Tootfinder

Ein Update zu der vor acht Jahren auf #Malta ermordeten #Investigativ-Journalistin #DaphneCaruanaGalizia

🇺🇦 Auf radioeins läuft...
Foo Fighters:
🎵 The Teacher
#NowPlaying #FooFighters
https://open.spotify.com/track/7buGBnA0vkYulQafSZnpHx

Building on the 90s, statistical n-gram language models, trained on vast text collections, became the backbone of NLP research. They fueled advancements in nearly all NLP techniques of the era, laying the groundwork for today's AI.
F. Jelinek (1997), Statistical Methods for Speech Recognition, MIT Press, Cambridge, MA
#NLP

Begriffsverwirrungen Nr. 37:
Trojaner ist auch so ne Fehlbezeichnung. Ein Trojaner – also Bürger Trojas – gehört zu den Menschen, die ihre halbe Stadtmauer niedergerissen haben, um ein mit Feinden gefülltes Holzpferd in die Stadt zu holen, dann Party zu machen und so besoffen rumzuhängen, daß sie nicht merken, wie sie überfallen und nieder­gemetzelt werden.
„Sich einen Trojaner einfangen“ beschreibt folglich einfach den erfolgreichen Einsatz von Schadsoftware¹, der dazu führt, d…

This https://arxiv.org/abs/2505.19111 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Remote Sensing Image Classification with Decoupled Knowledge Distillation
To address the challenges posed by the large number of parameters in existing remote sensing image classification models, which hinder deployment on resource-constrained devices, this paper proposes a lightweight classification method based on knowledge distillation. Specifically, G-GhostNet is adopted as the backbone network, leveraging feature reuse to reduce redundant parameters and significantly improve inference efficiency. In addition, a decoupled knowledge distillation strategy is employ…

This https://arxiv.org/abs/2505.24009 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws. Although recent mechanistic-interpretability studies have deepened our understanding of the internal behavior of Transformers by analyzing their residual stream, the relationship between these internal mechanisms an…

Freeze-in production of scalaron dark matter in $f(R)$ gravity
Basabendu Barman, Ashmita Das, Rakesh Kumar SivaKumar, Rudra Pratap Udgata
https://arxiv.org/abs/2506.06436

Freeze-in production of scalaron dark matter in $f(R)$ gravity
We demonstrate that the scalaron, a scalar degree of freedom, emerging from the $f(R)$ theory of gravity, can account for the observed dark matter (DM) abundance if its mass is around the MeV scale, to ensure its cosmological stability. Focusing on two well-known $f(R)$ gravity models, we systematically show that if scalaron production proceeds via the freeze-in mechanism, the right relic abundance is satisfied over a very narrow window of reheating temperature $10^{14}\lesssim T_{\rm rh}\lesss…

Das #Rezept des Tages:
Eine #Gemüsepfanne in #Kokosmilch lässt sich in einem Wok sehr schnell zubereiten. 🌴🍛 Mit knackiger

Reis mit Gemüsepfanne in Kokosmilch
Das ist ein ganz einfaches Rezept und läßt sich beliebig improvisieren.Grundidee: verfügbares Gemüse schnibbeln, ab in den Wok, anbraten, fertig.

MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection
Weihan Lu, Hong Cai Chen
https://arxiv.org/abs/2506.07126 https://

MAGNet: A Multi-Scale Attention-Guided Graph Fusion Network for DRC Violation Detection
Design rule checking (DRC) is of great significance for cost reduction and design efficiency improvement in integrated circuit (IC) designs. Machine-learning-based DRC has become an important approach in computer-aided design (CAD). In this paper, we propose MAGNet, a hybrid deep learning model that integrates an improved U-Net with a graph neural network for DRC violation prediction. The U-Net backbone is enhanced with a Dynamic Attention Module (DAM) and a Multi-Scale Convolution Module (MSCM…

This https://arxiv.org/abs/2501.02469 has been replaced.
link: https://scholar.google.com/scholar?q=a

LoRaConnect: Unlocking HTTP Potential on LoRa Backbones for Remote Areas and Ad-Hoc Networks
The minimal infrastructure requirements of LoRa make it suitable for deployments in remote and disaster-stricken areas. Concomitantly, the modern era is witnessing the proliferation of web applications in all aspects of human life, including IoT and other network services. Contemporary IoT and network solutions heavily rely on web applications to render services. However, despite the recent research and development pivoted around LoRa, there is still a lack of studies focusing on web applicatio…