Tootfinder

We see what we have learned to see https://kaptur.co/we-see-what-we-have-learned-to-see/ via @…

We See What We Have Learned to See - Kaptur
See, the danger is not that AI images will fool us. The danger is that we will stop caring whether anything happened at all.

Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Yingze Li, Xianglong Liu, Dong Wang, Zixuan Wang, Hongzhi Wang, Kaixing Zhang, Yiming Guan
https://arxiv.org/abs/2507.07438

Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment. This work is the first to theoretical investigate how minimal data-level drifts can maximally degrade the accuracy of learned estimators. We propose data-centric algorithmic complexity attacks against learned estimators in a black-box setting, proving that finding the optimal attack strategy is NP-Hard. To address th…

Tightly-Coupled LiDAR-IMU-Leg Odometry with Online Learned Leg Kinematics Incorporating Foot Tactile Information
Taku Okawara, Kenji Koide, Aoki Takanose, Shuji Oishi, Masashi Yokozuka, Kentaro Uno, Kazuya Yoshida
https://arxiv.org/abs/2506.09548

Tightly-Coupled LiDAR-IMU-Leg Odometry with Online Learned Leg Kinematics Incorporating Foot Tactile Information
In this letter, we present tightly coupled LiDAR-IMU-leg odometry, which is robust to challenging conditions such as featureless environments and deformable terrains. We developed an online learning-based leg kinematics model named the neural leg kinematics model, which incorporates tactile information (foot reaction force) to implicitly express the nonlinear dynamics between robot feet and the ground. Online training of this model enhances its adaptability to weight load changes of a robot (e.…

"As anyone who travels abroad can testify, American racial categories are deeply strange to outsiders and straight-up nonsensical for someone like Mamdani."
https://prospect.org/politics/2025-07-09-what-we-learned-from-new-york-times…

Virtru, which offers data security services to clients like the US DOD and Salesforce, raised a $50M Series D led by Iconiq Capital at a $500M valuation (Allie Garfinkle/Fortune)
https://fortune.com/2025/07/11/exclusi

Exclusive: Virtru, data security company, raises $50 million Series D as valuation hits $500 million
Virtru has recently raised a $50 million Series D, led by Iconiq Capital, Fortune has exclusively learned.

Evaluating Learned Indexes in LSM-tree Systems: Benchmarks,Insights and Design Choices
Junfeng Liu, Jiarui Ye, Mengshi Chen, Meng Li, Siqiang Luo
https://arxiv.org/abs/2506.08671 …

Evaluating Learned Indexes in LSM-tree Systems: Benchmarks,Insights and Design Choices
LSM-tree-based data stores are widely used in industry due to their exceptional performance. However, as data volumes grow, efficiently querying large-scale databases becomes increasingly challenging. To address this, recent studies attempted to integrate learned indexes into LSM-trees to enhance lookup performance, which has demonstrated promising improvements. Despite this, only a limited range of learned index types has been considered, and the strengths and weaknesses of different learned i…

I should probably write some Python to do a map thing with OpenStreetMap now that I've learned how incredibly easy it is.

Today I Learned (finally!) why I sometimes saw apparently arbitrary changes in @ivory’s accent colors… and the reason was this setting was on! I turned it off to never be surprised in the future.
Ps. Pinging @… because I think I get the value of setting, but consider disabling it after a period of time (1 hour?). That way you get to test the different themes…

"Amsterdam University Press (AUP) had been acquired by the for-profit corporate publishing behemoth Taylor & Francis" – Martin Paul Eve: "What is a University Press?" https://doi.org/10.59348/paybh-98d21

Trump asks Liberian president where he learned English, his country's official language (Reuters)
https://www.reuters.com/world/africa/trump-asks-liberian-president-where-he-learned-english-his-countrys-official-2025-07-09/
http://www.memeorandum.com/250709/p109#a250709p109

Based on this thread, featuring one of #TarantadongKalbo's nostalgia comic strips, I learned that this typical 1990s PC setup is apparently not unique to the #Philippines 🇵🇭.
#comics

I've learned to use two new tools in the last weeks: https://bevy.org (a well-known game programming framework) and https://hax.cryspen.com

Bevy Engine
Bevy is a refreshingly simple data-driven game engine built in Rust. It is free and open-source forever!

Is there a name for the trend in Millennials and Gen Z to mispronounce things because they don't talk to human beings often enough?
Like the Corridor Crew on YouTube, alleged experts in computer graphics, not knowing how to pronounce "Gaussian".
Or the number of young makers who pronounce the "L" in soldering (and are not British).
My strong suspicion is that they learned these words without talking to human beings, and then mispronounced them to eac…

I learned everything I know about #Strands from my grandpa in a rowboat on Cisco Lake in northern Wisconsin.
#Strands466
“Gone fishing”
🟡🔵🔵🔵
🔵🔵🔵🔵
🔵

Fisher Score Matching for Simulation-Based Forecasting and Inference
Ce Sui, Shivam Pandey, Benjamin D. Wandelt
https://arxiv.org/abs/2507.07833 https://…

Fisher Score Matching for Simulation-Based Forecasting and Inference
We propose a method for estimating the Fisher score--the gradient of the log-likelihood with respect to model parameters--using score matching. By introducing a latent parameter model, we show that the Fisher score can be learned by training a neural network to predict latent scores via a mean squared error loss. We validate our approach on a toy linear Gaussian model and a cosmological example using a differentiable simulator. In both cases, the learned scores closely match ground truth for pl…

Dear Media,
The story is that he’s a fascist, not that he’s ignorant.
Thank you. https://frontrange.co/@apnewsbot/114828593247109938

Learning The Minimum Action Distance
Lorenzo Steccanella, Joshua B. Evans, \"Ozg\"ur \c{S}im\c{s}ek, Anders Jonsson
https://arxiv.org/abs/2506.09276

Learning The Minimum Action Distance
This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally enables critical downstream tasks such as goal-conditi…

On the Costs and Benefits of Learned Indexing for Dynamic High-Dimensional Data: Extended Version
Ter\'ezia Slanin\'akov\'a, Jaroslav Olha, David Proch\'azka, Matej Antol, Vlastislav Dohnal
https://arxiv.org/abs/2507.05865

On the Costs and Benefits of Learned Indexing for Dynamic High-Dimensional Data: Extended Version
One of the main challenges within the growing research area of learned indexing is the lack of adaptability to dynamically expanding datasets. This paper explores the dynamization of a static learned index for complex data through operations such as node splitting and broadening, enabling efficient adaptation to new data. Furthermore, we evaluate the trade-offs between static and dynamic approaches by introducing an amortized cost model to assess query performance in tandem with the build costs…

Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy
Sita Sch\"onbauer, Johanna P. Carbone, Andreas Gr\"uneis
https://arxiv.org/abs/2507.06929

Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy
We investigate Machine-Learned Force Fields (MLFFs) trained on approximate Density Functional Theory (DFT) and Coupled Cluster (CC) level potential energy surfaces for the carbon diamond and lithium hydride solids. We assess the accuracy and precision of the MLFFs by calculating phonon dispersions and vibrational densities of states (VDOS) that are compared to experiment and reference ab initio results. To overcome limitations from long-range effects and the lack of atomic forces in the CC trai…

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Haoyu Wu, Diankun Wu, Tianyu He, Junliang Guo, Yang Ye, Yueqi Duan, Jiang Bian
https://arxiv.org/abs/2507.07982

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned representations. To bridge this gap between video diffusion models and the underlying 3D nature of the physical world, we propose Geometry Forcing, a simple yet effective method that encourages video diffusion models to internalize latent 3D representations. Our ke…

JOB-Complex: A Challenging Benchmark for Traditional & Learned Query Optimization
Johannes Wehrstein, Timo Eckmann, Roman Heinrich, Carsten Binnig
https://arxiv.org/abs/2507.07471

JOB-Complex: A Challenging Benchmark for Traditional & Learned Query Optimization
Query optimization is a fundamental task in database systems that is crucial to providing high performance. To evaluate learned and traditional optimizer's performance, several benchmarks, such as the widely used JOB benchmark, are used. However, in this paper, we argue that existing benchmarks are inherently limited, as they do not reflect many real-world properties of query optimization, thus overstating the performance of both traditional and learned optimizers. In fact, simple but realistic…

Hegseth halted Ukraine weapons without informing White House
https://euromaidanpress.com/2025/07/09/cnn-hegseth-ordered-halt-to-ukraine-arms-white-house-learned-from-the-press/

today i learned that "mah nŠ mah nŠ" was written for an italian sexploitation film & its original title "viva la sauna svedese" translates to "hooray for the swedish sauna" https://en.wikipedia.org/wiki/Mah_NŠ_Mah_NŠ

Mah Nà Mah Nà - Wikipedia

Improving elliptic curve rank classification using multi-value and learned Mestre-Nagao sums
Zvonimir Bujanovi\'c, Matija Kazalicki, Domagoj Vlah
https://arxiv.org/abs/2506.07967

Improving elliptic curve rank classification using multi-value and learned Mestre-Nagao sums
Determining the rank of an elliptic curve E/Q remains a central challenge in number theory. Heuristics such as Mestre--Nagao sums are widely used to estimate ranks, but there is considerable room for improving their predictive power. This paper introduces two novel methods for enhancing rank classification using Mestre--Nagao sums. First, we propose a ``multi-value'' approach that simultaneously uses two distinct sums, S_0 and S_5, evaluated over multiple ranges. This multi-sum perspective sign…

Learned Off-Grid Imager for Low-Altitude Economy with Cooperative ISAC Network
Yixuan Huang, Jie Yang, Shuqiang Xia, Chao-Kai Wen, Shi Jin
https://arxiv.org/abs/2506.07799

Learned Off-Grid Imager for Low-Altitude Economy with Cooperative ISAC Network
The low-altitude economy is emerging as a key driver of future economic growth, necessitating effective flight activity surveillance using existing mobile cellular network sensing capabilities. However, traditional monostatic and localizationbased sensing methods face challenges in fusing sensing results and matching channel parameters. To address these challenges, we model low-altitude surveillance as a compressed sensing (CS)-based imaging problem by leveraging the cooperation of multiple bas…

Patterns of Patterns III
Joseph Corneli, Charles J. Danoff, Raymond S. Puzio, Sridevi Ayloo, Serge Belich, Mary Tedeschi
https://arxiv.org/abs/2506.09696 h…

Patterns of Patterns III
Building on earlier installments, this paper re-examines the PLACARD pattern. We report on a series of workshops where PLACARD was used to scaffold collaborative reflection, speculative inquiry, and stimulate design pattern generation. These accounts are enriched by a comparison case: virtual workshops carried out with simple AI-based chatbots. We discuss limitations and lessons learned from both the human and multi-agent settings. We conclude by outlining a future development strategy at the i…

A Study on the Fine-Tuning Performance of Universal Machine-Learned Interatomic Potentials (U-MLIPs)
Xiaoqing Liu, Kehan Zeng, Yangshuai Wang, Teng Zhao
https://arxiv.org/abs/2506.07401

A Study on the Fine-Tuning Performance of Universal Machine-Learned Interatomic Potentials (U-MLIPs)
Universal machine-learned interatomic potentials (U-MLIPs) have demonstrated effectiveness across diverse atomistic systems but often require fine-tuning for task-specific accuracy. We investigate the fine-tuning of two MACE-based foundation models, MACE-MP-0 and its variant MACE-MP-0b, and identify key insights. Fine-tuning on task-specific datasets enhances accuracy and, in some cases, outperforms models trained from scratch. Additionally, fine-tuned models benefit from faster convergence due…

Replaced article(s) found for eess.IV. https://arxiv.org/list/eess.IV/new/
[1/1]:
Variable Rate Learned Wavelet Video Coding using Temporal Layer Adaptivity

frmbl-grmbl. i just learned that the #teensy 4.x has no #jtag/#swd port, and if want some, i need to do some desoldering and a bit of messing around on the pcb. such a nice piece of hw. yesterday i was complaining about the lack of usb-jtag in the lot i'm messing with, but i have not expected that this p…

Improving the Price of Anarchy via Predictions in Parallel-Link Networks
George Christodoulou, Vasilis Christoforidis, Alkmini Sgouritsa, Ioannis Vlachos
https://arxiv.org/abs/2507.07915

Improving the Price of Anarchy via Predictions in Parallel-Link Networks
We study non-atomic congestion games on parallel-link networks with affine cost functions. We investigate the power of machine-learned predictions in the design of coordination mechanisms aimed at minimizing the impact of selfishness. Our main results demonstrate that enhancing coordination mechanisms with a simple advice on the input rate can optimize the social cost whenever the advice is accurate (consistency), while only incurring minimal losses even when the predictions are arbitrarily ina…

Exotic collective dynamics in molten Carbon
Taras Bryk, Giancarlo Ruocco, Jean-Fran\c{c}ois Wax, No\"el Jakse
https://arxiv.org/abs/2507.07657 https:/…

Exotic collective dynamics in molten Carbon
Collective longitudinal and transverse propagating modes in molten Carbon at $T=5500$~K and pressure range $10$-$40$ GPa are reported from {\it ab initio} based as well as machine learned molecular dynamics. A striking exotic feature in collective dynamics is the two-peak shape of the current spectral functions of the single-component liquid, which makes evidence of a second branch of longitudinal propagating modes in the wave number range $k>1$Å$^{-1}$. It is shown that time correlation funct…

The return of web rings.
https://serverless.industries/2025/05/27/webring.en.html

I learned about WACZ files today. (Web Archive Collection Zipped)
I also learned that Claude can't process WACZ files without treating them as text, so my file is 3247% over the text entry limit. 🙄
I could use the API but by the time I configure that, I could just manually extract the text.

What we learned at Eagles OTAs: Beware of Jalen Hurts' deep ball; Vic Fangio spills the tea about the defense

https://www.cbssports.com/nfl…

LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting
Yilin Zhuang, Karthik Duraisamy
https://arxiv.org/abs/2506.09193 https://…

LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting
Accurate probabilistic weather forecasting demands both high accuracy and efficient uncertainty quantification, challenges that overburden both ensemble numerical weather prediction (NWP) and recent machine-learning methods. We introduce LaDCast, the first global latent-diffusion framework for medium-range ensemble forecasting, which generates hourly ensemble forecasts entirely in a learned latent space. An autoencoder compresses high-dimensional ERA5 reanalysis fields into a compact representa…

Laurel, which uses AI to map how workers spend time by integrating with tools like Slack and Outlook, raised a $100M Series C led by IVP at a $510M valuation (Allie Garfinkle/Fortune)
https://fortune.com/2025/06/10/exclusive-laurel-r…

Exclusive: Laurel raises $100 Series C to map where the time goes
Laurel has raised a $100 million Series C led by IVP, Fortune has exclusively learned. The deal values the startup at $510 million.

Discrete Diffusion Models for Language Generation
Ashen Weligalle
https://arxiv.org/abs/2507.07050 https://arxiv.org/pdf/2507.07050…

Discrete Diffusion Models for Language Generation
Diffusion models have emerged as a powerful class of generative models, achieving state-of-the-art results in continuous data domains such as image and video generation. Their core mechanism involves a forward diffusion process that gradually transforms structured data into a Gaussian-like distribution, followed by a learned reverse process to reconstruct the data. While successful in continuous modalities, applying this framework to discrete data-particularly natural language-remains challengi…

Just learned about NYC Local Law 144 which requires bias audits for hiring decisions
https://www.nyc.gov/site/dca/about/automated-employment-decision-tools.page
(From younger, more principled brother; happy birthday dkg!)
I am really interes…

"Wreckers, money woes and mutirão: 10 things we learned about Cop30 from Bonn climate talks
Fiona Harvey - in Bonn"
#Brazil #COP30 #Climate

As I move my data away from Alphabet (Google), I also delete accounts I no longer use. Here's what I've learned:
Creating an account and sharing your data is very easy.
Deleting an account and your data is sometimes impossible and usually pretty hard.
#degoogle #degoogleAdventures

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new/
[1/2]:
Robust Perception-Based Navigation using PAC-NMPC with a Learned Value Function

Quantum Error Mitigation by Global Randomized Error Cancellation for Adiabatic Evolution in the Schwinger Model
Oleg Kaikov, Theo Saporiti, Vasily Sazonov, Mohamed Tamaazousti
https://arxiv.org/abs/2507.06601

Quantum Error Mitigation by Global Randomized Error Cancellation for Adiabatic Evolution in the Schwinger Model
We extend the global randomized error cancellation (GREC) method for quantum error mitigation (QEM) in an application to adiabatic evolution of states on a noisy quantum device. We apply the adiabatic GREC method to the evolution of eigenstates in the lattice Schwinger model on a simulated quantum device with custom noise. Our results suggest that the corresponding QEM learned in one parameter regime of the model successfully transfers to a different parameter regime. In particular, our finding…

Today I learned! Magento 1 Layout.XML and JSON to encode action parameter
https://winkelwagen.de/2025/06/05/magento-1-json-in-layout-xml/

Magento 1: JSON in layout xml
Today I learned, one can use JSON in Magento 1’s layout xml. Tell Magento which action parameter are json and that’s it. You can tell Magento that only one parameter is json, like this.…

"Sale of the Amsterdam University Press (AUP) film, media and communication list to Taylor & Francis – Resignation of series editors and editorial board members" https://mediastudies.hypotheses.org/6850

Had some fun exploring and understanding design of deepfakes over the weekend, by making a satire musical video, using a wide range of tools, and producing in the context of current politics. I learned a lot through exploring. Hope you find the result intersting.
https://youtu.be/dYv_AZdHvGI

9 years ago, Microsoft launched an AI chatbot on Twitter. It swiftly turned into a racist a******. Apparently we learned nothing since then.

Cockatoos start sipping from Sydney’s drinking fountains after mastering series of complex moves;
Experts think the clever birds learned the technique by watching people and then trying it themselves
https://www.theguardian.com/environment/20

Nice! I just learned that my forthcoming article (with Marijana Hamersak) will be #OpenAccess due to some agreement of @… with SAGE.
Coming soon in Memory Studies
#ElShatt

Individual Treatment Effect: Prediction Intervals and Sharp Bounds
Zhehao Zhang, Thomas S. Richardson
https://arxiv.org/abs/2506.07469 https://

Individual Treatment Effect: Prediction Intervals and Sharp Bounds
Individual treatment effect (ITE) is often regarded as the ideal target of inference in causal analyses and has been the focus of several recent studies. In this paper, we describe the intrinsic limits regarding what can be learned concerning ITEs given data from large randomized experiments. We consider when a valid prediction interval for the ITE is informative and when it can be bounded away from zero. The joint distribution over potential outcomes is only partially identified from a randomi…

Microsoft has a new blog post on securing your organization against the Golden SAML attack. I wasn't familiar with this attack and learned that it only applies to organizations who use a delegated IdP like Active Directory Federation Services (ADFS). If you use ADFS, this should be on your reading list. #cybersecurity

Understanding and Mitigating Golden SAML Attacks | Microsoft Community Hub
Learn how Golden SAML attacks work and discover strategies to protect your identity infrastructure.

Still More Morning Jams
The progression on this one is stolen from "Sultans of Swing." I learned the chords from a Mary Spender video. The organ is from Zebra 2. The guitar is my Strat through a ToneLib AC-30 Topboost sim.
http://guitarsophist.com/2025/06/05/s

MLOps with Microservices: A Case Study on the Maritime Domain
Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Rowanne Trapmann (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)

MLOps with Microservices: A Case Study on the Maritime Domain
This case study describes challenges and lessons learned on building Ocean Guard: a Machine Learning-Enabled System (MLES) for anomaly detection in the maritime domain. First, the paper presents the system's specification, and architecture. Ocean Guard was designed with a microservices' architecture to enable multiple teams to work on the project in parallel. Then, the paper discusses how the developers adapted contract-based design to MLOps for achieving that goal. As a MLES, Ocean Guard emplo…

Everything I know about sex I learned in health class.

This https://arxiv.org/abs/2505.19953 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Interpretable Augmented Physics-Based Model for Estimation and Tracking
State-space estimation and tracking rely on accurate dynamical models to perform well. However, obtaining an vaccurate dynamical model for complex scenarios or adapting to changes in the system poses challenges to the estimation process. Recently, augmented physics-based models (APBMs) appear as an appealing strategy to cope with these challenges where the composition of a small and adaptive neural network with known physics-based models (PBM) is learned on the fly following an augmented state-…

This https://arxiv.org/abs/2405.05969 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Learned harmonic mean estimation of the Bayesian evidence with normalizing flows
We present the learned harmonic mean estimator with normalizing flows - a robust, scalable and flexible estimator of the Bayesian evidence for model comparison. Since the estimator is agnostic to sampling strategy and simply requires posterior samples, it can be applied to compute the evidence using any Markov chain Monte Carlo (MCMC) sampling technique, including saved down MCMC chains, or any variational inference approach. The learned harmonic mean estimator was recently introduced, where ma…

@… My university (in London) had (has?) a Cheese Society.
Once a week, they meet to eat cheese.
Sometimes with ale.
It’s a good university. I learned a lot.

It's truth in advertising when the braided UHMWPE product page shows it unraveling! 🤣
I've learned that plasma lighters are great tools for cutting light gauge synthetic cord. They are basically small hot plasma knives that cut slowly. Works for UHMWPE, nylon, polyester, and more. Also PET cable sheath, which is otherwise highly motivated to spontaneously disassemble itself.

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Lipei Xie, Yingxin Li, Huiping Zhuang
https://arxiv.org/abs/2506.09623

Analytic Task Scheduler: Recursive Least Squares Based Method for Continual Learning in Embodied Foundation Models
Embodied foundation models are crucial for Artificial Intelligence (AI) interacting with the physical world by integrating multi-modal inputs, such as proprioception, vision and language, to understand human intentions and generate actions to control robots. While these models demonstrate strong generalization and few-shot learning capabilities, they face significant challenges in continually acquiring new skills without forgetting previously learned skills, a problem known as catastrophic forg…

Robust Multi-generation Learned Compression of Point Cloud Attribute
Xiangzuo Liu, Zhikai Liu, PengPeng Yu, Ruishan Huang, Fan Liang
https://arxiv.org/abs/2507.01320

Robust Multi-generation Learned Compression of Point Cloud Attribute
Existing learned point cloud attribute compression methods primarily focus on single-pass rate-distortion optimization, while overlooking the issue of cumulative distortion in multi-generation compression scenarios. This paper, for the first time, investigates the multi-generation issue in learned point cloud attribute compression. We identify two primary factors contributing to quality degradation in multi-generation compression: quantization-induced non-idempotency and transformation irrevers…

Sonnet 078 - LXXVIII
So oft have I invoked thee for my Muse,
And found such fair assistance in my verse
As every alien pen hath got my use
And under thee their poesy disperse.
Thine eyes, that taught the dumb on high to sing
And heavy ignorance aloft to fly,
Have added feathers to the learned's wing
And given grace a double majesty.
Yet be most proud of that which I compile,
Whose influence is thine, and born of thee:
In o…

Understanding support for AI regulation: A Bayesian network perspective
Andrea Cremaschi, Dae-Jin Lee, Manuele Leonelli
https://arxiv.org/abs/2507.05866 ht…

Understanding support for AI regulation: A Bayesian network perspective
As artificial intelligence (AI) becomes increasingly embedded in public and private life, understanding how citizens perceive its risks, benefits, and regulatory needs is essential. To inform ongoing regulatory efforts such as the European Union's proposed AI Act, this study models public attitudes using Bayesian networks learned from the nationally representative 2023 German survey Current Questions on AI. The survey includes variables on AI interest, exposure, perceived threats and opportunit…

Lessons Learned from FPF “Deploying AI Systems” Workshop
https://fpf.org/blog/lessons-learned-from-fpf-deploying-ai-systems-workshop/
@…

This https://arxiv.org/abs/2505.16809 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalities
Existing methods for multimodal MRI segmentation with missing modalities typically assume that all MRI modalities are available during training. However, in clinical practice, some modalities may be missing due to the sequential nature of MRI acquisition, leading to performance degradation. Furthermore, retraining models to accommodate newly available modalities can be inefficient and may cause overfitting, potentially compromising previously learned knowledge. To address these challenges, we p…

Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs
Hanno Gottschalk, Emil Partow, Tobias J. Riedlinger
https://arxiv.org/abs/2507.01533 h…

Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs
This paper provides a proof of the consistency of sparse grid quadrature for numerical integration of high dimensional distributions. In a first step, a transport map is learned that normalizes the distribution to a noise distribution on the unit cube. This step is built on the statistical learning theory of neural ordinary differential equations, which has been established recently. Secondly, the composition of the generative map with the quantity of interest is integrated numerically using th…

I had this idea for a Cairn lifepath generator where there are three stages of life and you roll 1d6 for your stats at each stage, and also get appropriate items.
It has not been playtested, it's barely been proofread, but I've been having a lot of fun generating guys
perchance.org/lt8m69fg35
#ttrpg #CairnRpg

Musk happens to be right:
The One Big Beautiful Bill Act
— its actual name!
— is indeed a disgusting abomination.
But this is one of those cases where it takes one to know one.
Few men have done as much damage out of sheer arrogance, ignorance and pettiness as Elon Musk.
He has thousands, maybe hundreds of thousands, of deaths on his hands.
And even his parting blast is destructive,
demonstrating that he has learned nothing from his abject f…

Elon Musk is a Disgusting Abomination
So is the One Big Beautiful Bill Act. But still

Do you have a 75% mech keyboard that you’d recommend?
Max budget €200. No special layout options (I’ve learned from the Kinesis that my fingers’ memory is too strong to break).

This https://arxiv.org/abs/2502.13574 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
Denoising diffusion probabilistic models (DDPMs) can be utilized to recover a clean signal from its degraded observation(s) by conditioning the model on the degraded signal. The degraded signals are themselves contaminated versions of the clean signals; due to this correlation, they may encompass certain useful information about the target clean data distribution. However, existing adoption of the standard Gaussian as the prior distribution in turn discards such information when shaping the pri…

"Men of my generation have had Spain in our hearts. It was there that they learned ... that one can be right and yet be beaten, that force can vanquish spirit and that there are times when courage is not rewarded."
- Albert Camus
#AlbertCamus #Anarchism

Rhythm Features for Speaker Identification
Nick Mehlman, Thomas Thebaud, Dani Byrd, Shri Narayanan
https://arxiv.org/abs/2506.06834 https://

Rhythm Features for Speaker Identification
While deep learning models have demonstrated robust performance in speaker recognition tasks, they primarily rely on low-level audio features learned empirically from spectrograms or raw waveforms. However, prior work has indicated that idiosyncratic speaking styles heavily influence the temporal structure of linguistic units in speech signals (rhythm). This makes rhythm a strong yet largely overlooked candidate for a speech identity feature. In this paper, we test this hypothesis by applying d…

Three things we learned about Bengals' Joe Burrow on 'Quarterback' https://www.espn.com/nfl/story/_/id/45694848/nfl-cincinnati-bengals-joe-burrow-quarterback-netlfix

This https://arxiv.org/abs/2504.21838 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Universal User Representations Leveraging Cross-domain User Intent at Snapchat
The development of powerful user representations is a key factor in the success of recommender systems (RecSys). Online platforms employ a range of RecSys techniques to personalize user experience across diverse in-app surfaces. User representations are often learned individually through user's historical interactions within each surface and user representations across different surfaces can be shared post-hoc as auxiliary features or additional retrieval sources. While effective, such schemes …

"Rebuilding the library community in a post-Twitter world" by Ned Potter: https://www.ned-potter.com/blog/rebuilding-the-library-community-in-a-post-twitter-world
(unfortunately, due to "audience reasons" he pr…

My attempt to bike 1,000 miles this year is going well! And I also learned how to make bar graphs in Python...
➡️ #bike

Miles Biked (so far)…
Sometimes I set goals...

Hands-on with seven coding agents tasked with building a website: Claude Code performed best, OpenAI's Codex lacked polish, and Replit failed to build the site (Timothy B. Lee/Understanding AI)
https://www.understandingai.org/p/what-i-learned-trying-seven-…

What I learned trying seven coding agents
There's still room for improvement, but don't underestimate this technology.

Two-point measurement correlations beyond the quantum regression theorem
Leonardo Santos, Otfried G\"uhne, Stefan Nimmrichter
https://arxiv.org/abs/2507.06088

Two-point measurement correlations beyond the quantum regression theorem
Temporal correlations are fundamental in quantum physics, yet their computation is often challenging. The regression theorem (or hypothesis) serves as a key tool in this context, offering a seemingly straightforward approach. However, it fails for systems strongly coupled to their surroundings, where memory effects become significant. Here, we extend the analysis of temporal correlations beyond the regression theorem, revealing what can be learned about open quantum systems when this hypothesis…

Combined Public Service Announcement and Today I Learned: if you have `CLICOLOR=1` on macOS, if you do an `ls` of a directory which is inside iCloud Drive, evicted files (i.e., those that cannot be immediately used, but need to be downloaded first from iCloud) show with a grey background… see below:
First, both files are in iCloud, but not locally available. They have a dotted cloud icons in the iCloud Status field of the Finder window, and a greyed background in the output of the `ls` …

"FEMA had not been told and, in fact, they learned the news from those news stories. They didn't get official word from the White House about that disaster declaration for more than four days, which meant the money that was supposed to go out the door to those hard-hit communities was delayed."
'Quite a statement': CNN host stunned by Trump 'trauma' inflicted on key agency - Raw Story
https://www.rawstory.com/fema-trump-administration-concerns-mount/

Word stress in self-supervised speech models: A cross-linguistic comparison
Martijn Bentum, Louis ten Bosch, Tomas O. Lentz
https://arxiv.org/abs/2507.04738

Word stress in self-supervised speech models: A cross-linguistic comparison
In this paper we study word stress representations learned by self-supervised speech models (S3M), specifically the Wav2vec 2.0 model. We investigate the S3M representations of word stress for five different languages: Three languages with variable or lexical stress (Dutch, English and German) and two languages with fixed or demarcative stress (Hungarian and Polish). We train diagnostic stress classifiers on S3M embeddings and show that they can distinguish between stressed and unstressed sylla…

This https://arxiv.org/abs/2501.09799 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Scan-Adaptive MRI Undersampling Using Neighbor-based Optimization (SUNO)
Accelerated MRI involves collecting partial k-space measurements to reduce acquisition time, patient discomfort, and motion artifacts, and typically uses regular undersampling patterns or hand-designed schemes. Recent works have studied population-adaptive sampling patterns that are learned from a group of patients (or scans) based on population-specific metrics. However, such a general sampling pattern can be sub-optimal for any specific scan since it may lack scan or slice adaptive details. T…

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
Tobias W\"urth, Niklas Freymuth, Gerhard Neumann, Luise K\"arger
https://arxiv.org/abs/2506.06045

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics
Graph-based learned simulators have emerged as a promising approach for simulating physical systems on unstructured meshes, offering speed and generalization across diverse geometries. However, they often struggle with capturing global phenomena, such as bending or long-range correlations, and suffer from error accumulation over long rollouts due to their reliance on local message passing and direct next-step prediction. We address these limitations by introducing the Rolling Diffusion-Batched …

In Donald Trump’s White House, the easiest way to avoid being surprised is to remember that anything can happen.
Air Force leaders learned that lesson earlier this year when they arrived for a 💥top-secret briefing 💥with Trump in the Oval Office,
which according to NBC News was scheduled for them to discuss plans for America’s sixth-generation fighter aircraft, dubbed the F-47 in a nod to Trump’s status as the 47th President of the United States.
As the generals were going o…

Military leaders aghast as Meta founder Zuckerberg crashes classified Oval Office meeting on fighter jets: report
Facebook mogul’s sudden appearance is increasingly typical of freewheeling West Wing during Donald Trump’s second term, which president has reportedly nicknamed ‘Grand Central Terminal’

Sonnet 078 - LXXVIII
So oft have I invoked thee for my Muse,
And found such fair assistance in my verse
As every alien pen hath got my use
And under thee their poesy disperse.
Thine eyes, that taught the dumb on high to sing
And heavy ignorance aloft to fly,
Have added feathers to the learned's wing
And given grace a double majesty.
Yet be most proud of that which I compile,
Whose influence is thine, and born of thee:
In o…

SPIRA: Building an Intelligent System for Respiratory Insufficiency Detection
Renato Cordeiro Ferreira (University of S\~ao Paulo), Dayanne Gomes (University of S\~ao Paulo), Vitor Tamae (University of S\~ao Paulo), Francisco Wernke (University of S\~ao Paulo), Alfredo Goldman (University of S\~ao Paulo)
https://arxiv.org/abs/25…

SPIRA: Building an Intelligent System for Respiratory Insufficiency Detection
Respiratory insufficiency is a medic symptom in which a person gets a reduced amount of oxygen in the blood. This paper reports the experience of building SPIRA: an intelligent system for detecting respiratory insufficiency from voice. It compiles challenges faced in two succeeding implementations of the same architecture, summarizing lessons learned on data collection, training, and inference for future projects in similar systems.

Scope Meets Screen: Lessons Learned in Designing Composite Visualizations for Marksmanship Training Across Skill Levels
Emin Zerman, Jonas Carlsson, M{\aa}rten Sj\"ostr\"om
https://arxiv.org/abs/2507.00333

Scope Meets Screen: Lessons Learned in Designing Composite Visualizations for Marksmanship Training Across Skill Levels
Marksmanship practices are required in various professions, including police, military personnel, hunters, as well as sports shooters, such as Olympic shooting, biathlon, and modern pentathlon. The current form of training and coaching is mostly based on repetition, where the coach does not see through the eyes of the shooter, and analysis is limited to stance and accuracy post-session. In this study, we present a shooting visualization system and evaluate its perceived effectiveness for both n…

When I was a kid I learned about Harvey Milk from the Dead Kennedys.

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
Shilong Tao, Zhe Feng, Haonan Sun, Zhanxing Zhu, Yunhuai Liu
https://arxiv.org/abs/2506.06021

Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
Multi-solid systems are foundational to a wide range of real-world applications, yet modeling their complex interactions remains challenging. Existing deep learning methods predominantly rely on implicit modeling, where the factors influencing solid deformation are not explicitly represented but are instead indirectly learned. However, as the number of solids increases, these methods struggle to accurately capture intricate physical interactions. In this paper, we introduce a novel explicit mod…

PLACE: Prompt Learning for Attributed Community Search
Shuheng Fang, Kangfei Zhao, Rener Zhang, Yu Rong, Jeffrey Xu Yu
https://arxiv.org/abs/2507.05311 htt…

PLACE: Prompt Learning for Attributed Community Search
In this paper, we propose PLACE (Prompt Learning for Attributed Community Search), an innovative graph prompt learning framework for ACS. Enlightened by prompt-tuning in Natural Language Processing (NLP), where learnable prompt tokens are inserted to contextualize NLP queries, PLACE integrates structural and learnable prompt tokens into the graph as a query-dependent refinement mechanism, forming a prompt-augmented graph. Within this prompt-augmented graph structure, the learned prompt tokens s…

Flexible Mixed Precision Quantization for Learned Image Compression
Md Adnan Faisal Hossain, Zhihao Duan, Fengqing Zhu
https://arxiv.org/abs/2506.01221 htt…

Flexible Mixed Precision Quantization for Learned Image Compression
Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the computational complexity of LIC models. However, most existing works perform fixed-precision quantization which suffers from sub-optimal utilization of resources due to the varying sensitivity to quantization of different layers of a neural network. In this p…

A developer details how he shipped Context, a native macOS app that was almost 100% built using Claude Code (Indragie Karunaratne/My Portfolio)
https://www.indragie.com/blog/i-shipped-a-macos-app-built-entirely-by-claude-code

I Shipped a macOS App Built Entirely by Claude Code
How I built Context—a native macOS SwiftUI app for debugging MCP servers—almost entirely with Claude Code, and what I learned about building with AI coding agents.

Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games
Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren
https://arxiv.org/abs/2506.02849 …

Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games
The increasing proliferation of small UAVs in civilian and military airspace has raised critical safety and security concerns, especially when unauthorized or malicious drones enter restricted zones. In this work, we present a reinforcement learning (RL) framework for agile 1v1 quadrotor pursuit-evasion. We train neural network policies to command body rates and collective thrust, enabling high-speed pursuit and evasive maneuvers that fully exploit the quadrotor's nonlinear dynamics. To mitigat…

Antithetic Noise in Diffusion Models
Jing Jia, Sifan Liu, Bowen Song, Wei Yuan, Liyue Shen, Guanyang Wang
https://arxiv.org/abs/2506.06185 https://

Antithetic Noise in Diffusion Models
We initiate a systematic study of antithetic initial noise in diffusion models. Across unconditional models trained on diverse datasets, text-conditioned latent-diffusion models, and diffusion-posterior samplers, we find that pairing each initial noise with its negation consistently yields strongly negatively correlated samples. To explain this phenomenon, we combine experiments and theoretical analysis, leading to a symmetry conjecture that the learned score function is approximately affine an…

LIMAO: A Framework for Lifelong Modular Learned Query Optimization
Qihan Zhang, Shaolin Xie, Ibrahim Sabek
https://arxiv.org/abs/2507.00188 https://…

LIMAO: A Framework for Lifelong Modular Learned Query Optimization
Query optimizers are crucial for the performance of database systems. Recently, many learned query optimizers (LQOs) have demonstrated significant performance improvements over traditional optimizers. However, most of them operate under a limited assumption: a static query environment. This limitation prevents them from effectively handling complex, dynamic query environments in real-world scenarios. Extensive retraining can lead to the well-known catastrophic forgetting problem, which reduces …

Structured Pruning and Quantization for Learned Image Compression
Md Adnan Faisal Hossain, Fengqing Zhu
https://arxiv.org/abs/2506.01229 https://

Structured Pruning and Quantization for Learned Image Compression
The high computational costs associated with large deep learning models significantly hinder their practical deployment. Model pruning has been widely explored in deep learning literature to reduce their computational burden, but its application has been largely limited to computer vision tasks such as image classification and object detection. In this work, we propose a structured pruning method targeted for Learned Image Compression (LIC) models that aims to reduce the computational costs ass…

Mitigating Shortcut Learning with InterpoLated Learning
Michalis Korakakis, Andreas Vlachos, Adrian Weller
https://arxiv.org/abs/2507.05527 https://…

Mitigating Shortcut Learning with InterpoLated Learning
Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issu…

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Hao Li, Qi Lv, Rui Shao, Xiang Deng, Yinchuan Li, Jianye Hao, Liqiang Nie
https://arxiv.org/abs/2506.03863

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills. To address these limitations, we present \textbf{S}kill \textbf{T}raining with \textbf{A}ugmented \textbf{R}otation (\textbf{STAR}), a f…

A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads
Andr\'as Strausz, Niels Pardon, Ioana Giurgiu
https://arxiv.org/abs/2506.02802 http…

A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads
Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine capability, a complex and manual task that only becomes more difficult with the emergence of new engines and workloads. In this paper, we address this limitation by proposing a cross-engine optimizer that can automate engine selection for diverse SQL queries throu…

This https://arxiv.org/abs/2402.11871 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Real World to Logic and Back: Learning Generalizable Relational Concepts For Long Horizon Robot Planning
Humans efficiently generalize from limited demonstrations, but robots still struggle to transfer learned knowledge to complex, unseen tasks with longer horizons and increased complexity. We propose the first known method enabling robots to autonomously invent relational concepts directly from small sets of unannotated, unsegmented demonstrations. The learned symbolic concepts are grounded into logic-based world models, facilitating efficient zero-shot generalization to significantly more comple…