Tootfinder

The Gustav Klimt portrait of Elisabeth Lederer,
which was looted by the Nazis and nearly destroyed in a fire during the second world war,
sells for $236.4m,
making it the second most expensive artwork ever sold at auction

Raiders’ Darien Porter intent on learning from mistakes https://www.reviewjournal.com/sports/raiders/raiders-darien-porter-intent-on-learning-from-mistakes-3597557/

White House adds plaques below Biden and Obama portraits, calling them 'the worst President in American history' and 'divisive' (Ariana Baio/The Independent)
https://www.independent.co.uk/news/world/americas/us-politics/white-house-portraits-biden-obama-trump-b2886535.html
http://www.memeorandum.com/251217/p112#a251217p112

Semi-Supervised 3D Medical Segmentation from 2D Natural Images Pretrained Model
Pak-Hei Yeung, Jayroop Ramesh, Pengfei Lyu, Ana Namburete, Jagath Rajapakse
https://arxiv.org/abs/2509.15167

Semi-Supervised 3D Medical Segmentation from 2D Natural Images Pretrained Model
This paper explores the transfer of knowledge from general vision models pretrained on 2D natural images to improve 3D medical image segmentation. We focus on the semi-supervised setting, where only a few labeled 3D medical images are available, along with a large set of unlabeled images. To tackle this, we propose a model-agnostic framework that progressively distills knowledge from a 2D pretrained model to a 3D segmentation model trained from scratch. Our approach, M&N, involves iterative co-…

Patent Language Model Pretraining with ModernBERT
Amirhossein Yousefiramandi, Ciaran Cooney
https://arxiv.org/abs/2509.14926 https://arxiv.org/pdf/2509.149…

Patent Language Model Pretraining with ModernBERT
Transformer-based language models such as BERT have become foundational in NLP, yet their performance degrades in specialized domains like patents, which contain long, technical, and legally structured text. Prior approaches to patent NLP have primarily relied on fine-tuning general-purpose models or domain-adapted variants pretrained with limited data. In this work, we pretrain 3 domain-specific masked language models for patents, using the ModernBERT architecture and a curated corpus of over …

Le trafic est interrompu entre Marly-le-Roi et St-Nom-la-Bretèche dans les 2 sens jusqu'Š 21h et perturbé entre Paris Saint-Lazare et Marly-le-Roi dans les 2 sens.
Rendez-vous sur la rubrique "Recherche Itinéraire", pour retrouver un itinéraire prenant en compte cette perturbation.
Pour plus d'informations sur cette perturbation, consultez le fil X de la ligne L.
Motif : Incident affectant les voies entre Marly-le-Roi et St-Nom-la-Bretêche.
🤖 19/09 19…

ExT: Towards Scalable Autonomous Excavation via Large-Scale Multi-Task Pretraining and Fine-Tuning
Yifan Zhai, Lorenzo Terenzi, Patrick Frey, Diego Garcia Soto, Pascal Egli, Marco Hutter
https://arxiv.org/abs/2509.14992

ExT: Towards Scalable Autonomous Excavation via Large-Scale Multi-Task Pretraining and Fine-Tuning
Scaling up the deployment of autonomous excavators is of great economic and societal importance. Yet it remains a challenging problem, as effective systems must robustly handle unseen worksite conditions and new hardware configurations. Current state-of-the-art approaches rely on highly engineered, task-specific controllers, which require extensive manual tuning for each new scenario. In contrast, recent advances in large-scale pretrained models have shown remarkable adaptability across tasks a…

Olivia's friend Danielle wearing a witch hat at a Horse show put on by Maine Mavericks at Whitney Point
#photo #photography #portrait

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Yuming Jiang, Siteng Huang, Shengke Xue, Yaxi Zhao, Jun Cen, Sicong Leng, Kehan Li, Jiayan Guo, Kexiang Wang, Mingxiu Chen, Fan Wang, Deli Zhao, Xin Li
https://arxiv.org/abs/2509.15212

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pretraining methodology. The first stage, Ego-Centric Video Generative Pretraining, trains an Image-to-Video model on 12M ego-centric manipulation videos to predict future frames conditioned on an initial frame and a language instruction. The second stage, Human-Centric Trajectory-Aware Modeling, extends this by jointly …

Here's a photo of me that my son took near the very highest point of Shindagin Hollow State Forest
#photo #photography #portrait