Tootfinder

The new Raspberry Pi Connect feature works really, really well. After setting one up for work, it has me rethinking what I want to do with my various pieces of pi-ware at home. The latest Raspberry Pi Imager is a bit of a joke, though. Two different installs for two different machines where it completely ignored my custom settings during install, so I had to set up everything twice.

#ChatGPT Will Soon Have #Erotic Chats With Verified #Adults

I wish mastodon had a “throttle” feature. https://merveilles.town/@lrhodes/115379960146577252

HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
Shuwei Chen, Jiajun Cui, Zhengqi Xu, Fan Zhang, Jiangke Fan, Teng Zhang, Xingxing Wang
https://arxiv.org/abs/2510.11100

HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction
Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence side features provide less granular interest representation compared to extensive non-sequential features, thereby impairing sequence modeling…

Spotify will begin testing a feature that lets a user write a prompt for a playlist and receive a unique set of songs based on the user's earlier behavior (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/12/10/spotify-tests-more-person…

Spotify tests more personalized, AI-powered 'Prompted Playlists' | TechCrunch
The playlists can factor in world knowledge, go back to your listening history from day one, and be refreshed daily or weekly.

Spotify will begin testing a feature that lets a user write a prompt for a playlist and receive a unique set of songs based on the user's earlier behavior (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/12/10/spotify-tests-more-person…

Spotify tests more personalized, AI-powered 'Prompted Playlists' | TechCrunch
The playlists can factor in world knowledge, go back to your listening history from day one, and be refreshed daily or weekly.

This summer, Mikhail Loshchinin set out for Russia on a motorcycle with German plates, reaching the border in Latvia on July 1.
At the Ubylinka checkpoint on the Russian side, he presented his Russian passport.
According to his mother, Olga, he didn’t use his Belgian passport because of the urgency of the trip and to avoid needing a visa.
Russian border guards examined Loshchinin’s phone and likely discovered his many contacts in Ukraine.
After holding him for several…

Belgian-Russian dual citizen charged with treason after trying to visit father in St. Petersburg following a heart attack
A 48-year-old man with dual Russian and Belgian citizenship has been charged with treason in Russia following an attempt to visit his father, who recently suffered a heart attack. Mikhail Loshchinin’s family is scattered across Europe. He has lived in Germany for the past several years, working as a database administrator in Luxembourg. His mother is in Poland, his father is in St. Petersburg, and his sister is a Ukrainian citizen. Mikhail also has many friends in Ukraine, i…

Graph Conditioned Diffusion for Controllable Histopathology Image Generation
Sarah Cechnicka, Matthew Baugh, Weitong Zhang, Mischa Dombrowski, Zhe Li, Johannes C. Paetzold, Candice Roufosse, Bernhard Kainz
https://arxiv.org/abs/2510.07129

Graph Conditioned Diffusion for Controllable Histopathology Image Generation
Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature inherent structure such as consistent spatial arrangement, shape or texture, all of which are critical for diagnosis. However, existing DPMs operate in noisy latent spaces that lack semantic structure and strong priors, making it difficult to ensure meaningf…

Efficient & Correct Predictive Equivalence for Decision Trees
Joao Marques-Silva, Alexey Ignatiev
https://arxiv.org/abs/2509.17774 https://arxiv.org/pd…

Efficient & Correct Predictive Equivalence for Decision Trees
The Rashomon set of decision trees (DTs) finds importance uses. Recent work showed that DTs computing the same classification function, i.e. predictive equivalent DTs, can represent a significant fraction of the Rashomon set. Such redundancy is undesirable. For example, feature importance based on the Rashomon set becomes inaccurate due the existence of predictive equivalent DTs, i.e. DTs with the same prediction for every possible input. In recent work, McTavish et al. proposed solutions for s…

I had originally dismissed this feature, as I thought “these are just filters”, but this is an interesting insight and I can’t find a ton of information on this or thr tone/color/palette set of settings.
Would welcome any pointers

I finally got Link Previews in Firefox today. I disabled the ‘AI’ feature and then disabled link previews altogether as I played with it.
But the setting disappeared completely, so I couldn’t turn it on again.
If this happens to you:
about:config − set browser.ml.linkPreview.enabled to true

A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities
Reza Rahimi Baghbadorani, Peyman Mohajerin Esfahani, Sergio Grammatico
https://arxiv.org/abs/2510.03842 ht…

A Frank-Wolfe Algorithm for Strongly Monotone Variational Inequalities
We propose an accelerated algorithm with a Frank-Wolfe method as an oracle for solving strongly monotone variational inequality problems. While standard solution approaches, such as projected gradient descent (aka value iteration), involve projecting onto the desired set at each iteration, a distinctive feature of our proposed method is the use of a linear minimization oracle in each iteration. This difference potentially reduces the projection cost, a factor that can become significant for cer…

Excited for a The Mitchells vs. the Machines sequel!
#movies

Series A, Episode 08 - Duel
MUTOID: Time Distort Six.
TRAVIS: Minimum scan, their sensors mustn't register the beam.
MUTOID: Scan complete, identification confirmed.
https://blake.torpidity.net/m/108/12 B7B5

Gaussian Ensemble Topology (GET): A New Explicit and Inherently Smooth Framework for Manufacture-Ready Topology Optimization
Xinyu Ma, Chengxin Wang, Meng Wang, Xu Guo, Liu Yang, Huajian Gao
https://arxiv.org/abs/2510.05572

Gaussian Ensemble Topology (GET): A New Explicit and Inherently Smooth Framework for Manufacture-Ready Topology Optimization
We introduce the Gaussian Ensemble Topology (GET) method, a new explicit and manufacture-ready framework for topology optimization in which design geometries are represented as superpositions of anisotropic Gaussian functions. By combining explicit Gaussian descriptions with a level-set-like Heaviside projection, GET inherently generates smooth, curvature-continuous designs without requiring post-processing steps such as mesh or corner smoothing and feature extraction. The method is validated o…

Anyone know of a #tui building tool similar to #fzf that allows for preselection?
Use case: editing a list of selected files in a text file which are files in a directory on disk somewhere. I want the UI to preselect stuff already in the text file.
fzf has made the conscious decision not t…

I wondered why our Humax PVR had stopped being able to search the programme guide for weeks now but had been a bit busy and we don't find that many things that aren't on streaming anyway, so never found time to look into it until now.
It seems that they have decided to abandon the feature unless you buy a newer PVR.
This comes after they also cancelled the app (that allowed you to set recordings from your phone)

Mathematical Theory of Collinearity Effects on Machine Learning Variable Importance Measures
Kelvyn K. Bladen, D. Richard Cutler, Alan Wisler
https://arxiv.org/abs/2510.00557 ht…

Mathematical Theory of Collinearity Effects on Machine Learning Variable Importance Measures
In many machine learning problems, understanding variable importance is a central concern. Two common approaches are Permute-and-Predict (PaP), which randomly permutes a feature in a validation set, and Leave-One-Covariate-Out (LOCO), which retrains models after permuting a training feature. Both methods deem a variable important if predictions with the original data substantially outperform those with permutations. In linear regression, empirical studies have linked PaP to regression coefficie…

Feature Selection via Graph Topology Inference for Soundscape Emotion Recognition
Samuel Rey, Luca Martino, Roberto San Millan, Eduardo Morgado
https://arxiv.org/abs/2509.16760 …

Feature Selection via Graph Topology Inference for Soundscape Emotion Recognition
Research on soundscapes has shifted the focus of environmental acoustics from noise levels to the perception of sounds, incorporating contextual factors. Soundscape emotion recognition (SER) models perception using a set of features, with arousal and valence commonly regarded as sufficient descriptors of affect. In this work, we blend \emph{graph learning} techniques with a novel \emph{information criterion} to develop a feature selection framework for SER. Specifically, we estimate a sparse gr…

Intelligent Algorithm Selection for Recommender Systems: Meta-Learning via in-depth algorithm feature engineering
Jarne Mathi Decker
https://arxiv.org/abs/2509.20134 https://

Intelligent Algorithm Selection for Recommender Systems: Meta-Learning via in-depth algorithm feature engineering
The "No Free Lunch" theorem dictates that no single recommender algorithm is optimal for all users, creating a significant Algorithm Selection Problem. Standard meta-learning approaches aim to solve this by selecting an algorithm based on user features, but treat the fundamentally diverse algorithms themselves as equivalent, "black-box" choices. This thesis investigates the impact of overcoming this limitation by engineering a comprehensive feature set to explicitly characterize the algorithms …

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21341

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views via semantic-preserving feature partitioning (SPFP). A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views…

Toward a Theory of Gravitational Wave Turbulence
Holly Krynicki, Jiaxi Wu, Elias R. Most
https://arxiv.org/abs/2509.19769 https://arxiv.org/pdf/2509.19769

Toward a Theory of Gravitational Wave Turbulence
General relativity describes the dynamics of gravitational waves, which can feature nonlinear interactions, such as those underlying turbulent processes. Theoretical and numerical explorations have demonstrated the existence of gravitational wave turbulence, of which a full and general mathematical description is currently not known. Here, we take essential steps towards such a theory. Leveraging a formulation exactly recasting general relativity as a set of nonlinear electrodynamics equations,…

FERA: Foil Fencing Referee Assistant Using Pose-Based Multi-Label Move Recognition and Rule Reasoning
Ziwen Chen, Zhong Wang
https://arxiv.org/abs/2509.18527 https://

FERA: Foil Fencing Referee Assistant Using Pose-Based Multi-Label Move Recognition and Rule Reasoning
The sport of fencing, like many other sports, faces challenges in refereeing: subjective calls, human errors, bias, and limited availability in practice environments. We present FERA (Fencing Referee Assistant), a prototype AI referee for foil fencing which integrates pose-based multi-label action recognition and rule-based reasoning. FERA extracts 2D joint positions from video, normalizes them, computes a 101-dimensional kinematic feature set, and applies a Transformer for multi-label move and…

ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
Jihwan Lee, Sean Foley, Thanathai Lertpetchpun, Kevin Huang, Yoonjeong Lee, Tiantian Feng, Louis Goldstein, Dani Byrd, Shrikanth Narayanan
https://arxiv.org/abs/2509.21447

ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
We propose ARTI-6, a compact six-dimensional articulatory speech encoding framework derived from real-time MRI data that captures crucial vocal tract regions including the velum, tongue root, and larynx. ARTI-6 consists of three components: (1) a six-dimensional articulatory feature set representing key regions of the vocal tract; (2) an articulatory inversion model, which predicts articulatory features from speech acoustics leveraging speech foundation models, achieving a prediction correlatio…