Tootfinder

#Norway is ending #coal #mining

Can Donovan Ezeiruaku put a merciful end to Cowboys' strange curse? https://www.si.com/nfl/cowboys/news/can-donovan-ezeiruaku-put-merciful-end-dallas-cowboys-strange-curse

FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
Hongda Zhu, Yiwen Zhang, Bing Zhao, Jingzhe Ding, Siyao Liu, Tong Liu, Dandan Wang, Yanan Liu, Zhaojian Li
https://arxiv.org/abs/2506.13832

FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, and end-to-end validation is absent. These issues hinder the accurate assessment of model performance. To address these challenges, we present FrontendBench, a benchmark co-developed by humans and LLMs. FrontendBench categorizes tasks based on code functionality and incorporates …

Jonnu Smith rumors: Contract negotiations 'still fluid' as Dolphins tight end remains out of minicamp

https://www.cbssports.com/nfl/news/jonnu-…

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving
Ren Xin, Hongji Liu, Xiaodong Mei, Wenru Liu, Maosheng Ye, Zhili Chen, Jun Ma
https://arxiv.org/abs/2506.14589

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving
Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing specialized driving models. However, this integration leads to problems of asynchronous systems, which arise from the distinct characteristics inherent in GMs and SMs. To tackle this challenge, we propose NetRoller, an adapter that incorporates a set of novel mechan…

Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving
Boris Ivanovic, Cristiano Saltori, Yurong You, Yan Wang, Wenjie Luo, Marco Pavone
https://arxiv.org/abs/2506.12251

Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving
Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D ne…

https://apnews.com/article/iran-whatsapp-meta-israel-d9e6fe43280123c9963802e6f10ac8d1
Iran asks its people to delete WhatsApp from their devices

Iran asks its people to delete WhatsApp from their devices
Iranian state television on Tuesday afternoon urged the country’s public to remove the messaging app WhatsApp from their smart phones, alleging without offering any evidence the app gathered user information to send to Israel. WhatsApp is end-to-end encrypted, which means a service provider in the middle can't read messages. WhatsApp says it does not track users' precise location and does not track personal messages. Iran had banned WhatsApp in 2022 following mass protests. It lifted the ban …

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios
Aswin Shanmugam Subramanian, Amit Das, Naoyuki Kanda, Jinyu Li, Xiaofei Wang, Yifan Gong
https://arxiv.org/abs/2506.14204

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios
We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to real-time captioning and summarization requirements. We propose several key improvements: (1) Leveraging Continuous Speech Separation (CSS) single-channel front-end with end-to-end (E2E) systems for highly overlapping scenarios, challenging the conventional wisdom…

Bernie Sanders dives into a key House battleground Trump carried in 2024 with a new endorsement (Alexandra Marquez/NBC News)
https://www.nbcnews.com/politics/2026-election/bernie-sanders-dives-key-house-battleground-trump-carried-2024-new-end-rcna213874
http://www.memeorandum.com/250619/p14#a250619p14

This is what I always say: "It doesn't actually matter how cryptographically secure your end-to-end encryption is when 1 entity controls all ends and can instantly update them whenever they want." https://www.moparisthebest.com/against-silos-signal/

Integrated photonic deep neural network with end-to-end on-chip backpropagation training
Farshid Ashtiani, Mohamad Hossein Idjadi, Kwangwoong Kim
https://arxiv.org/abs/2506.14575 …

Integrated photonic deep neural network with end-to-end on-chip backpropagation training
Integrated photonic neural networks (PNNs) have demonstrated significant potential to complement the digital electronic counterparts [1-3]. Nevertheless, robust and repeatable performance of scalable integrated PNNs is directly tied to the quality of their training. Error backpropagation (BP), which relies on nonlinear activation gradient computation, is the mainstream algorithm to train digital neural networks due to its scalability, versatility, and implementation efficiency [4]. Consequently…

I would like to see an initiative that evaluates messaging services that promise encryption and document the findings. For example, a service may claim that emails are encrypted and secure. However, if the secret keys are managed on infrastructure controlled by the service without further protection, there are limitations, and I wouldn't call it end-to-end encryption. I think it would be useful to have a neutral web page where users could lookup the security levels of services (or apps).…

A requested feature for #Jellyfin for #Roku, displaying the time the playing video will end based on current time and seek position.
It will even keep updated if the video is paused and a minute passes 🤘

Période : toute la journée
Dates :
- le week-end du samedi 10 au dimanche 11 mai 15h45
- le week-end du samedi 17 au dimanche 18 mai 15h45
- le week-end du samedi 31 mai au dimanche 1er juin 15h45
La desserte des trains de la Ligne U est prolongée jusqu'Š la gare de Rambouillet (mission REFI - FERI)
Reprise des circulations le dimanche :
Premier train VERI au départ de la Défense 15h15
Premier train DEFI au départ de La Verrière 16h30
L…

Sources: Microsoft plans to announce thousands of job cuts, particularly in sales, early next month after the end of its fiscal year (Bloomberg)
https://www.bloomberg.com/news/articles/2025-06-18/microsoft-planning…

Enhancing Symbolic Machine Learning by Subsymbolic Representations
Stephen Roth, Lennart Baur, Derian Boer, Stefan Kramer
https://arxiv.org/abs/2506.14569 …

Enhancing Symbolic Machine Learning by Subsymbolic Representations
The goal of neuro-symbolic AI is to integrate symbolic and subsymbolic AI approaches, to overcome the limitations of either. Prominent systems include Logic Tensor Networks (LTN) or DeepProbLog, which offer neural predicates and end-to-end learning. The versatility of systems like LTNs and DeepProbLog, however, makes them less efficient in simpler settings, for instance, for discriminative machine learning, in particular in domains with many constants. Therefore, we follow a different approach:…

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
Ruiyan Zhu, Xi Cheng, Ke Liu, Brian Zhu, Daniel Jin, Neeraj Parihar, Zhoutian Xu, Oliver Gao
https://arxiv.org/abs/2506.12339

SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
We present SheetMind, a modular multi-agent framework powered by large language models (LLMs) for spreadsheet automation via natural language instructions. The system comprises three specialized agents: a Manager Agent that decomposes complex user instructions into subtasks; an Action Agent that translates these into structured commands using a Backus Naur Form (BNF) grammar; and a Reflection Agent that validates alignment between generated actions and the user's original intent. Integrated int…

Latent Action Diffusion for Cross-Embodiment Manipulation
Erik Bauer, Elvis Nava, Robert K. Katzschmann
https://arxiv.org/abs/2506.14608 https://

Latent Action Diffusion for Cross-Embodiment Manipulation
End-to-end learning approaches offer great potential for robotic manipulation, but their impact is constrained by data scarcity and heterogeneity across different embodiments. In particular, diverse action spaces across different end-effectors create barriers for cross-embodiment learning and skill transfer. We address this challenge through diffusion policies learned in a latent action space that unifies diverse end-effector actions. We first show that we can learn a semantically aligned laten…

Urban Living II 🌝
都市生活 II 🌝
📷 Nikon FE
🎞️Lucky SHD 400
buy me ☕️ ?/请我喝杯☕️？
#filmphotography

Yiding Cao Geld mit PayPal.Me senden
Folgen Sie dem Link PayPal.Me/dingsterdingster und geben Sie den Betrag ein. Es ist bequem und sicher. Sie haben noch kein PayPal-Konto? Kein Problem.

Officially, I came along towards the end of Gen X. So far as I can tell, one of the main differences between myself and my generational elders is that while I, like them, learned to type (on a typewriter!) with a double space after every period, I got over it when we all made the transition to word processors.

More Montessori:
❝Imagination does not become great until human beings, given the courage and the strength, use it to create.❞
And here’s a kicker:
❝Establishing lasting peace is the work of education; all politics can do is keep us out of war.❞
Put that last thought in the context of arts and education being deeply intertwined, and oligarchy seeking to dismantle both, and…well….
/end

the cave of dormant accounts. at the end of time, these posters will awake from their slumber and ravish the earth with their judgement

Juneteenth celebrates the end of most slavery in the United States. It is also known as Emancipation Day, Freedom Day, Jubilee Day, Juneteenth Independence Day, Black Independence Day, and by U.S. statute, Juneteenth National Independence Day.
https://www.cong…

I’m starting to wonder if my shoulder problems might in the end be related to my use of a trackpad, specifically hovering over it. So I’ll try using a mouse (with the other hand) instead for a while and see if this helps.

Gannett says the Detroit Free Press' joint operating agreement with The Detroit News, signed in 1989, will be dissolved at the start of 2026 (Neal Rubin/Detroit Free Press)
https://www.freep.com/story/news/local/mic

Detroit Free Press, Detroit News to end joint operating agreement at end of 2025
The Detroit Free Press and Detroit News’ joint operating agreement combined the two newspapers’ business operations since 1989.

Dissecting the Segmentation Model of End-to-End Diarization with Vector Clustering
Alexis Plaquet, Naohiro Tawara, Marc Delcroix, Shota Horiguchi, Atsushi Ando, Shoko Araki, Herv\'e Bredin
https://arxiv.org/abs/2506.11605

Dissecting the Segmentation Model of End-to-End Diarization with Vector Clustering
End-to-End Neural Diarization with Vector Clustering is a powerful and practical approach to perform Speaker Diarization. Multiple enhancements have been proposed for the segmentation model of these pipelines, but their synergy had not been thoroughly evaluated. In this work, we provide an in-depth analysis on the impact of major architecture choices on the performance of the pipeline. We investigate different encoders (SincNet, pretrained and finetuned WavLM), different decoders (LSTM, Mamba, …

Britain's parliament voted on Tuesday to
decriminalise abortion
in England and Wales
to stop a growing number of women from being investigated by police
for terminating pregnancies
under legislation dating back to the mid-19th century.
Abortions have been legal in England and Walesfor almost 60 years
but only up to 24 weeks and with the approval of two doctors.
Women can face criminal charges if they decide to end a pregnancy after 24 week…

Dead Amstrad ALT-286 becomes something new #Amstrad

Dead Amstrad Becomes Something New
When you run into old hardware you cannot restore, what do you do? Toss it? Sell it for parts? If you’re [TME Retro], you hide a high-end mini PC inside an Amstrad-shaped sleeper build. The d…

Signal-First Architectures: Rethinking Front-End Reactivity
Shrinivass Arunachalam Balasubramanian
https://arxiv.org/abs/2506.13815 https://

Signal-First Architectures: Rethinking Front-End Reactivity
Modern front-end frameworks face escalating reactivity management challenges, including performance degradation from complex observable chains and unpredictable re-renders. This paper introduces Signal-First Architecture--a novel paradigm where granular, dependency-tracked signals are the atomic unit of reactivity. Unlike traditional RxJS or NgRx patterns, Signal-First enforces reactive flows from explicit signal declarations, with derived values via computed() and side effects scoped to effect…

“CVE naming and assignment to software packages and versions are the foundation upon which the software vulnerability ecosystem is based. Without it, we can’t track newly discovered vulnerabilities. We can’t score their severity or predict their exploitation. And we certainly wouldn’t be able to make the best decisions regarding patching them.”

CVE program averts swift end after CISA executes 11-month contract extension
After DHS did not renew its funding contract for reasons unspecified, MITRE’s 25-year-old Common Vulnerabilities and Exposures (CVE) program was slated for an abrupt shutdown on April 16, which would have left security flaw tracking in limbo. CISA stepped in to provide a bridge.

SETI@home: Data Acquisition and Front-End Processing
Eric J. Korpela (Space Sciences Laboratory, University of California, Berkeley), David P. Anderson (Space Sciences Laboratory, University of California, Berkeley), Jeff Cobb (Space Sciences Laboratory, University of California, Berkeley), Matt Lebofsky (Space Sciences Laboratory, University of California, Berkeley), Wei Liu (Space Sciences Laboratory, University of California, Berkeley), Dan Werthimer (Space Sciences Laboratory, Univ…

SETI@home: Data Acquisition and Front-End Processing
SETI@home is a radio Search for Extraterrestrial Intelligence (SETI) project, looking for technosignatures in data recorded at multiple observatories from 1998 to 2020. Most radio SETI projects analyze data using dedicated processing hardware. SETI@home uses a different approach: time-domain data is distributed over the Internet to $\gt 10^{5}$ volunteered home computers, which analyze it. The large amount of computing power this affords ($\sim 10^{15}$ floating-point operations per second (FPO…

Ticking away, the moments that make up #Caturday; fritter and waste the hours in an offhand way

While closing the garage door this evening, a sight that still makes me smile.
#LandRover

Sonnet 050 - L
How heavy do I journey on the way,
When what I seek, my weary travel's end,
Doth teach that ease and that repose to say,
'Thus far the miles are measured from thy friend!'
The beast that bears me, tired with my woe,
Plods dully on, to bear that weight in me,
As if by some instinct the wretch did know
His rider lov'd not speed being made from thee.
The bloody spur cannot provoke him on,
That sometimes a…

N.Y. Lawmakers Target Prison Reform and A.I. in Frantic End of Session https://www.nytimes.com/2025/06/19/nyregion/new-york-legislature-ai-prison-reform.html

Reeves’s partial fixes don’t end austerity – and the drive to war goes on | Morning Star
https://morningstaronline.co.uk/article/reevess-partial-fixes-dont-end-austerity-and-drive-war-goes

Modica type estimates and curvature results for overdetermined $p$-Laplace problems
Yuanyuan Lian, Jing Wu
https://arxiv.org/abs/2506.14579 https://…

Modica type estimates and curvature results for overdetermined $p$-Laplace problems
In this paper we prove Modica type estimates for the following overdetermined $p$-Laplace problem \begin{equation*} \begin{cases} \mathrm{div} \left(|\nabla u|^{p-2}\nabla u\right)+f(u) =0& \mbox{in $Ω$, } u>0 &\mbox{in $Ω$, } u=0 &\mbox{on $\partialΩ$, } \partial_ν u=-κ&\mbox{on $\partialΩ$, } \end{cases} \end{equation*} where $1

How bad are the cuts to NASA? And is this the first hint of Planet 9? | Night Sky News May 2025
Some projects already built and scheduled for launch might end up in storage https://www.youtube.com/watch?v=si6paqM2_ug

As a fan of train travel I get this.

Opinion | Europe Built Trains. America Built Highways and Regret.
As Europe embraces the night train, the United States seems to be sleepwalking into a transport dead end.

This https://arxiv.org/abs/2502.06830 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Prediction
Accurate and reliable probabilistic prediction of intraday electricity prices is essential to manage market uncertainties and support robust trading strategies. However, current methods rely heavily on domain feature extraction and fail to capture the dynamics between buy and sell orders, limiting the ability to form rich representations of the orderbook. Furthermore, these methods often require training separate models for different quantiles and introduce additional procedures-such as post-ho…

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion
Ni Ou, Zhuo Chen, Xinru Zhang, Junzheng Wang
https://arxiv.org/abs/2506.14706 https:/…

Iterative Camera-LiDAR Extrinsic Optimization via Surrogate Diffusion
Cameras and LiDAR are essential sensors for autonomous vehicles. The fusion of camera and LiDAR data addresses the limitations of individual sensors but relies on precise extrinsic calibration. Recently, numerous end-to-end calibration methods have been proposed; however, most predict extrinsic parameters in a single step and lack iterative optimization capabilities. To address the increasing demand for higher accuracy, we propose a versatile iterative framework based on surrogate diffusion. Th…

Adam did not deserve this https://front-end.social/@argyleink/114320655479972337

This episode was incredibly good! It’s super interesting that HTML imports would actually be possible (and also that they might be called <rupert> – and include lazy loading)! Thank you guys! 👏
https://front-end.social/@shoptalkshow/114652349874960200

Hamiltonian Formalism for Comparing Quantum and Classical Intelligence
Elija Perrier
https://arxiv.org/abs/2506.14456 https://arxiv.o…

Hamiltonian Formalism for Comparing Quantum and Classical Intelligence
The prospect of AGI instantiated on quantum substrates motivates the development of mathematical frameworks that enable direct comparison of their operation in classical and quantum environments. To this end, we introduce a Hamiltonian formalism for describing classical and quantum AGI tasks as a means of contrasting their interaction with the environment. We propose a decomposition of AGI dynamics into Hamiltonian generators for core functions such as induction, reasoning, recursion, learning,…

Where Does Raiders' Michael Mayer Stand? https://www.si.com/nfl/raiders/las-vegas-michael-mayer-geno-smith-ashton-jeanty-pete-carroll

You know it's bad when the DeArrow title for a video straight up has "Video has lots of incorrect information" on the end.

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
Zhenhao Zhu, Yue Liu, Yingwei Ma, Hongcheng Gao, Nuo Chen, Yanpei Guo, Wenjie Qu, Huiying Xu, Xinzhong Zhu, Jiaheng Zhang
https://arxiv.org/abs/2506.13737

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning
Large Reasoning Models (LRMs) have demonstrated promising performance in complex tasks. However, the resource-consuming reasoning processes may be exploited by attackers to maliciously occupy the resources of the servers, leading to a crash, like the DDoS attack in cyber. To this end, we propose a novel attack method on LRMs termed ExtendAttack to maliciously occupy the resources of servers by stealthily extending the reasoning processes of LRMs. Concretely, we systematically obfuscate characte…

In both cases, the message is clear:
“Trump is really with •those other people•. Trump never cared about •you•. Trump never really wanted what •you• want. He just wants your money and your vote. He thinks you owe him your vote. Well you don’t.”
You know the playbook. If you’re having trouble coming up with it, just conjure up what the trolls did in your replies about Biden, turn that into a Mad Lib, and fill in the blanks for Trump supporters.
/end

"Nearly 100 countries call for ambitious global treaty to end plastic pollution at UN ocean summit"
#UN #UnitedNations #Plastic

Nations issue ‘Nice Wake-Up Call’ on plastic pollution treaty
Countries have shown a united front for ambition after talks on a landmark plastic pollution treaty collapsed last year.

Trump Administration Will End L.G.B.T.Q. Suicide Prevention Service (Maggie Astor/New York Times)
https://www.nytimes.com/2025/06/18/well/lgbtq-988-suicide-prevention.html
http://www.memeorandum.com/250618/p107#a250618p107

Hello all!
I wasn't able to process the photos of my recent trips, but I wanted to share this one from last year.
I went there on a hot day to "take a couple of photos". In the end I spent 3h just at this waterfall searching for the right composition & interpretation, the right motive etc.
I love the result, but I'm surprised how much time I spent there to get it.

Twisted second moment of primitive cubic L-functions
Ziwei Hong, Zhiyong Zheng
https://arxiv.org/abs/2506.14656 https://arxiv.org/pdf…

Twisted second moment of primitive cubic L-functions
We investigate the mean value of the twisted second moment of primitive cubic $L$-functions over $\mathbb{F}_q(T)$ in the non-Kummer setting. Specifically, we study the sum \begin{equation*} \sum_{\substack{χ primitive\ cubic\\ genus(χ)=g}}χ(h_1)\barχ(h_2)|L_q(\frac{1}{2}, χ)|^2, \end{equation*} where $L_q(s,χ)$ denotes the $L$-function associated with primitive cubic character $χ$. Employing a double Dirichlet series approach, we establish an error term of size

In the end it seems to me that one of the main distinctions between people who see LLMs as good and those who don't is whether they see the digital part of the world as "content" or "people".
If it's all just content, LLMs make sense. If it's where people live LLMs become a somewhat dumb idea.

SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition
Yuta Hirano, Sakriani Sakti
https://arxiv.org/abs/2506.12672

SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition
We propose Speaker-Conditioned Serialized Output Training (SC-SOT), an enhanced SOT-based training for E2E multi-talker ASR. We first probe how SOT handles overlapped speech, and we found the decoder performs implicit speaker separation. We hypothesize this implicit separation is often insufficient due to ambiguous acoustic cues in overlapping regions. To address this, SC-SOT explicitly conditions the decoder on speaker information, providing detailed information about "who spoke when". Specifi…

This https://arxiv.org/abs/2505.06780 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csOS_…

Work-in-Progress: Multi-Deadline DAG Scheduling Model for Autonomous Driving Systems
Autoware is an autonomous driving system implemented on Robot Operation System (ROS) 2, where an end-to-end timing guarantee is crucial to ensure safety. However, existing ROS 2 cause-effect chain models for analyzing end-to-end latency struggle to accurately represent the complexities of Autoware, particularly regarding sync callbacks, queue consumption patterns, and feedback loops. To address these problems, we propose a new scheduling model that decomposes the end-to-end timing constraints o…

K3 surfaces over small number fields and Kummer constructions in families
Stefan Schr\"oer
https://arxiv.org/abs/2506.14732 https://

K3 surfaces over small number fields and Kummer constructions in families
We construct K3 surfaces over number fields that have good reduction everywhere. These do not exists over the rational numbers, by results of Abrashkin and Fontaine. Our surfaces exist for three quadratic number fields, and an infinite family of $S_3$-number fields. To this end we develop a theory of Kummer constructions in families, based on Romagny's notion of the effective models, here applied to sign involutions. This includes quotients of non-normal surfaces by infinitesimal group schemes …

EasyDRAM: An FPGA-based Infrastructure for Fast and Accurate End-to-End Evaluation of Emerging DRAM Techniques
O\u{g}uzhan Canpolat, Ataberk Olgun, David Novo, O\u{g}uz Ergin, Onur Mutlu
https://arxiv.org/abs/2506.10441

EasyDRAM: An FPGA-based Infrastructure for Fast and Accurate End-to-End Evaluation of Emerging DRAM Techniques
DRAM is a critical component of modern computing systems. Recent works propose numerous techniques (that we call DRAM techniques) to enhance DRAM-based computing systems' throughput, reliability, and computing capabilities (e.g., in-DRAM bulk data copy). Evaluating the system-wide benefits of DRAM techniques is challenging as they often require modifications across multiple layers of the computing stack. Prior works propose FPGA-based platforms for rapid end-to-end evaluation of DRAM techniques…

I’ll be 60 this year, and thinking this might end up being my retirement plan too… https://social.lol/@nad/114698321072149153

Nad's curated garbage (@nad@social.lol)
Attached: 1 image

OneRec Technical Report
Guorui Zhou, Jiaxin Deng, Jinghao Zhang, Kuo Cai, Lejian Ren, Qiang Luo, Qianqian Wang, Qigen Hu, Rui Huang, Shiyao Wang, Weifeng Ding, Wuchao Li, Xinchen Luo, Xingmei Wang, Zexuan Cheng, Zixing Zhang, Bin Zhang, Boxuan Wang, Chaoyi Ma, Chengru Song, Chenhui Wang, Di Wang, Dongxue Meng, Fan Yang, Fangyu Zhang, Feng Jiang, Fuxing Zhang, Gang Wang, Guowang Zhang, Han Li, Hengrui Hu, Hezheng Lin, Hongtao Cheng, Hongyang Cao, Huanjie Wang, Jiaming Huang, Jiapeng Che…

OneRec Technical Report
Recommender systems have been widely used in various large-scale user-oriented platforms for many years. However, compared to the rapid developments in the AI community, recommendation systems have not achieved a breakthrough in recent years. For instance, they still rely on a multi-stage cascaded architecture rather than an end-to-end approach, leading to computational fragmentation and optimization inconsistencies, and hindering the effective application of key breakthrough technologies from …

Monophotons at Neutrino Experiments from Neutrino Polarizability
Julia Gehrlein, Ian M. Shoemaker, Anil Thapa
https://arxiv.org/abs/2506.14881 https://

Monophotons at Neutrino Experiments from Neutrino Polarizability
Nontrivial electromagnetic properties of neutrinos are an avenue to physics beyond the Standard Model. To this end, we investigate the power of monophoton signals at neutrino experiments to probe a higher-dimensional operator connecting neutrinos to SM photons dubbed, neutrino polarizability. A simplified scenario giving rise to this operator involves a new pseudo-scalar that couples to both neutrinos and photons, with clear implications for axion-like particle (ALP) and Majoron physics. By ana…

End-to-End Dynamic Metasurface Antenna Wireless System: Prototype, Opportunities, and Challenges
Fran\c{c}ois Yven, Jean Tapie, J\'er\^ome Sol, Philipp del Hougne
https://arxiv.org/abs/2506.09732

End-to-End Dynamic Metasurface Antenna Wireless System: Prototype, Opportunities, and Challenges
Dynamic metasurface antennas (DMAs) are a promising hybrid analog/digital beamforming technology to realize next-generation wireless systems with low cost, footprint, and power consumption. The research on DMA-empowered wireless systems is still at an early stage, mostly limited to theoretical studies under simplifying assumptions on the one hand and a few antenna-level experiments on the other hand. Substantial knowledge gaps arise from the lack of complete end-to-end DMA-empowered wireless sy…

Under Randy Clarke, WMATA has cut the end-to-end travel time on the Metro Red Line by 8 minutes. This is a 68 minute trip, so it's a gain in efficiency of over 10% on top of faster trips for riders.
This is a combination of automated train operation (with doors closing sooner), raising the speed limit back to the original design of 75 mph, and I imagine other fixes.

WMATA | Metro to launch Automatic Train Operation on the Blue, Orange, and Silver lines on June 15
Metro news and service information for the Washington, DC, Maryland, and Virginia region.

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
Luke Rowe, Rodrigue de Schaetzen, Roger Girgis, Christopher Pal, Liam Paull
https://arxiv.org/abs/2506.11234

Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
We present Poutine, a 3B-parameter vision-language model (VLM) tailored for end-to-end autonomous driving in long-tail driving scenarios. Poutine is trained in two stages. To obtain strong base driving capabilities, we train Poutine-Base in a self-supervised vision-language-trajectory (VLT) next-token prediction fashion on 83 hours of CoVLA nominal driving and 11 hours of Waymo long-tail driving. Accompanying language annotations are auto-generated with a 72B-parameter VLM. Poutine is obtained …

Cowboys trying to turn undrafted RB into a tight end https://www.sportingnews.com/us/nfl/dallas-cowboys/news/cowboys-trying-turn-undrafted-rb-tight-end/ece13a32f7dcbd6d66d17ea8

The US Senate's draft tax bill would raise the CHIPS Act's tax credit for semiconductor factories from 25% to 30% until the tax break expires at the end of 2026 (Alicia Diaz/Bloomberg)
https://www.bloomberg.com/news/articles/20

Unifying Streaming and Non-streaming Zipformer-based ASR
Bidisha Sharma, Karthik Pandia Durai, Shankar Venkatesan, Jeena J Prakash, Shashi Kumar, Malolan Chetlur, Andreas Stolcke
https://arxiv.org/abs/2506.14434

Unifying Streaming and Non-streaming Zipformer-based ASR
There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We present a unified framework that trains a single end-to-end ASR model for both streaming and non-streaming applications, leveraging future context information. We propose to use dynamic right-context through the chunked attention masking in the training of zipformer-based ASR models. We demonstrate that using right-context…

A Point Cloud Completion Approach for the Grasping of Partially Occluded Objects and Its Applications in Robotic Strawberry Harvesting
Ali Abouzeid, Malak Mansour, Chengsong Hu, Dezhen Song
https://arxiv.org/abs/2506.14066

A Point Cloud Completion Approach for the Grasping of Partially Occluded Objects and Its Applications in Robotic Strawberry Harvesting
In robotic fruit picking applications, managing object occlusion in unstructured settings poses a substantial challenge for designing grasping algorithms. Using strawberry harvesting as a case study, we present an end-to-end framework for effective object detection, segmentation, and grasp planning to tackle this issue caused by partially occluded objects. Our strategy begins with point cloud denoising and segmentation to accurately locate fruits. To compensate for incomplete scans due to occlu…

Known as “white” asbestos,
chrysotile asbestos is banned in more than 50 countries
for its link to lung cancer and mesothelioma,
a cancer that forms in the lining of internal organs.
White asbestos, however, has been imported for use in the United States for roofing materials, textiles and cement as well as gaskets, clutches, brake pads and other automotive parts.
It is also used in chlorine manufacturing.
Last year the Environmental Protection Agency, u…

E.P.A. Plans to Reconsider a Ban on Cancer-Causing Asbestos
The Trump administration’s move sets back a decades-long effort to end the use of the material, which is widely banned in other countries.

"I Cannot Write This Because It Violates Our Content Policy": Understanding Content Moderation Policies and User Experiences in Generative AI Products
Lan Gao, Oscar Chen, Rachel Lee, Nick Feamster, Chenhao Tan, Marshini Chetty
https://arxiv.org/abs/2506.14018

"I Cannot Write This Because It Violates Our Content Policy": Understanding Content Moderation Policies and User Experiences in Generative AI Products
While recent research has focused on developing safeguards for generative AI (GAI) model-level content safety, little is known about how content moderation to prevent malicious content performs for end-users in real-world GAI products. To bridge this gap, we investigated content moderation policies and their enforcement in GAI online tools -- consumer-facing web-based GAI applications. We first analyzed content moderation policies of 14 GAI online tools. While these policies are comprehensive i…

BeIN Sports extends its three-year Premier League live TV rights deal in MENA for ~£550M, up 10% over the last cycle; League's total overseas rights rose 27% (Matt Slater/New York Times)
https://www.nytimes.com/athletic/6432549/2025/06/17/p…

Premier League extends Middle East TV deal, overseas media rights value up 27%
The new three-year deal runs from next season through until the end of 2027-28 and is worth approximately £550m.

Chiefs' Travis Kelce says returning for 2025 season 'wasn't that hard of a decision' https://www.nfl.com/news/chiefs-travis-kelce-says-returning-for-2025-season-wasn-t-that-hard-of-a-decision

"A solar panel recycling scheme would help reduce waste, but please repair and reuse first"
#SolarPower #Energy #Renewables

A solar panel recycling scheme would help reduce waste, but please repair and reuse first
Older rooftop solar systems are being scrapped – often well before the end of their useful life. Establishing a product stewardship scheme is part of the solution.

Army Parade Begins in Light Drizzle, Light Crowd on West End of Route (Wall Street Journal)
https://www.wsj.com/livecoverage/trump-protests-military-parade/card/army-parade-begins-in-light-drizzle-light-crowd-on-west-end-of-route-0ZruEAhwAbXZjR2m8rrp
http://www.memeorandum.com/250615/p39#a250615p39

I think a key reason the AI grift is so devious it it's built on top of an actual product that does have some utility. The grift just promises far more than AI is actually capable of in the foreseeable future.
Previous grifts like crypto and NFTs were entirely vaporware, but when we see AI generated images and text in the wild, it takes a more nuanced understanding to navigate the hype.

Quadrotor Morpho-Transition: Learning vs Model-Based Control Strategies
Ioannis Mandralis, Richard M. Murray, Morteza Gharib
https://arxiv.org/abs/2506.14039

Quadrotor Morpho-Transition: Learning vs Model-Based Control Strategies
Quadrotor Morpho-Transition, or the act of transitioning from air to ground through mid-air transformation, involves complex aerodynamic interactions and a need to operate near actuator saturation, complicating controller design. In recent work, morpho-transition has been studied from a model-based control perspective, but these approaches remain limited due to unmodeled dynamics and the requirement for planning through contacts. Here, we train an end-to-end Reinforcement Learning (RL) controll…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/4]:
How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?

MatchPlant: An Open-Source Pipeline for UAV-Based Single-Plant Detection and Data Extraction
Worasit Sangjan, Piyush Pandey, Norman B. Best, Jacob D. Washburn
https://arxiv.org/abs/2506.12295

MatchPlant: An Open-Source Pipeline for UAV-Based Single-Plant Detection and Data Extraction
Accurate identification of individual plants from unmanned aerial vehicle (UAV) images is essential for advancing high-throughput phenotyping and supporting data-driven decision-making in plant breeding. This study presents MatchPlant, a modular, graphical user interface-supported, open-source Python pipeline for UAV-based single-plant detection and geospatial trait extraction. MatchPlant enables end-to-end workflows by integrating UAV image processing, user-guided annotation, Convolutional Neu…

Sources: OpenAI wants Microsoft to take a ~33% stake in exchange for giving up future profit rights, and seeks to revise its exclusive cloud deal with Microsoft (The Information)
https://www.theinformation.com/articles/opena…

OpenAI Seeks New Financial Concessions From Microsoft, a Top Shareholder
Negotiations between Microsoft and OpenAI over the startup’s plan to restructure its for-profit unit, which requires Microsoft’s approval, have entered their eighth month with no end in sight and new conflicts emerging. OpenAI wants Microsoft, the startup’s biggest outside shareholder, to have a ...

Can Luke Schoonmaker contend for Dallas Cowboys starting tight end job? https://www.si.com/nfl/cowboys/news/can-luke-schoonmaker-contend-dallas-cowboys-starting-tight-end-job

End-to-End Diarization utilizing Attractor Deep Clustering
David Palzer, Matthew Maciejewski, Eric Fosler-Lussier
https://arxiv.org/abs/2506.11090 https://…

End-to-End Diarization utilizing Attractor Deep Clustering
Speaker diarization remains challenging due to the need for structured speaker representations, efficient modeling, and robustness to varying conditions. We propose a performant, compact diarization framework that integrates conformer decoders, transformer-updated attractors, and a deep clustering style angle loss. Our approach refines speaker representations with an enhanced conformer structure, incorporating cross-attention to attractors and an additional convolution module. To enforce struct…

Agile and Student-Centred Teaching of Agile/Scrum Concepts
Maria Spichkova
https://arxiv.org/abs/2506.14369 https://arxiv.org/pdf/250…

Agile and Student-Centred Teaching of Agile/Scrum Concepts
In this paper, we discuss our experience in designing and teaching a course on Software Engineering Project Management, where the focus is on Agile/Scrum development and Requirement Engineering activities. The course has undergone fundamental changes since 2020 to make the teaching approach more student-centred and flexible. As many universities abandoned having face-to-face exams at the end of the semester, authentic assessments now play an even more important role than before. This makes asse…

Former Jets, Ravens LB Mosley retiring from NFL https://www.espn.com/nfl/story/_/id/45543544/ex-jets-ravens-lb-cj-mosley-retires-10-nfl-seasons

The move to Windows 11 isn’t just about security updates.
It increases dependence on Microsoft through aggressive cloud integration,
forcing users to adopt Microsoft accounts and services.
It also leads to higher costs due to subscription and licensing models,
and reduces control over how your computer works and how your data is managed.
Furthermore, new hardware requirements will render millions of perfectly good PCs obsolete.
This is a turning point.

The end of Windows 10 is approaching, so it's time to consider Linux and LibreOffice - The Document Foundation Blog
The Document Foundation and LibreOffice support the international campaign @endof10 https://endof10.org/ The countdown has begun. On 14 October 2025, Microsoft will end support for Windows 10. This will leave millions of users and organisations with a difficult choice: should they upgrade to Windows 11, or completely rethink their work environment? The good news? You don’t […]

I think a key reason the AI grift is so devious it it's built on top of an actual product that does have some utility. The grift just promises far more than AI is actually capable of in the foreseeable future.
Previous grifts like crypto and NFTs were entirely vaporware, but when we see AI generated images and text in the wild, it takes a more nuanced understanding to navigate the hype.

Apple says macOS 26 Tahoe will be the last release of macOS that supports Intel Macs, with future macOS versions only available to Apple Silicon Macs (Benjamin Mayo/9to5Mac)
https://9to5mac.com/2025/06/09/apple-will-end-support-for-intel-macs/

Apple will end support for Intel Macs next year, macOS 27 will require Apple Silicon - 9to5Mac
During the Platforms State of the Union at WWDC, Apple just announced that macOS 26 Tahoe will be the last...

Chiefs' Travis Kelce plummets 78 spots in Pete Prisco's annual top 100 NFL players list

https://www.cbssports.com/nfl/news/chiefs-

Lamar Jackson defends Mark Andrews, says Ravens have 'vengeance on our mind' after playoff loss https://www.nfl.com/news/lamar-jackson-defends-mark-andrews-says-ravens-have-vengeance-on-our-mind-after-playoff-…

Niners' George Kittle believes TEs should be making more money: 'I want guys to get paid' https://www.nfl.com/news/niners-george-kittle-believes-tes-should-be-making-more-money-i-want-guys-to-get-paid

Personalizable Long-Context Symbolic Music Infilling with MIDI-RWKV
Christian Zhou-Zheng, Philippe Pasquier
https://arxiv.org/abs/2506.13001 https://

Personalizable Long-Context Symbolic Music Infilling with MIDI-RWKV
Existing work in automatic music generation has primarily focused on end-to-end systems that produce complete compositions or continuations. However, because musical composition is typically an iterative process, such systems make it difficult to engage in the back-and-forth between human and machine that is essential to computer-assisted creativity. In this study, we address the task of personalizable, multi-track, long-context, and controllable symbolic music infilling to enhance the process …

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
Haochen Liu, Tianyu Li, Haohan Yang, Li Chen, Caojun Wang, Ke Guo, Haochen Tian, Hongchen Li, Hongyang Li, Chen Lv
https://arxiv.org/abs/2506.09800

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
End-to-end autonomous driving has emerged as a promising paradigm for directly mapping sensor inputs to planning maneuvers using learning-based modular integrations. However, existing imitation learning (IL)-based models suffer from generalization to hard cases, and a lack of corrective feedback loop under post-deployment. While reinforcement learning (RL) offers a potential solution to tackle hard cases with optimality, it is often hindered by overfitting to specific driving cases, resulting i…

My top #CSS tip is this: treat it like you treat other code.
* Once it works, clean it up before committing code
* Refactor as needed when you make changes
* Investigate & understand the root cause of bugs before fixing them

Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
Amirreza Payandeh, Anuj Pokhrel, Daeun Song, Marcos Zampieri, Xuesu Xiao
https://arxiv.org/abs/2506.14233

Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
Large Vision-Language Models (VLMs) have demonstrated potential in enhancing mobile robot navigation in human-centric environments by understanding contextual cues, human intentions, and social dynamics while exhibiting reasoning capabilities. However, their computational complexity and limited sensitivity to continuous numerical data impede real-time performance and precise motion control. To this end, we propose Narrate2Nav, a novel real-time vision-action model that leverages a novel self-su…

Robust Adaptive Time-Varying Control Barrier Function with Application to Robotic Surface Treatment
Yitaek Kim, Christoffer Sloth
https://arxiv.org/abs/2506.14249

Robust Adaptive Time-Varying Control Barrier Function with Application to Robotic Surface Treatment
Set invariance techniques such as control barrier functions (CBFs) can be used to enforce time-varying constraints such as keeping a safe distance from dynamic objects. However, existing methods for enforcing time-varying constraints often overlook model uncertainties. To address this issue, this paper proposes a CBFs-based robust adaptive controller design endowing time-varying constraints while considering parametric uncertainty and additive disturbances. To this end, we first leverage Robust…

NFL teams most likely to end long playoff droughts in 2025 season: Will Bears, Jets break out? https://www.nfl.com/news/nfl-teams-most-likely-to-end-long-playoff-droughts-in-2025-season-will-bears-jets-break-out…

Improving Long-Range Navigation with Spatially-Enhanced Recurrent Memory via End-to-End Reinforcement Learning
Fan Yang, Per Frivik, David Hoeller, Chen Wang, Cesar Cadena, Marco Hutter
https://arxiv.org/abs/2506.05997

Improving Long-Range Navigation with Spatially-Enhanced Recurrent Memory via End-to-End Reinforcement Learning
Recent advancements in robot navigation, especially with end-to-end learning approaches like reinforcement learning (RL), have shown remarkable efficiency and effectiveness. Yet, successful navigation still relies on two key capabilities: mapping and planning, whether explicit or implicit. Classical approaches use explicit mapping pipelines to register ego-centric observations into a coherent map frame for the planner. In contrast, end-to-end learning achieves this implicitly, often through rec…

Robotic System for Chemical Experiment Automation with Dual Demonstration of End-effector and Jig Operations
Hikaru Sasaki, Naoto Komeno, Takumi Hachimine, Kei Takahashi, Yu-ya Ohnishi, Tetsunori Sugawara, Araki Wakiuchi, Miho Hatanaka, Tomoyuki Miyao, Hiroharu Ajiro, Mikiya Fujii, Takamitsu Matsubara
https://arxiv.org/abs/2506.…

Robotic System for Chemical Experiment Automation with Dual Demonstration of End-effector and Jig Operations
While robotic automation has demonstrated remarkable performance, such as executing hundreds of experiments continuously over several days, it is challenging to design a program that synchronizes the robot's movements with the experimental jigs to conduct an experiment. We propose a concept that enables the automation of experiments by utilizing dual demonstrations of robot motions and jig operations by chemists in an experimental environment constructed to be controlled by a robot. To verify t…