Tootfinder

Ascent Fails to Forget
Ioannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi, Volkan Cevher
https://arxiv.org/abs/2509.26427 https://arxiv.org/pdf/250…

Ascent Fails to Forget
Contrary to common belief, we show that gradient ascent-based unconstrained optimization methods frequently fail to perform machine unlearning, a phenomenon we attribute to the inherent statistical dependence between the forget and retain data sets. This dependence, which can manifest itself even as simple correlations, undermines the misconception that these sets can be independently manipulated during unlearning. We provide empirical and theoretical evidence showing these methods often fail p…

Interdisciplinary Digital Twin Engine InterTwin for calorimeter simulation
Corentin Allaire, Vera Maiboroda, David Rousseau
https://arxiv.org/abs/2509.26527 https://

Interdisciplinary Digital Twin Engine InterTwin for calorimeter simulation
Calorimeter shower simulations are computationally expensive, and generative models offer an efficient alternative. However, achieving a balance between accuracy and speed remains a challenge, with distribution tail modeling being a key limitation. Invertible generative network CaloINN provides a trade-off between simulation quality and efficiency. The ongoing study targets introducing a set of post-processing modifications of analysis-level observables aimed at improving the accuracy of distri…

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
Maybritt Schillinger, Maxim Samarin, Xinwei Shen, Reto Knutti, Nicolai Meinshausen
https://arxiv.org/abs/2509.26258

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
The practical use of future climate projections from global circulation models (GCMs) is often limited by their coarse spatial resolution, requiring downscaling to generate high-resolution data. Regional climate models (RCMs) provide this refinement, but are computationally expensive. To address this issue, machine learning models can learn the downscaling function, mapping coarse GCM outputs to high-resolution fields. Among these, generative approaches aim to capture the full conditional distr…

Multilingual Hope Speech Detection: A Comparative Study of Logistic Regression, mBERT, and XLM-RoBERTa with Active Learning
T. O. Abiola, K. D. Abiodun, O. E. Olumide, O. O. Adebanji, O. Hiram Calvo, Grigori Sidorov
https://arxiv.org/abs/2509.20315

Multilingual Hope Speech Detection: A Comparative Study of Logistic Regression, mBERT, and XLM-RoBERTa with Active Learning
Hope speech language that fosters encouragement and optimism plays a vital role in promoting positive discourse online. However, its detection remains challenging, especially in multilingual and low-resource settings. This paper presents a multilingual framework for hope speech detection using an active learning approach and transformer-based models, including mBERT and XLM-RoBERTa. Experiments were conducted on datasets in English, Spanish, German, and Urdu, including benchmark test sets from …

Heel prettig, NRC kent nu 10 kado-links per maand die iedereen kan lezen. Wel maar zeven dagen geldig.

Grote smokkelzaken laten zien dat België de Nederlandse drugsmisdaad heeft geïmporteerd
Strafzaak: De geruchtmakende zaak tegen de Belg Flor B. – verdacht van het invoeren van 16.000 kilo cocaïne – is vertraagd door wraking van de rechter. Het is een van de strafzaken die toont hoezeer de Nederlandse drugscriminaliteit is verweven met de Belgische. „Netwerken uit beide landen werken al vele decennia samen.”

Replaced article(s) found for eess.SY. https://arxiv.org/list/eess.SY/new
[1/1]:
- Real-time Hybrid System Identification with Online Deterministic Annealing
Christos Mavridis, Karl Henrik Johansson

What if we could hot swap our Biometrics?
Jon Crowcroft, Anil Madhavapeddy, Chris Hicks, Richard Mortier, Vasilios Mavroudis
https://arxiv.org/abs/2509.17962 https://

What if we could hot swap our Biometrics?
What if you could really revoke your actual biometric identity, and install a new one, by live rewriting your biological self? We propose some novel mechanisms for hot swapping identity based in novel biotechnology. We discuss the potential positive use cases, and negative consequences if such technology was to become available and affordable. Biometrics are selected on the basis that they are supposed to be unfakeable, or at least not at reasonable cost. If they become easier to fake, it may b…

Tom convida Š investigação
#profecias

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
Marc Marone, Orion Weller, William Fleshman, Eugene Yang, Dawn Lawrie, Benjamin Van Durme
https://arxiv.org/abs/2509.06888

mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
Encoder-only languages models are frequently used for a variety of standard machine learning tasks, including classification and retrieval. However, there has been a lack of recent research for encoder models, especially with respect to multilingual models. We introduce mmBERT, an encoder-only language model pretrained on 3T tokens of multilingual text in over 1800 languages. To build mmBERT we introduce several novel elements, including an inverse mask ratio schedule and an inverse temperature…

Can maiBERT Speak for Maithili?
Sumit Yadav, Raju Kumar Yadav, Utsav Maskey, Gautam Siddharth Kashyap Md Azizul Hoque, Ganesh Gautam
https://arxiv.org/abs/2509.15048 https://

Can maiBERT Speak for Maithili?
Natural Language Understanding (NLU) for low-resource languages remains a major challenge in NLP due to the scarcity of high-quality data and language-specific models. Maithili, despite being spoken by millions, lacks adequate computational resources, limiting its inclusion in digital and AI-driven applications. To address this gap, we introducemaiBERT, a BERT-based language model pre-trained specifically for Maithili using the Masked Language Modeling (MLM) technique. Our model is trained on a…