Tootfinder

Evaluating Ensemble and Deep Learning Models for Static Malware Detection with Dimensionality Reduction Using the EMBER Dataset
Md Min-Ha-Zul Abedin, Tazqia Mehrub
https://arxiv.org/abs/2507.16952

Evaluating Ensemble and Deep Learning Models for Static Malware Detection with Dimensionality Reduction Using the EMBER Dataset
This study investigates the effectiveness of several machine learning algorithms for static malware detection using the EMBER dataset, which contains feature representations of Portable Executable (PE) files. We evaluate eight classification models: LightGBM, XGBoost, CatBoost, Random Forest, Extra Trees, HistGradientBoosting, k-Nearest Neighbors (KNN), and TabNet, under three preprocessing settings: original feature space, Principal Component Analysis (PCA), and Linear Discriminant Analysis (L…

Junggesellen­abschied ist auch so ein Phänomen. Früher nur in Gegenden, da es die Tradition des Polterabends nicht gab, wurde der künftige Bräutigam¹ von Kumpels am Abend vor der Hochzeit² in ne Kneipe gelotst³ und stand dann Tags drauf verkatert mit Restalkohol⁴ vor dem Altar.
Heutzutage ist ein JGA immer öfter ein großes, für die Beteiligten teures Event, da werden Partyflüge nach Mallorca gebucht… Mir reichten ja schon die mit Kappen und extra fürs Event bedruckten T-Shirts Uniformi…

🇺🇦 #NowPlaying on #BBC6Music's #Glastonbury
Blondie:
🎵 Union City Blue
#Blondie
https://carnivalstar.bandcamp.com/track/union-city-blue-blondie-cover-ftr-allegra-lusini
https://open.spotify.com/track/27pRt9vwkrFUFp9lgzKkCl

Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
Buddhi Wijenayake, Athulya Ratnayake, Praveen Sumanasekara, Nichula Wasalathilaka, Mathivathanan Piratheepan, Roshan Godaliyadda, Mervyn Ekanayake, Vijitha Herath
https://arxiv.org/abs/2507.11523

Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as convolutional neural networks (CNNs), struggle to capture long-range dependencies and global context essential for accurate change detection in complex scenes. While Transformer-based models mitigate these issues, their computational complexity limits their applica…

Interesting that some who replied to my post on tax and GDP growth yesterday missed the point.
The point isn't to debate whether tax -> growth (it might, with a tail wind).
The point is that
1) Growth won't happen like it used to.
2) That is good because GDP growth is ecologically and socially lethal.
3) So our leaders (sic) had better adapt to the new reality and use taxation and other measures to build a better, fairer future.
More here:

Getting Real about the Crises Facing the UK | Stop the Damage! Build a Better Future!
Britain and the rest of the world face a set of almost intractable challenges, ecological (including climate), economic and social. Yet political leaders with few exceptions are failing to propose the actions and policies that could address the scale of this pancrisis. Here though is an alternative initiative, a kind of alternative manifesto with a portfolio of illustrative policies...

projects in the near future:
1. my mac-mini server runs ubuntu server and need apps. I'm thinking about Heimdall and a next cloud instance that I can reach via tailscale. I will also use it as an exit node for my tailscale network.
2. Making the server sleep when not in use and use an old RPi to 'wake it up' also over tailscale.
3. Making a portable router out of a Radxa Rock 4c that also use tailscale as a vpn alternative using the exit node.

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Pengfei Cai, Yan Song, Qing Gu, Nan Jiang, Haoyu Song, Ian McLoughlin
https://arxiv.org/abs/2507.16343

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting audio-language models, their performance is still far from satisfactory due to the lack of fine-grained alignment and cross-modal feature fusion. In this work, we propose the Detect Any Sound Model (DASM), a query-based framework for open-vocabulary SED guided by …

Probably stating the obvious, but for the past 30 years at least, contributing (in any capacity) on opensource projects is an excellent way to network with a global pool of top-tier folks in all the related domains, and to test the limits of your craft, plus all the work you do can be openly shared with any prospective employer. So you aren't 'volunteering' as much as you're building your portfolio in grad school, but with no student fees 😁
#fedihire #lifelonglearning

Kernel Learning for Mean-Variance Trading Strategies
Owen Futter, Nicola Muca Cirone, Blanka Horvath
https://arxiv.org/abs/2507.10701 https://

Kernel Learning for Mean-Variance Trading Strategies
In this article, we develop a kernel-based framework for constructing dynamic, pathdependent trading strategies under a mean-variance optimisation criterion. Building on the theoretical results of (Muca Cirone and Salvi, 2025), we parameterise trading strategies as functions in a reproducing kernel Hilbert space (RKHS), enabling a flexible and non-Markovian approach to optimal portfolio problems. We compare this with the signature-based framework of (Futter, Horvath, Wiese, 2023) and demonstrat…

📣 Calling all GÉANT Project partners…
Got an idea for digital research, data transfer or secure storage solutions to support open science?
The 2025 GÉANT Above-the-Net Services Incubator is officially open for proposals!
This is your opportunity to:
✅ Develop and test your innovative idea
✅ Deliver impact to the whole community through new, shared, open-source services
✅ Help shape the future of GÉANT's Above-the-Net services portfolio
Learn more: …

GÉANT Project Above-the-Net Services Incubator: Call for Proposals | GÉANT CONNECT Online
The GÉANT (GN5-2) Project’s Above-the-Net Services incubator is looking for practical proposals around three areas of service concept investment being developed by the GN5-2 Above-the-Net Services team. These are: Digital Research Environment (DRE) Object Storage Infrastructure Data Movement Infrastructure Through the incubator, the GN5-2 project will offer person months (PMs) to project partners to develop