Tootfinder

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
Ruyi Ding, Tianhong Xu, Xinyi Shen, Aidong Adam Ding, Yunsi Fei
https://arxiv.org/abs/2508.15036

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to scale explosively for performance, implementation efficiency remains a critical challenge. Mixture of Experts (MoE) architectures, selectively activating specialized subnetworks (experts), offer a unique balance between model accuracy and computational cost. However, the adaptive …

Filing: the Internet Archive and major music labels settle a copyright infringement lawsuit against IA over its project to preserve early music recordings (Ashley Belanger/Ars Technica)
https://arstechnica.com/tech-policy/202…

Internet Archive’s big battle with music publishers ends in settlement
The true cost of keeping the Internet Archive alive will likely remain unknown.

Privacy Preserving Inference of Personalized Content for Out of Matrix Users
Michael Sun, Tai Vu, Andrew Wang
https://arxiv.org/abs/2508.14905 https://arxi…

Privacy Preserving Inference of Personalized Content for Out of Matrix Users
Recommender systems for niche and dynamic communities face persistent challenges from data sparsity, cold start users and items, and privacy constraints. Traditional collaborative filtering and content-based approaches underperform in these settings, either requiring invasive user data or failing when preference histories are absent. We present DeepNaniNet, a deep neural recommendation framework that addresses these challenges through an inductive graph-based architecture combining user-item in…

Filing: the Internet Archive and major music labels settle a copyright lawsuit against Internet Archive over its project to preserve early music recordings (Ashley Belanger/Ars Technica)
https://arstechnica.com/tech-policy/20…

Internet Archive’s big battle with music publishers ends in settlement
The true cost of keeping the Internet Archive alive will likely remain unknown.

Phenome-Wide Multi-Omics Integration Uncovers Distinct Archetypes of Human Aging
Huifa Li, Feilong Tang, Haochen Xue, Yulong Li, Xinlin Zhuang, Bin Zhang, Eran Segal, Imran Razzak
https://arxiv.org/abs/2510.12384

Phenome-Wide Multi-Omics Integration Uncovers Distinct Archetypes of Human Aging
Aging is a highly complex and heterogeneous process that progresses at different rates across individuals, making biological age (BA) a more accurate indicator of physiological decline than chronological age. While previous studies have built aging clocks using single-omics data, they often fail to capture the full molecular complexity of human aging. In this work, we leveraged the Human Phenotype Project, a large-scale cohort of 12,000 adults aged 30--70 years, with extensive longitudinal prof…

Entanglement dynamics and performance of two-qubit gates for superconducting qubits under non-Markovian effects
Kiyoto Nakamura, Joachim Ankerhold
https://arxiv.org/abs/2510.05872

Entanglement dynamics and performance of two-qubit gates for superconducting qubits under non-Markovian effects
Within a numerically exact simulation technique, the dissipative dynamics of a two-qubit architecture is considered in which each qubit couples to its individual noise source (reservoir). The goal is to reveal the role of subtle qubit-reservoir correlations including non-Markovian processes as a prerequisite to guide further improvements of quantum computing devices. This paper addresses the following three topics. First, we examine the validity of the rotating wave approximation imposed previo…

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 …

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
Jessica Bader, Mateusz Pach, Maria A. Bravo, Serge Belongie, Zeynep Akata
https://arxiv.org/abs/2509.26644

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
Text-to-Image (T2I) generation models have advanced rapidly in recent years, but accurately capturing spatial relationships like "above" or "to the right of" poses a persistent challenge. Earlier methods improved spatial relationship following with external position control. However, as architectures evolved to enhance image quality, these techniques became incompatible with modern models. We propose Stitch, a training-free method for incorporating external position control into Multi-Modal Dif…

Filing: Trump's lawyers argue that Rupert Murdoch should be deposed within 15 days because of his advanced age, in the $10B libel suit against Murdoch and WSJ (Katie Robertson/New York Times)
https://www.nytimes.com/2025/07/28/business/media/trum…

Trump Says Rupert Murdoch Should Be Deposed Within 15 Days in Suit Over Epstein Article
The president’s legal team argued in a legal filing that discovery process for the media mogul should be expedited because of his age and health.