Tootfinder

A low-latency neural inference framework for real-time handwriting recognition from #EEG signals on an edge device https://www.nature.com/articles/s41598-025-24972-y

A low-latency neural inference framework for real-time handwriting recognition from EEG signals on an edge device - Scientific Reports
Brain–computer interfaces (BCIs) hold significant promise for restoring communication in individuals with severe motor or speech impairments. Imagined handwriting, as a form of motor imagery, offers an intuitive paradigm for character-level neural decoding. While invasive techniques such as electrocorticography (ECoG) offer high decoding accuracy, their surgical requirements pose clinical risks and hinder scalability. Non-invasive alternatives like electroencephalography (EEG) are safer and m…

Amazon Web Services announces AWS RTB Fabric, a real-time bidding service for ad buyers and sellers, aiming to cut integration hours between ad tech partners (Seb Joseph/Digiday)
https://digiday.com/marketing/amazons-next-frontier-in-ad…

Amazon’s next frontier in advertising: the cloud infrastructure it runs on
The ad dollars are nice but the real prize for Amazon is the infrastructure itself -- the rails on which the entire system runs.

PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control
Tianheng Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng
https://arxiv.org/abs/2509.16922

PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control
Audio-driven talking head generation is crucial for applications in virtual reality, digital avatars, and film production. While NeRF-based methods enable high-fidelity reconstruction, they suffer from low rendering efficiency and suboptimal audio-visual synchronization. This work presents PGSTalker, a real-time audio-driven talking head synthesis framework based on 3D Gaussian Splatting (3DGS). To improve rendering performance, we propose a pixel-aware density control strategy that adaptively …

How Google predicts the near-future availability of #EV charging points. This new Google Maps feature not only shows current real-time availability, but also predicts availability at the time of your arrival.

Reducing EV range anxiety: How a simple AI model predicts port availability

Exploring Bichronous Collaboration in Virtual Environments
Alexander Giovannelli, Shakiba Davari, Cherelle Connor, Fionn Murphy, Trey Davis, Haichao Miao, Vuthea Chheang, Brian Giera, Peer-Timo Bremer, Doug A. Bowman
https://arxiv.org/abs/2509.17230

Exploring Bichronous Collaboration in Virtual Environments
Virtual environments (VEs) empower geographically distributed teams to collaborate on a shared project regardless of time. Existing research has separately investigated collaborations within these VEs at the same time (i.e., synchronous) or different times (i.e., asynchronous). In this work, we highlight the often-overlooked concept of bichronous collaboration and define it as the seamless integration of archived information during a real-time collaborative session. We revisit the time-space ma…

End2Race: Efficient End-to-End Imitation Learning for Real-Time F1Tenth Racing
Zhijie Qiao, Haowei Li, Zhong Cao, Henry X. Liu
https://arxiv.org/abs/2509.16894 https://

End2Race: Efficient End-to-End Imitation Learning for Real-Time F1Tenth Racing
F1Tenth is a widely adopted reduced-scale platform for developing and testing autonomous racing algorithms, hosting annual competitions worldwide. With high operating speeds, dynamic environments, and head-to-head interactions, autonomous racing requires algorithms that diverge from those in classical autonomous driving. Training such algorithms is particularly challenging: the need for rapid decision-making at high speeds severely limits model capacity. To address this, we propose End2Race, a …

Privacy oversight board finds FBI does not buy real-time location data https://therecord.media/pclob-finds-fbi-does-not-use-real-time-location-data

From real-time calibrations to smart HV tuning for FAIR
Valentin Kladov, Johan Messchendorp, James Ritman
https://arxiv.org/abs/2509.17653 https://arxiv.or…

From real-time calibrations to smart HV tuning for FAIR
Real-time data processing of the next generation of experiments at FAIR requires reliable event reconstruction and thus depends heavily on in-situ calibration procedures. Previously, we developed a neural-network-based approach that predicts calibration parameters from continuously available environmental and operational data and validated it on the HADES Multiwire Drift Chambers (MDCs), achieving fast predictions as accurate as offline calibrations. In this work, we introduce several methodolo…

When it comes to international conflict, Donald Trump learns everything the hard way.
On issue after issue
—North Korea, Venezuela, Ukraine, Gaza, and more
—Trump begins by bucking conventional wisdom and insisting that a bold new approach will yield breakthroughs.
Implied, and often said outright, is that past officials who worked on the matter were feeble, inept, and craven.
Trump insists that his determination and powers of persuasion will force seismic change—…

Ahead of His U.N. Speech, Remember That Trump Is Learning Geopolitics in Real Time
A guide to pushing the U.S. president more quickly up his learning curve.

Wow. I've dealt with various toxic personalities in software development, but a good portion of the time those toxic personalities were at least extremely knowledgeable in their (often, very limited) domain.
AI, however, seems to be enabling toxic personalities *who are completely clueless*. Impressive!
https://github…

My contribution to #footpathFriday !
This was a really nice walk. Just as I like it: small paths along a nice mountain.
But I also remember that it was the time I was suffering from something called "frozen shoulder". It was a bit of a challenge to take off /on the backpack. As a wrong movement cause some REAL pain.
But this is over as well and I just try to rec…

Any sufficiently advanced disaster preparedness is indistinguishable from revolutionary dual power. This essay is a bit of a transition between the theory I've written earlier, and more concrete plans.
Even though I only touched on my life on the commune, it was hard not to write more. These are such weird spaces, with so much invisible opportunity. But they're also just so unique and special. For all the stress and uncertainty of making sure you stayed on Lorean's (the head priestess), there were also those long summer nights with the whole community (except the old lady) gathered around a fire, talking and drinking. There was almost a child-like play to the whole time.
There were so Fridays I'd come home with a couple of gallons of beer from the real world, folks would bring things from the garden, someone would grill a steak, everyone who didn't cook would clean up, and we'd just hang out and have fun. So many evenings I'd go over to Miles place with a guitar, or with his guitar, and we'd pass it around over a few beers, talking about philosophy, Star Wars, or some book or other. It's hard not to write about the strange magic of that space.
My partner and I bonded over similar experiences, mine on a weird little religious commune in California and theirs as a temporary worker at Omega Institute. Both had exploitation, people on weird power trips, frustrating dynamics, but also a strange magic and freedom. Both were sort of fantasy worlds, but places that let us see through this one, let us imagine something that something else is possible behind the veil.
There are many such veils.
Perhaps it's fitting that this is more meandering, as a good wander can help the transition between lots of hard thinking and lots of hard working.
https://anarchoccultism.org/building-zion/evaluating-options
Editing feedback (especially typos, spelling, grammar) is always welcome, as are questions and even wider structural advice. I've been adding the handles of folks who provide feedback to the intro in a "thank you" section. If you do help and wouldn't like to be added, please let me know.

Happy WKRP Turkey Drop Day to all who celebrate
#Shitpost #Shitposting #ShamelesslyStolenFromSomewhereElseOnTheInternetHonestlyICantKeepTrackOfThisStuffAnymore

This tanker does the BEST review of 'Fury' ever! "Better Than Walking?" HAHAHA!
(You'll see. This guy's got stories...)
▶️ Real Army Tanker's FIRST TIME Watching FURY (2014) | First Time Movie Review
https://youtube.com/watch?v=ih-RNp8eMM

Maintaining accurate timing in virtual machines has always been a challenge. Especially on hosts with many VMs.
Here's a clever solution, hopefully coming soon to a hypervisor or OS near you.
https://uapi-group.org/specifications/specs/vmclock/

NFL says it's trying to improve officiating on 'very difficult' tush push plays https://www.nytimes.com/athletic/6737672/2025/10/21/tush-push-officiating-nfl/

Very good overview of the effectiveness of Honeywell PTM7950 phase-change thermal compound compared to traditional thermal pastes https://www.igorslab.de/en/overhyped-honeywell-ptm7950-in-lab-test-and-as-game-changer-for-graphics-cards/4…

Threat intel company Dataminr plans to acquire cybersecurity threat intel provider ThreatConnect for $290M; Dataminr raised $85M in convertible funding in March (Greg Otto/CyberScoop)
https://cyberscoop.com/dataminr-threatconnect-acquisition/

Dataminr to acquire cybersecurity firm ThreatConnect for $290 million
Dataminr, a New York-based company specializing in real-time threat intelligence, announced plans Tuesday to acquire ThreatConnect, a cybersecurity threat intelligence provider, for $290 million. The acquisition will combine Dataminr’s AI-powered analysis of public data with ThreatConnect’s internal threat management capabilities, creating what the companies describe as “Client-Tailored intelligence” that adapts to individual customer needs. The […]

A Reliable Robot Motion Planner in Complex Real-world Environments via Action Imagination
Chengjin Wang, Yanmin Zhou, Zhipeng Wang, Zheng Yan, Feng Luan, Shuo Jiang, Runjie Shen, Hongrui Sang, Bin He
https://arxiv.org/abs/2509.16963

A Reliable Robot Motion Planner in Complex Real-world Environments via Action Imagination
Humans and animals can make real-time adjustments to movements by imagining their action outcomes to prevent unanticipated or even catastrophic motion failures in unknown unstructured environments. Action imagination, as a refined sensorimotor strategy, leverages perception-action loops to handle physical interaction-induced uncertainties in perception and system modeling within complex systems. Inspired by the action-awareness capability of animal intelligence, this study proposes an imaginati…

Dataminr to acquire cybersecurity firm ThreatConnect for $290 million
https://cyberscoop.com/dataminr-threatconnect-acquisition/

Dataminr to acquire cybersecurity firm ThreatConnect for $290 million
Dataminr, a New York-based company specializing in real-time threat intelligence, announced plans Tuesday to acquire ThreatConnect, a cybersecurity threat intelligence provider, for $290 million. The acquisition will combine Dataminr’s AI-powered analysis of public data with ThreatConnect’s internal threat management capabilities, creating what the companies describe as “Client-Tailored intelligence” that adapts to individual customer needs. The […]

DroFiT: A Lightweight Band-fused Frequency Attention Toward Real-time UAV Speech Enhancement
Jeongmin Lee, Chanhong Jeon, Hyungjoo Seo, Taewook Kang
https://arxiv.org/abs/2509.16945

DroFiT: A Lightweight Band-fused Frequency Attention Toward Real-time UAV Speech Enhancement
This paper proposes DroFiT (Drone Frequency lightweight Transformer for speech enhancement, a single microphone speech enhancement network for severe drone self-noise. DroFit integrates a frequency-wise Transformer with a full/sub-band hybrid encoder-decoder and a TCN back-end for memory-efficient streaming. A learnable skip-and-gate fusion with a combined spectral-temporal loss further refines reconstruction. The model is trained on VoiceBank-DEMAND mixed with recorded drone noise (-5 to -25 d…

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
Md Wasiul Haque, Md Erfan, Sagar Dasgupta, Md Rayhanur Rahman, Mizanur Rahman
https://arxiv.org/abs/2509.16899

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
The interest in autonomous vehicles (AVs) for critical missions, including transportation, rescue, surveillance, reconnaissance, and mapping, is growing rapidly due to their significant safety and mobility benefits. AVs consist of complex software systems that leverage artificial intelligence (AI), sensor fusion algorithms, and real-time data processing. Additionally, AVs are becoming increasingly reliant on open-source software supply chains, such as open-source packages, third-party software …

Can they be trusted to get/do anything right?
The SSL certificate of Transport Canberra's real-time feeds is currently expired. This has resulted in an outage of the MyWay real-time data feed, impacting the availability of real-time data across Transport Canberra bus and light rail services.
#TransportCanberra

Implementation of the Collision Avoidance System for DO-178C Compliance
Rim Zrelli, Henrique Amaral Misson, Sorelle Kamkuimo, Maroua Ben Attia, Abdo Shabah, Felipe Gohring de Magalhaes, Gabriela Nicolescu
https://arxiv.org/abs/2509.16844

Implementation of the Collision Avoidance System for DO-178C Compliance
This technical report presents the detailed implementation of a Collision Avoidance System (CAS) for Unmanned Aerial Vehicles (UAVs), developed as a case study to demonstrate a rigorous methodology for achieving DO-178C compliance in safety-critical software. The CAS is based on functional requirements inspired by NASA's Access 5 project and is designed to autonomously detect, evaluate, and avoid potential collision threats in real-time, supporting the safe integration of UAVs into civil airspa…

Monitoring Nitric Oxide in Trigeminal Neuralgia Rats with a Cerium Single-Atom Nanozyme Electrochemical Biosensor
Kangling Tian, Fuhua Li, Ran Chen, Shihong Chen, Wenbin Wei, Yihang Shen, Muzi Xu, Chunxian Guo, Luigi G. Occhipinti, Hong Bin Yang, Fangxin Hu
https://arxiv.org/abs/2509.17448

Monitoring Nitric Oxide in Trigeminal Neuralgia Rats with a Cerium Single-Atom Nanozyme Electrochemical Biosensor
Trigeminal neuralgia (TN) is the most common neuropathic disorder; however, its pathogenesis remains unclear. A prevailing theory suggests that nitric oxide (NO) may induce nerve compression and irritation via vascular dilation, thereby being responsible for the condition, making real-time detection of generated NO critical. However, traditional evaluations of NO rely on indirect colorimetric or chemiluminescence techniques, which offer limited sensitivity and spatial resolution for its real-ti…

Low-energy proton impact dynamics on hydrocarbons: Dependence on kinetic energy and incident site
Misa Viveiros, Roy Lau, Samuel S. Taylor, Patrick Barron, Attila Czirjak, Cody Covington, Kalman Varga
https://arxiv.org/abs/2509.16252

Low-energy proton impact dynamics on hydrocarbons: Dependence on kinetic energy and incident site
The dynamics of low-energy proton collisions with hydrocarbon with hydrocarbon molecules are investigated using real-time time-dependent density functional theory. Through systematic variation of proton kinetic energy and impact site on the molecular surface, the resulting scattering, proton capture, and bond dissociation pathways are analyzed. The simulations reveal a strong dependence of reaction outcomes on both incident energy and collision geometry, with the interplay between electronic an…

An Improved Yau-Yau Algorithm for High Dimensional Nonlinear Filtering Problems
Shing-Tung Yau, Yi-Shuai Niu
https://arxiv.org/abs/2509.16896 https://arxiv…

An Improved Yau-Yau Algorithm for High Dimensional Nonlinear Filtering Problems
Nonlinear state estimation under noisy observations is rapidly intractable as system dimension increases. We introduce an improved Yau-Yau filtering framework that breaks the curse of dimensionality and extends real-time nonlinear filtering to systems with up to thousands of state dimensions, achieving high-accuracy estimates in just a few seconds with rigorous theoretical error guarantees. This new approach integrates quasi-Monte Carlo low-discrepancy sampling, a novel offline-online update, h…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

Closing the Loop Inside Neural Networks: Causality-Guided Layer Adaptation for Fault Recovery Control
Mahdi Taheri, Soon-Jo Chung, Fred Y. Hadaegh
https://arxiv.org/abs/2509.16837

Closing the Loop Inside Neural Networks: Causality-Guided Layer Adaptation for Fault Recovery Control
This paper studies the problem of real-time fault recovery control for nonlinear control-affine systems subject to actuator loss of effectiveness faults and external disturbances. We derive a two-stage framework that combines causal inference with selective online adaptation to achieve an effective learning-based recovery control method. In the offline phase, we develop a causal layer attribution technique based on the average causal effect (ACE) to evaluate the relative importance of each laye…

MRADNET: a Compact Radar Object Detector with MetaFormer
Huaiyu Chen, Fahed Hassanat, Robert Laganiere, Martin Bouchard
https://arxiv.org/abs/2509.16223 https://

MRADNET: a Compact Radar Object Detector with MetaFormer
Frequency-modulated continuous wave radars have gained increasing popularity in the automotive industry. Its robustness against adverse weather conditions makes it a suitable choice for radar object detection in advanced driver assistance systems. These real-time embedded systems have requirements for the compactness and efficiency of the model, which have been largely overlooked in previous work. In this work, we propose mRadNet, a novel radar object detection model with compactness in mind. m…

Learn to Rank Risky Investors: A Case Study of Predicting Retail Traders' Behaviour and Profitability
Weixian Waylon Li, Tiejun Ma
https://arxiv.org/abs/2509.16616 https://

Learn to Rank Risky Investors: A Case Study of Predicting Retail Traders' Behaviour and Profitability
Identifying risky traders with high profits in financial markets is crucial for market makers, such as trading exchanges, to ensure effective risk management through real-time decisions on regulation compliance and hedging. However, capturing the complex and dynamic behaviours of individual traders poses significant challenges. Traditional classification and anomaly detection methods often establish a fixed risk boundary, failing to account for this complexity and dynamism. To tackle this issue…

Neural likelihood estimators for flexible gravitational wave data analysis
Luca Negri, Anuradha Samajdar
https://arxiv.org/abs/2509.17606 https://arxiv.org…

Neural likelihood estimators for flexible gravitational wave data analysis
In this paper, we develop a Neural Likelihood Estimator and apply it to analyse real gravitational-wave (GW) data for the first time. We assess the usability of neural likelihood for GW parameter estimation and report the parameter space where neural likelihood performs as a robust estimator to output posterior probability distributions using modest computational resources. In addition, we demonstrate that the trained Neural likelihood can also be used in further analysis, enabling us to obtain…

RE: https://assortedflotsam.com/@NewsBot/115753581696805755
More piracy.
The movie "Pirates of the Caribbean" is being updated in real time.

Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
Eason Chen, Sophia Judicke, Kayla Beigh, Xinyi Tang, Zimo Xiao, Chuangji Li, Shizhuo Li, Reed Luttmer, Shreya Singh, Maria Yampolsky, Naman Parikh, Yi Zhao, Meiyi Chen, Scarlett Huang, Anishka Mohanty, Gregory Johnson, John Mackey, Jionghao Lin, Ken Koedinger
https://…

Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
We evaluate the effectiveness of LLM-Tutor, a large language model (LLM)-powered tutoring system that combines an AI-based proof-review tutor for real-time feedback on proof-writing and a chatbot for mathematics-related queries. Our experiment, involving 148 students, demonstrated that the use of LLM-Tutor significantly improved homework performance compared to a control group without access to the system. However, its impact on exam performance and time spent on tasks was found to be insignifi…

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Junhao Zhuang, Shi Guo, Xin Cai, Xiaohui Li, Yihao Liu, Chun Yuan, Tianfan Xue
https://arxiv.org/abs/2510.12747

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving efficiency, scalability, and real-time performance. To this end, we propose FlashVSR, the first diffusion-based one-step streaming framework towards real-time VSR. FlashVSR runs at appro…

How the Nintendo Wii's Wiimote changed gaming #Wii #Nintendo

How the Nintendo Wii's remote control changed gaming — one strike at a time - Australia News Beep
With a television remote-style controller that tracked the motion of a player's hands in real time, the Nintendo Wii was unlike any console before it.

Meta-optical Miniscope for Multifunctional Imaging
Zhihao Zhou, Khushboo Kumari, Ningzhi Xie, Shane Colburn, Chetan Poudel, Praneeth Chakravarthula, Karl F. B\"ohringer, Arka Majumdar, Johannes E. Fr\"och
https://arxiv.org/abs/2509.16373

Meta-optical Miniscope for Multifunctional Imaging
Miniaturized microscopes (miniscopes) have opened a new frontier in animal behavior studies, enabling real-time imaging of neuron activity while leaving animals largely unconstrained. Canonical designs typically use Gradient-Index (GRIN) lenses or refractive lenses as the objective module for excitation and fluorescence collection, but GRIN lenses suffer from aberrations and refractive lenses are bulky and complex. Meta-optics, composed of subwavelength diffractive elements, offer a promising a…

My latest* #MathReviews review has appeared! (*this is the first time the order of appearance didn't match the order of my submitting it)
link for subscribers =
https://mathscinet.ams.org/mathscinet/

Evaluating the Energy Efficiency of NPU-Accelerated Machine Learning Inference on Embedded Microcontrollers
Anastasios Fanariotis, Theofanis Orphanoudakis, Vasilis Fotopoulos
https://arxiv.org/abs/2509.17533

Evaluating the Energy Efficiency of NPU-Accelerated Machine Learning Inference on Embedded Microcontrollers
The deployment of machine learning (ML) models on microcontrollers (MCUs) is constrained by strict energy, latency, and memory requirements, particularly in battery-operated and real-time edge devices. While software-level optimizations such as quantization and pruning reduce model size and computation, hardware acceleration has emerged as a decisive enabler for efficient embedded inference. This paper evaluates the impact of Neural Processing Units (NPUs) on MCU-based ML execution, using the A…

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Donghang Wu (Tony), Haoyang Zhang (Tony), Jun Chen (Tony), Xiangyu (Tony), Zhang, Hexin Liu, Eng Siong Chng, Fei Tian, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu
https://arxiv.org/abs/2510.09592

Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models
Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially. Enabling SLMs to think while speaking, similar to humans, is attracting increasing attention. We present, for the first time, Mind-Paced Speaking (MPS), a brain-inspired framework that enables high-fidelity, real-time reasoning. Similar to how humans utilize distinct brain regions for thinking and responding, we propo…

It's time for Cascadia to impound federal taxes
https://www.cascadia-journal.com/its-time-for-cascadia-to-impound-federal-taxes/?ref=cascadia-journal-newsletter
Where Cascadia is Washington and Oregon only.…

It's time for Cascadia to impound federal taxes
As Washington and Oregon face numerous economic threats, including the real possibility of recession, disastrous flooding, continued wildfires, and massive cuts to the federal budget by the Trump administration, it's time to consider an idea that's been gaining traction in blue states hit hard by Trump's authoritarian rule: holding federal

We've all seen wobbly windows on Linux. I think it's time for an upgrade: We need to make real-time cloth simulation windows a thing!
#Linux #Wayland

NOW we did it
y'all I'm absolutely a sucker for just a Really Gross Funny Early 2000s Movie
I feel like the early to mid 2000s was simply the best time to make a Real Nasty Movie

End-to-End Co-Simulation Testbed for Cybersecurity Research and Development in Intelligent Transportation Systems
Minhaj Uddin Ahmad, Akid Abrar, Sagar Dasgupta, Mizanur Rahman
https://arxiv.org/abs/2509.16489

End-to-End Co-Simulation Testbed for Cybersecurity Research and Development in Intelligent Transportation Systems
Intelligent Transportation Systems (ITS) have been widely deployed across major metropolitan regions worldwide to improve roadway safety, optimize traffic flow, and reduce environmental impacts. These systems integrate advanced sensors, communication networks, and data analytics to enable real-time traffic monitoring, adaptive signal control, and predictive maintenance. However, such integration significantly broadens the ITS attack surface, exposing critical infrastructures to cyber threats th…

🔪 A scalpel that can diagnose? Scientists unveil a 'Lab-on-a-Scalpel' for real-time surgical insights
https://medicalxpress.com/news/2025-10-scalpel-scientists-unveil-lab-real.html

A scalpel that can diagnose? Scientists unveil a 'Lab-on-a-Scalpel' for real-time surgical insights
Imagine a surgeon in the middle of a complex operation, able to get instant biochemical feedback not from a lab down the hall, but from the very tool in their hand. This vision is now one step closer to reality thanks to researchers at the University of Chemistry and Technology, Prague (UCT Prague).

In the Washington, DC area there's a real estate agency called RLAH, and every time I see one of their signs for a split second I think that it's for R'lyeh Real Estate. #cthulhu

Spagnola: Time to prove Cowboys are for real https://www.dallascowboys.com/news/spagnola-time-to-prove-cowboys-are-for-real

The most 2004 interview quote ever.
#smartphone #web

“In fact, while the trauma and terror that Bovino’s unit instills is certainly real and damaging, it’s remarkable to note how _ineffective_ the force has turned out to be. Time and again, these agents — and the broader DHS and White House policies behind it — are being exposed not for their strength, but their weakness. Ordinary Americas are stronger — braver _and_ better.”

Trump, Border Patrol Retreat in Failure from Chicago
Five important lessons of the first six months of Trump’s immigration raids — and why CBP’s Greg Bovino is the Nathan Bedford Forrest of the Trump era.

LangChain, whose open-source framework connects AI apps to real-time data, raised a $125M Series B led by IVP at a $1.25B valuation (Sharon Goldman/Fortune)
https://fortune.com/2025/10/20/exclusive-early-ai-darling-lan…

Exclusive: Early AI darling LangChain is now a unicorn with a fresh $125 million in funding
With new funding led by IVP and a roster of enterprise customers, LangChain wants to power the coming wave of AI agents—and investors are betting it could be the next big infrastructure giant.

Cool projection/tracking system Panasonic!
https://docs.connect.panasonic.com/projector/products/swr10/
(via @……

#overunder

Time for a piece of rock ’n’ roll history this week with a track from Link Wray and His Ray Men.
This one's got some real history, so give it a listen and read about the story behind the song, the band and a piece of classic rock music.
Don't forget to follow us to keep up with our musical journey, as we shine a spotlight on one handpicked track from across the epic world of #rock

Link Wray and His Ray Men - Rumble
One awesome, hand picked song from the world of rock and metal, showcased every week. Nothing more, nothing less! 🤘

SwarmChat: An LLM-Based, Context-Aware Multimodal Interaction System for Robotic Swarms
Ettilla Mohiuddin Eumi, Hussein Abbass, Nadine Marcus
https://arxiv.org/abs/2509.16920 ht…

SwarmChat: An LLM-Based, Context-Aware Multimodal Interaction System for Robotic Swarms
Traditional Human-Swarm Interaction (HSI) methods often lack intuitive real-time adaptive interfaces, making decision making slower and increasing cognitive load while limiting command flexibility. To solve this, we present SwarmChat, a context-aware, multimodal interaction system powered by Large Language Models (LLMs). SwarmChat enables users to issue natural language commands to robotic swarms using multiple modalities, such as text, voice, or teleoperation. The system integrates four LLM-ba…

ParaCook: On Time-Efficient Planning for Multi-Agent Systems
Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
https://arxiv.org/abs/2510.11608

ParaCook: On Time-Efficient Planning for Multi-Agent Systems
Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking t…

Friends, of course we all hope the #ceasefire will hold. Of course we all hope that aid trucks will be allowed to move. Of course we all hope that there will be a stable, just peace.
But hope isn't enough. The suffering in #Gaza hasn't ended. We must keep pressure on our governments to ensu…

This is a good video about Masculinity. I generally agree with it. Galloway get a lot wrong on gender. Though I don't really think he is a grifter. I think he cares about the topic and wants a good out come not too far off what the person in this video wants.
As I think more about big tent politics I wonder if this video could do more calling in then calling out. There are real enemies out there and to me, at this time, Galloway is a mistaken ally rather then an enemy

Kronecker second limit formula for real quadratic fields
YoungJu Choie, Rahul Kumar
https://arxiv.org/abs/2510.10554 https://arxiv.org/pdf/2510.10554

Kronecker second limit formula for real quadratic fields
In this paper, the second Kronecker ``limit" formula for a real quadratic field is established for the first time. More precisely, we obtain the second Kronecker limit formula of Zagier's zeta function. Using the reduction theory of Zagier, which connects Zagier's zeta function to the zeta function of real quadratic fields, we express the values of the zeta function of narrow ideal classes in real quadratic fields at natural arguments in terms of an analytic function which we call the \emph{hig…

Ionospheric gradient estimation using ground-based GEO observations for monitoring multi-scale ionospheric dynamics: #Ionosphere in motion - a new way to track space weather in real time: https://www.eurekalert.org/news-releases/1110143

No, Jayden Daniels isn't on the path to becoming Washington's next RGIII https://www.nytimes.com/athletic/6734044/2025/10/21/jayden-daniels-rgiii-commanders-injury/

Want to see a LLM become real self-aware, real fast?
Ask it to pretend it’s giving you advice that would have been current based on everything it could have known in 2005, and if it had been built by one of the big technology companies of the time.
Then ask it if everyone followed that advice, would it—the LLM—exist today?
(Then, for yourself, think about what the result of everyone vibe coding their way to 20 years into the future from today looks like.)

Human-in-the-Loop Bandwidth Estimation for Quality of Experience Optimization in Real-Time Video Communication
Sami Khairy, Gabriel Mittag, Vishak Gopal, Ross Cutler
https://arxiv.org/abs/2510.12265

Human-in-the-Loop Bandwidth Estimation for Quality of Experience Optimization in Real-Time Video Communication
The quality of experience (QoE) delivered by video conferencing systems is significantly influenced by accurately estimating the time-varying available bandwidth between the sender and receiver. Bandwidth estimation for real-time communications remains an open challenge due to rapidly evolving network architectures, increasingly complex protocol stacks, and the difficulty of defining QoE metrics that reliably improve user experience. In this work, we propose a deployed, human-in-the-loop, data-…

Real-Time Health Analytics Using Ontology-Driven Complex Event Processing and LLM Reasoning: A Tuberculosis Case Study
Ritesh Chandra, Sonali Agarwal, Navjot Singh
https://arxiv.org/abs/2510.09646

Real-Time Health Analytics Using Ontology-Driven Complex Event Processing and LLM Reasoning: A Tuberculosis Case Study
Timely detection of critical health conditions remains a major challenge in public health analytics, especially in Big Data environments characterized by high volume, rapid velocity, and diverse variety of clinical data. This study presents an ontology-enabled real-time analytics framework that integrates Complex Event Processing (CEP) and Large Language Models (LLMs) to enable intelligent health event detection and semantic reasoning over heterogeneous, high-velocity health data streams. The a…

#cloudflair is down for matrix.org
Does anyone else host #matterbridge

Pentagon pizza spike
https://pizzint.watch/

Feeling helpless? Don’t. All of this resistance makes a real and concrete difference. Honestly, the fact that this huge chunk of local residents is giving a visible, sustained “HELL NO” all the time is basically the •only• thing holding them back at this point — but it •is• making a difference.
If there were a sense of blanket permission, a sense that nobody is watching and nobody cares, a sense that there will never be consequences…we’d be in a whole different circle of hell right now.

Only Fortnite got a problem, a demo seems to work fine.
I think I got it! Nvidia is maintaining their cloud service in a few locations.
Maybe I'm just unlucky to be in one of these locations...
Does the GeForce NOW service have any downtime now?
Glad I have the status link:
https://status.geforcenow.com/

There's a word at the beginning and end of Dawn of Everything that feels self-referential right now: Kairos.
> We began this book with a quote which refers to the Greek notion of kairos as one of those occasional moments in a society’s history when its frames of reference undergo a shift – a metamorphosis of the fundamental principles and symbols, when the lines between myth and history, science and magic become blurred – and, therefore, real change is possible. Philosophers sometimes like to speak of ‘the Event’ – a political revolution, a scientific discovery, an artistic masterpiece – that is, a breakthrough which reveals aspects of reality that had previously been unimaginable but, once seen, can never be unseen. If so, kairos is the kind of time in which Events are prone to happen.
> Societies around the world appear to be cascading towards such a point. This is particularly true of those which, since the First World War, have been in the habit of calling themselves ‘Western’. On the one hand, fundamental breakthroughs in the physical sciences, or even artistic expression, no longer seem to occur with anything like the regularity people came to expect in the late nineteenth and early twentieth centuries. Yet at the same time, our scientific means of understanding the past, not just our species’ past but that of our planet, has been advancing with dizzying speed. Scientists in 2020 are not (as readers of mid-twentieth-century science fiction might have hoped) encountering alien civilizations in distant star systems; but they are encountering radically different forms of society under their own feet, some forgotten and newly rediscovered, others more familiar, but now understood in entirely new ways.
Reading this as I write something very inspired by this work feels especially serendipitous, especially at this time. When they wrote the book, I think that kairos felt more serendipitous itself. But as the frequency of opportunity increases, the veil between realities feels more malleable... that perhaps we can poke a finger through and open a portal to a completely different future than the one we've felt locked into for such a long time.
https://anarchoccultism.org/building-zion/the-coordinated-swarm-lyhr

Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
Jasmin Freudenberg, Kai Hahn, Christian Weber, Madjid Fathi
https://arxiv.org/abs/2510.12541 https:…

Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
The increasing popularity of portable ECG systems and the growing demand for privacy-compliant, energy-efficient real-time analysis require new approaches to signal processing at the point of data acquisition. In this context, the edge domain is acquiring increasing importance, as it not only reduces latency times, but also enables an increased level of data security. The FACE project aims to develop an innovative machine learning solution for analysing long-term electrocardiograms that synergi…

SMART-3D: Three-Dimensional Self-Morphing Adaptive Replanning Tree
Priyanshu Agrawal, Shalabh Gupta, Zongyuan Shen
https://arxiv.org/abs/2509.16812 https://

SMART-3D: Three-Dimensional Self-Morphing Adaptive Replanning Tree
This paper presents SMART-3D, an extension of the SMART algorithm to 3D environments. SMART-3D is a tree-based adaptive replanning algorithm for dynamic environments with fast moving obstacles. SMART-3D morphs the underlying tree to find a new path in real-time whenever the current path is blocked by obstacles. SMART-3D removed the grid decomposition requirement of the SMART algorithm by replacing the concept of hot-spots with that of hot-nodes, thus making it computationally efficient and scal…

Reverse Attention for Lightweight Speech Enhancement on Edge Devices
Shuubham Ojha, Felix Gervits, Carol Espy-Wilson
https://arxiv.org/abs/2509.16705 https://

Reverse Attention for Lightweight Speech Enhancement on Edge Devices
This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference without compromising performance. Key contributions include infusing soft attention-based attention gates in the U-Net architecture which is known to perform well for segmentation tasks and is optimized for GPUs. Experimental evaluations demonstrate that the …

Spagnola: Time to prove Cowboys are for real https://www.dallascowboys.com/news/spagnola-time-to-prove-cowboys-are-for-real

Amazon partners with FanDuel to allow viewers to track their NBA wagers in real time during NBA games on Prime Video (CNBC)
https://www.cnbc.com/2025/09/30/amazon-prime-fanduel-real-time-nba-betting-updates.html

Amazon Prime Video teams up with FanDuel for real-time betting updates during NBA games
Bettors will be able to link their FanDuel accounts to their Prime Video profiles and see how their wagers are playing out in real time.

Seeing Life at the Quantum Limit
Congratulations to
Dr Nicolas Mauranyapin,
winner of QUBIC’s inaugural Scientific Achievement Award - Cell Theme!
Nico has built a quantum-limited microscope, so sensitive it operates at the quantum shot noise limit,
the same benchmark used in gravitational wave detection.
This means it can capture the faintest signals nature allows.
This breakthrough enables real-time observation of living cells without damage,

New Android malware can capture private messages, researchers warn https://therecord.media/new-android-malware-captures-private-messages

Nirvana, which uses real-time driving telematics to build insurance policies for truckers, raised a $100M Series D at a $1.5B valuation, up from $830M in March (Mary Ann Azevedo/Crunchbase News)
https://news.crunchbase.com/ai/insurance-platform-nirvana-val…

Exclusive: AI Insurance Startup Nirvana Nearly Doubles Valuation To $1.5B with $100M Series D
Nirvana Insurance, an AI-based commercial insurance platform for the trucking industry, has raised a $100 million Series D round at a $1.5 billion valuation, it tells Crunchbase News exclusively. The raise comes just over nine months after the startup raised $80 million in a Series C round of funding at an $830 million valuation.

StreamingVLM: Real-Time Understanding for Infinite Video Streams
Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, Song Han
https://arxiv.org/abs/2510.09608 …

StreamingVLM: Real-Time Understanding for Infinite Video Streams
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we in…

"Europe needs to recognize this as the crisis it has been waiting for. The continent is in real danger of being sidelined by its most important ally, and its ability to defend itself and secure its future role in the world hinges on its ability to mobilize resources and act collectively.
The EU’s decision last week to extend sanctions on Russian central bank assets—made without unanimous consent—is a good start."

Matchmaker: An Open-source Library for Real-time Piano Score Following and Systematic Evaluation
Jiyun Park, Carlos Cancino-Chac\'on, Suhit Chiruthapudi, Juhan Nam
https://arxiv.org/abs/2510.10087 …

Matchmaker: An Open-source Library for Real-time Piano Score Following and Systematic Evaluation
Real-time music alignment, also known as score following, is a fundamental MIR task with a long history and is essential for many interactive applications. Despite its importance, there has not been a unified open framework for comparing models, largely due to the inherent complexity of real-time processing and the language- or system-dependent implementations. In addition, low compatibility with the existing MIR environment has made it difficult to develop benchmarks using large datasets avail…

TF-CorrNet: Leveraging Spatial Correlation for Continuous Speech Separation
Ui-Hyeop Shin, Bon Hyeok Ku, Hyung-Min Park
https://arxiv.org/abs/2509.16481 https://

TF-CorrNet: Leveraging Spatial Correlation for Continuous Speech Separation
In general, multi-channel source separation has utilized inter-microphone phase differences (IPDs) concatenated with magnitude information in time-frequency domain, or real and imaginary components stacked along the channel axis. However, the spatial information of a sound source is fundamentally contained in the differences between microphones, specifically in the correlation between them, while the power of each microphone also provides valuable information about the source spectrum, which is…

WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis
Anderson de Lima Luiz
https://arxiv.org/abs/2509.25192

WARP -- Web-Augmented Real-time Program Repairer: A Real-Time Compilation Error Resolution using LLMs and Web-Augmented Synthesis
Compilation errors represent a significant bottleneck in software development productivity. This paper introduces WARP (Web-Augmented Real-time Program Repairer), a novel system that leverages Large Language Models (LLMs) and dynamic web-augmented synthesis for real-time resolution of these errors. WARP actively monitors developer terminals, intelligently detects compilation errors, and synergistically combines the understanding of a fine-tuned Code-LLM with relevant solutions, explanations, an…

Analysis of the Geometric Heat Flow Equation: Computing Geodesics in Real-Time with Convergence Guarantees
Samuel G. Gessow, Brett T. Lopez
https://arxiv.org/abs/2510.11692 http…

Analysis of the Geometric Heat Flow Equation: Computing Geodesics in Real-Time with Convergence Guarantees
We present an analysis on the convergence properties of the so-called geometric heat flow equation for computing geodesics (shortest-path~curves) on Riemannian manifolds. Computing geodesics numerically in real-time has become an important capability in several fields, including control and motion planning. The geometric heat flow equation involves solving a parabolic partial differential equation whose solution is a geodesic. In practice, solving this PDE numerically can be done efficiently, a…

The Trump administration is arguing that requiring real-time American Sign Language interpretation of events like White House press briefings
“would severely intrude on the President’s prerogative to control the image he presents to the public,”
part of a lawsuit seeking to require the White House to provide the services.
Department of Justice attorneys haven’t elaborated on how doing so might hamper the portrayal Trump seeks to present to the public.
But overturning p…

White House says sign language services 'intrude' on Trump's public image
The Trump administration argues that providing real-time American Sign Language interpretation for events like White House press briefings would intrude on the president’s control over his public image. This stance is part of a lawsuit filed by the National Association for the Deaf, which claims the lack of ASL interpretation denies deaf Americans access to important communications. The Justice Department suggests alternatives like online transcripts and closed captioning provide what's neede…

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Guo Qin, Zhi Chen, Yong Liu, Zhiyuan Shi, Haixuan Liu, Xiangdong Huang, Jianmin Wang, Mingsheng Long
https://arxiv.org/abs/2510.12681

CoRA: Covariate-Aware Adaptation of Time Series Foundation Models
Time Series Foundation Models (TSFMs) have shown significant impact through their model capacity, scalability, and zero-shot generalization. However, due to the heterogeneity of inter-variate dependencies and the backbone scalability on large-scale multivariate datasets, most TSFMs are typically pre-trained on univariate time series. This limitation renders them oblivious to crucial information from diverse covariates in real-world forecasting tasks. To further enhance the performance of TSFMs,…

Newsletter platform Beehiiv announces new features, including for AI website creation, podcast hosting, digital product sales, and real-time analytics (Dominic-Madori Davis/TechCrunch)
https://techcrunch.com/2025/11/13/news

Newsletter platform beehiiv adds AI website building, creator tools in major expansion | TechCrunch
Newsletter platform beehiiv announced a massive expansion to its platform on Thursday, including offering real-time analytics and AI website creation.

LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation
Jun Chen, Shichao Hu, Jiuxin Lin, Wenjie Li, Zihan Zhang, Xingchen Li, JinJiang Liu, Longshuai Xiao, Chao Weng, Lei Xie, Zhiyong Wu
https://arxiv.org/abs/2510.10687

LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation
In-car multi-zone speech separation, which captures voices from different speech zones, plays a crucial role in human-vehicle interaction. Although previous SpatialNet has achieved notable results, its high computational cost still hinders real-time applications in vehicles. To this end, this paper proposes LSZone, a lightweight spatial information modeling architecture for real-time in-car multi-zone speech separation. We design a spatial information extraction-compression (SpaIEC) module that…

Chord Colourizer: A Near Real-Time System for Visualizing Musical Key
Paul Haimes
https://arxiv.org/abs/2510.10173 https://arxiv.org/pdf/2510.10173

Chord Colourizer: A Near Real-Time System for Visualizing Musical Key
This paper introduces Chord Colourizer, a near real-time system that detects the musical key of an audio signal and visually represents it through a novel graphical user interface (GUI). The system assigns colours to musical notes based on Isaac Newton's original colour wheel, preserving historical links between pitch and hue, and also integrates an Arduino-controlled LED display using 3D-printed star-shaped diffusers to offer a physical ambient media representation. The method employs Constant…

High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
Feng Zhang, Haoyou Deng, Zhiqiang Li, Lida Li, Bin Xu, Qingbo Lu, Zisheng Cao, Minchen Wei, Changxin Gao, Nong Sang, Xiang Bai
https://arxiv.org/abs/2510.11613

High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network
Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performance, producing powerful models that cannot be deployed on edge devices, or prioritized computational efficiency, resulting in inadequate performance for real-world applications. To this end, this paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacia…

QASTAnet: A DNN-based Quality Metric for Spatial Audio
Adrien Llave, Emma Granier, Gr\'egory Pallone
https://arxiv.org/abs/2509.16715 https://arxiv.org…

QASTAnet: A DNN-based Quality Metric for Spatial Audio
In the development of spatial audio technologies, reliable and shared methods for evaluating audio quality are essential. Listening tests are currently the standard but remain costly in terms of time and resources. Several models predicting subjective scores have been proposed, but they do not generalize well to real-world signals. In this paper, we propose QASTAnet (Quality Assessment for SpaTial Audio network), a new metric based on a deep neural network, specialized on spatial audio (ambison…

I keep coming back to the mirror dualities of the oppressed and oppressor under authoritarianism.
The oppressed is portrayed as both weak and godlike. The stereotypes are always some variation on sloth and incompetence, but yet somehow also a menace capable of destroying the "pure" society. To use the most relevant current example, Antifa being both little femme soy boys who would always get beat up by "real men" while also being an international terrorist organization on the brink of overthrowing the US government, the unarmed presence of whom makes the heavily armed agents of ICE flee for their lives. Antifa is both having absolutely no impact on ICE, and also having such an impact on ICE that the military needs to come in to protect them. The contradiction is obvious but never seems to occur to those who hold both to be true at the same time.
But few talk about the duality of the oppressor. The sovereign throughout history has always been both a ruler above the law, sometimes even the representative or incarnation of a divine force. Yet, this same superhuman/god-man is also a baby who needs constant care. This is absolutely a through line from the very earliest records of sovereign cults to modern cult leaders, CEOs, and Trump today. Power, for these people, is expressed both as the ability to force others to enact their will and in the ability to compel others to care for them. Can any of these "men" cook? Can they fix anything themselves? They are driven everywhere, cooked for all the time, constantly protected from danger. Kings are still dressed, at least for rituals. I could dissect masculinity here, but that's a whole thing.
It is as though the drive to care for our children, who must be taught to behave within acceptable norms, is hijacked by "leaders" who demand our care and attention... even at the expense of our literal children. And recently we've seen some of those very CEOs, with LLMs and return to office demands, show that their judgment is also little better than children, making decisions while pretending to understand a subject.
The oppressed are portrayed as both god-like and impotent and are, in fact, neither. Meanwhile the rulers portray themselves only as invulnerable and are, in fact, childish in their ability to survive without constant support. Their greatest fear from the collapse of society is figuring out how to make sure people keep taking care of them.
It just keeps rattling around in my head.
#USPol

Amazon's Twitch begins testing livestream shopping ads allowing users to buy products "in real time", starting with e.l.f. Cosmetics (Peter Adams/Marketing Dive)
https://www.marketingdive.com/news/elf-cosmetics-first-test-twitc…

E.l.f. Cosmetics first to test Twitch’s new livestream shopping ads
A new integration powered by Amazon Ads’ retail media data is meant to drive “more measurable business outcomes” for E.l.f. on the platform. 

Deciphering Invariant Feature Decoupling in Source-free Time Series Forecasting with Proxy Denoising
Kangjia Yan, Chenxi Liu, Hao Miao, Xinle Wu, Yan Zhao, Chenjuan Guo, Bin Yang
https://arxiv.org/abs/2510.05589

Deciphering Invariant Feature Decoupling in Source-free Time Series Forecasting with Proxy Denoising
The proliferation of mobile devices generates a massive volume of time series across various domains, where effective time series forecasting enables a variety of real-world applications. This study focuses on a new problem of source-free domain adaptation for time series forecasting. It aims to adapt a pretrained model from sufficient source time series to the sparse target time series domain without access to the source data, embracing data protection regulations. To achieve this, we propose …

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
Maggie Wang, Stephen Tian, Aiden Swann, Ola Shorinwa, Jiajun Wu, Mac Schwager
https://arxiv.org/abs/2510.11689

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
Learning robotic manipulation policies directly in the real world can be expensive and time-consuming. While reinforcement learning (RL) policies trained in simulation present a scalable alternative, effective sim-to-real transfer remains challenging, particularly for tasks that require precise dynamics. To address this, we propose Phys2Real, a real-to-sim-to-real RL pipeline that combines vision-language model (VLM)-inferred physical parameter estimates with interactive adaptation through unce…

I keep saying the same thing over and over with my kids: you don't make decisions with your voice, you make them with your body.
"I want to go to the park."
"Ok, put your shoes on."
"I want to go on my play date."
"Put on a jacket and get in the bike."
"I don't want to be late to school."
"I don't control time, if you don't want to be late you have to brush your teeth."
There's a fundamental truth underlying this concept though, one that I hadn't really thought about. On some level, I feel as though, any choice you can't make with your body isn't a real choice. If you're begging someone to do something for you, it's ultimately not something you control.
As I'm compelled, by threat of violence against my family, to pay for war against my comrades and to kill people I don't even know, I think about that. How far is our concept of freedom from the police state we are taught to imagine as the global beacon of liberty. My participation in the violence had always been compulsory.
Perhaps we could do better than just #NoKings.
#USPol

Amazon's Twitch begins testing livestream shopping ads allowing users to buy products "in real time", starting with e.l.f. Cosmetics (Peter Adams/Marketing Dive)
https://www.marketingdive.com/news/elf-cosmetics-first-test-twitc…

E.l.f. Cosmetics first to test Twitch’s new livestream shopping ads
A new integration powered by Amazon Ads’ retail media data is meant to drive “more measurable business outcomes” for E.l.f. on the platform. 

Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz
Frederic Gmeiner, Kenneth Holstein, Nikolas Martelaro
https://arxiv.org/abs/2510.06872

Prototyping Multimodal GenAI Real-Time Agents with Counterfactual Replays and Hybrid Wizard-of-Oz
Recent advancements in multimodal generative AI (GenAI) enable the creation of personal context-aware real-time agents that, for example, can augment user workflows by following their on-screen activities and providing contextual assistance. However, prototyping such experiences is challenging, especially when supporting people with domain-specific tasks using real-time inputs such as speech and screen recordings. While prototyping an LLM-based proactive support agent system, we found that exis…

Lattice-allocated Real-time Line Segment Feature Detection and Tracking Using Only an Event-based Camera
Mikihiro Ikura, Arren Glover, Masayoshi Mizuno, Chiara Bartolozzi
https://arxiv.org/abs/2510.06829

Lattice-allocated Real-time Line Segment Feature Detection and Tracking Using Only an Event-based Camera
Line segment extraction is effective for capturing geometric features of human-made environments. Event-based cameras, which asynchronously respond to contrast changes along edges, enable efficient extraction by reducing redundant data. However, recent methods often rely on additional frame cameras or struggle with high event rates. This research addresses real-time line segment detection and tracking using only a modern, high-resolution (i.e., high event rate) event-based camera. Our lattice-a…

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
Tianheng Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng
https://arxiv.org/abs/2510.08587

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation
This paper presents EGSTalker, a real-time audio-driven talking head generation framework based on 3D Gaussian Splatting (3DGS). Designed to enhance both speed and visual fidelity, EGSTalker requires only 3-5 minutes of training video to synthesize high-quality facial animations. The framework comprises two key stages: static Gaussian initialization and audio-driven deformation. In the first stage, a multi-resolution hash triplane and a Kolmogorov-Arnold Network (KAN) are used to extract spatia…