Tootfinder

A silent scenery in four acts...
(Selenium-toned[1] 4x6 salt print (still in final wash) plus previous work-in-progress stages... see alt text for details)
The picture/motif itself is one of my personal favorites and was taken 4 years ago in the Alpstein massif, when clouds were spontaneously forming around us, creating a wonderful light/scene/drama and a dear memory... now also as print which likely will/can outlast myself
[1] The tones will become more neutral once dry...…

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu, Namyong Park, Christopher Jung, Rong Jin, Yang Wang, Zhigang Wang, Somayeh Sojoudi, Xue Feng
https://arxiv.org/abs/2510.09435

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where the output is generated by removing redundant and preserving non-redundant information from the query input by referencing another domain data whic…

#Drumpf Dream Scheme Team Ramping Up Pressure Points Day & Night On #GOP Members To Thwart A Vote To Release Contents Of Messy #MarALago Moments And Other Damning Deets Buried In

Trump Summons Lauren Boebert as He Pushes GOP to Block Epstein Vote
Representative Lauren Boebert, one of the Republicans pressing for more Epstein disclosures, was summoned for a meeting in the White House Situation Room.

Behind the scenes, some of the most powerful people around Trump have been trying to persuade him to attack Venezuela
— and remove its president, Nicolšs Maduro
— in what would be an extraordinary escalation of months-long military build-up in the Caribbean.
Those in favour of the strikes say they could bring democracy and prosperity to Venezuela
and provide a way for the eight million people who have fled the country in the past ten years to return.
These includ…

Will Trump invade Venezuela — and what comes next?
Pressure is ramping up on Maduro’s regime, amid reports Trump has spoken to the leader by phone. Inside the White House, advisers are pushing for the US to do more

When Names Disappear: Revealing What LLMs Actually Understand About Code
Cuong Chi Le, Minh V. T. Pham, Cuong Duc Van, Hoang N. Phan, Huy N. Phan, Tien N. Nguyen
https://arxiv.org/abs/2510.03178

When Names Disappear: Revealing What LLMs Actually Understand About Code
Large Language Models (LLMs) achieve strong results on code tasks, but how they derive program meaning remains unclear. We argue that code communicates through two channels: structural semantics, which define formal behavior, and human-interpretable naming, which conveys intent. Removing the naming channel severely degrades intent-level tasks such as summarization, where models regress to line-by-line descriptions. Surprisingly, we also observe consistent reductions on execution tasks that shou…

On yesterday's Teaching, Learning, and Everything Else podcast, I talked about AI's impact on the environment and classrooms—and argued that it isn’t reinventing education so much as exposing bad habits we should’ve let go years ago https://www.link…

"Will EU give ground on 2035 combustion-engine ban?"
#EU #EuropeanUnion #Cars #Vehicles

Will EU give ground on 2035 combustion-engine ban?
Europe's embattled auto industry and its backers are ramping up pressure on the EU to relax its planned 2035 ban on new petrol and diesel car sales—hoping for a decision by year end.

Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead
Thanh Linh Nguyen, Marcela Tuler de Oliveira, An Braeken, Aaron Yi Ding, Quoc-Viet Pham
https://arxiv.org/abs/2510.00833

Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Ahead
Federated unlearning (FUL) enables removing the data influence from the model trained across distributed clients, upholding the right to be forgotten as mandated by privacy regulations. FUL facilitates a value exchange where clients gain privacy-preserving control over their data contributions, while service providers leverage decentralized computing and data freshness. However, this entire proposition is undermined because clients have no reliable way to verify that their data influence has be…

CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems
Fnu Shivam, Nima Najafzadeh, Yenumula Reddy, Prashnna Gyawali
https://arxiv.org/abs/2509.19562

CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems
In the current digital era, facial recognition systems offer significant utility and have been widely integrated into modern technological infrastructures; however, their widespread use has also raised serious privacy concerns, prompting regulations that mandate data removal upon request. Machine unlearning has emerged as a powerful solution to address this issue by selectively removing the influence of specific user data from trained models while preserving overall model performance. However, …