Tootfinder

Moody Urbanity - Somewhere 🔲
情绪化城市 - 某处 🔲
📷 Nikon FE
🎞️ Lucky SHD 400
#filmphotography #Photography #blackandwhite

Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
Daniel Gallo Fern\'andez
https://arxiv.org/abs/2510.02206 https://arxiv.org/pdf/…

Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
Sequence-to-sequence models have become central in Artificial Intelligence, particularly following the introduction of the transformer architecture. While initially developed for Natural Language Processing, these models have demonstrated utility across domains, including Computer Vision. Such models require mechanisms to exchange information along the time dimension, typically using recurrent or self-attention layers. However, self-attention scales quadratically with sequence length, limiting …

Moody Urbanity - Nowhere 🔲
情绪化城市 - 无处 🔲
📷 Nikon FE
🎞️ Lucky SHD 400
#filmphotography #Photography #blackandwhite

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Nanxi Li, Zhengyue Zhao, Chaowei Xiao
https://arxiv.org/abs/2508.18649 https://

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To this end, we introduce PRISM (Principled Reasoning for Integrated Safety in Multimodality), a system2-like framework that aligns VLMs by embedding a structured, safety-aware reasoning process. Our framework consists of two key components: PRISM-CoT, a dataset th…

Electrically Tunable Excitonic-Hyperbolicity in Chirality-Pure Carbon Nanotubes
Jason Lynch, Pavel Shapturenka, Mohammad Mojtaba Sadafi, Zoey Liu, Tobia Ruth, Kritika Jha, Zahra Fakhraai, Hossein Mosallaei, Nader Engheta, Jeffrey A. Fagan, Deep Jariwala
https://arxiv.org/abs/2509.24848

Electrically Tunable Excitonic-Hyperbolicity in Chirality-Pure Carbon Nanotubes
Metamaterials exhibiting hyperbolic dispersion enable unprecedented control over light-matter interactions, from sub-diffraction imaging to enhanced spontaneous emission. However, conventional plasmonic hyperbolic metamaterials suffer from limited tunability and lack intrinsic emission capabilities, constraining their utility for active photonic devices. Here, we demonstrate the first room-temperature, electrically tunable, excitonic hyperbolic metamaterial using aligned films of chirality-pure…

Can utilities replace power lines with solar and batteries in remote areas? The rise of microgrids offers a promising solution for communities looking to reduce costs and carbon footprint. #climatechange #climatesolutions

Can utilities replace power lines with solar and batteries in remote areas?
Expanding the grid to reach far-flung customers can be a costly fire hazard. So utilities like PG&E are testing out microgrids using solar, batteries, and…

The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
Zoe Kotti, Konstantina Dritsa, Diomidis Spinellis, Panos Louridas
https://arxiv.org/abs/2508.16131

The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
Code completion entails the task of providing missing tokens given a surrounding context. It can boost developer productivity while providing a powerful code discovery tool. Following the Large Language Model (LLM) wave, code completion has been approached with diverse LLMs fine-tuned on code (code LLMs). The performance of code LLMs can be assessed with downstream and intrinsic metrics. Downstream metrics are usually employed to evaluate the practical utility of a model, but can be unreliable …

Efficacy of Galaxy Catalogues for following up gravitational wave events
Tamojeet Roychowdhury, Harsh Choudhary, Varun Bhalerao, David O. Cook, Viraj Karambelkar, Mansi M. Kasliwal, Harsh Kumar, Surhud More, Gaurav Waratkar
https://arxiv.org/abs/2507.11635

Efficacy of Galaxy Catalogues for following up gravitational wave events
The detection of gravitational waves (GW) by the LIGO-Virgo-KAGRA (LVK) network has opened up a new era in astrophysics. The identification of the electromagnetic counterparts of GW sources is crucial for multi-messenger astronomy, one way of which is to use galaxy catalogues to guide optical follow-up observations. In this paper, we test the utility of galaxy-targeted approach with mass prioritised galaxy ranking for the ongoing LIGO O4 run. We have used the simulated results for the expected …

Water Demand Forecasting of District Metered Areas through Learned Consumer Representations
Adithya Ramachandran, Thorkil Flensmark B. Neergaard, Tom\'as Arias-Vergara, Andreas Maier, Siming Bayer
https://arxiv.org/abs/2509.07515

Water Demand Forecasting of District Metered Areas through Learned Consumer Representations
Advancements in smart metering technologies have significantly improved the ability to monitor and manage water utilities. In the context of increasing uncertainty due to climate change, securing water resources and supply has emerged as an urgent global issue with extensive socioeconomic ramifications. Hourly consumption data from end-users have yielded substantial insights for projecting demand across regions characterized by diverse consumption patterns. Nevertheless, the prediction of water…

MAUI: Reconstructing Private Client Data in Federated Transfer Learning
Ahaan Dabholkar, Atul Sharma, Z. Berkay Celik, Saurabh Bagchi
https://arxiv.org/abs/2509.11451 https://…

MAUI: Reconstructing Private Client Data in Federated Transfer Learning
Recent works in federated learning (FL) have shown the utility of leveraging transfer learning for balancing the benefits of FL and centralized learning. In this setting, federated training happens after a stable point has been reached through conventional training. Global model weights are first centrally pretrained by the server on a public dataset following which only the last few linear layers (the classification head) of the model are finetuned across clients. In this scenario, existing da…