Tootfinder

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…

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 …

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…

Moody Urbanity - UP 🔝
情绪化城市 - 上面 🔝
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

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…

Got my water/utility bill for the spring/summer yesterday. (we get billed 3 times a year as part of our general city utilities bill including water, sewer and garbage/recycling fees).
Figured it would be a big water year this year so I've been wanting to see this. And of course, I have data going back to 2019ish.
Today's bill only goes to August 1st, so it doesn't include when we started to fill the #pondpool!
This was already a dry year in the spring and we were doing lots of watering in the front yard for the new ground cover in the modified driveway and the 3 new fruit trees.
Verdict:
2024: Apr 12 - Aug 7: 122, 200L
2025 Apr 14 - Aug 1 (7 less days!): 136,600L
It will be interesting to see if the August pond filling will add a big chunk onto our summer/fall consumption or if that is offset by both the brief August water restrictions, and the departure of both kids this fall to consume other people's water. ;=)
If you want an indication of how much water people use vs. yards: look at our August 2022 bill, which captures when we were on our cross-Canada roadtrip for 30 days in July/August of the 100 day period.
#water #consumption #gardening #utility #PortAlberni

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…

Moody Urbanity - UP ⬆️
情绪化城市 - 上面 ⬆️
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#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