies to effectively imitate and generalize robotic behavior. Our key insight is to treat open-source robotic APIs not only as execution interfaces but also as sources of structured supervision: …