Tootfinder

Alibaba Cloud details a GPU pooling system that it claims reduced the number of Nvidia H20 required by 82% when serving dozens of LLMs of up to 72B parameters (Vincent Chow/South China Morning Post)
https://www.scmp.com/business/article/3329

Alibaba Cloud claims to slash Nvidia GPU use by 82% with new pooling system
The new Aegaeon system can serve dozens of large language models using a fraction of the GPUs previously required, potentially reshaping AI workloads.

Pooling Probabilistic Forecasts for Cooperative Wind Power Offering
Honglin Wen, Pierre Pinson
https://arxiv.org/abs/2510.12382 https://arxiv.org/pdf/2510.…

Pooling Probabilistic Forecasts for Cooperative Wind Power Offering
Wind power producers can benefit from forming coalitions to participate cooperatively in electricity markets. To support such collaboration, various profit allocation rules rooted in cooperative game theory have been proposed. However, existing approaches overlook the lack of coherence among producers regarding forecast information, which may lead to ambiguity in offering and allocations. In this paper, we introduce a ``reconcile-then-optimize'' framework for cooperative market offerings. This …

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 …

First gudgin of the season. We'll have kilos of them this year but the first are always a treat. They're mouth puckeringly sour but so deep in flavour (and extremely good forvyou). I'll make jam and sauce and dried powder later but these first 4 go in the fridge (seeds taken out) with a sprinkle of sugar overnight and onto my yoghurt tomorrow. #fromthegarden

Climate action is finally moving from promises to practice. The Global Implementation Accelerator is bridging the gap between national climate plans and real-world results.
Here's what's working: Private capital restoring Brazilian forests. Unilever switching to renewables. H&M and IKEA modernizing Vietnam's grid. Companies in Taiwan pooling demand for clean energy.
The breakthrough? Aligning business needs with national climate goals creates wins on both sides.

From Plans to Progress: A Blueprint for Delivering 1.5°C Through the ‘Global Mutirão’
The Global Mutirão sent a clear message: delivering 1.5°C is only possible through shared effort.

Replaced article(s) found for q-fin.MF. https://arxiv.org/list/q-fin.MF/new
[1/1]:
- A General CoVaR Based on Entropy Pooling
Yuhong Xu, Xinyao Zhao
https://…

SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
Jiaye Tan, Haonan Luo, Linfeng Song, Shuaiqi Chen, Yishan Lyu, Zian Zhong, Roujia Wang, Daniel Jiang, Haoran Zhang, Jiaming Bai, Haoran Cheng, Q. Vera Liao, Hao-Wen Dong
https://arxiv.org/abs/2510.00395…

SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We pr…