Tootfinder

3 sleepers critical to Cowboys success this season https://insidethestar.com/3-sleepers-critical-to-cowboys-success-this-season

Gutierrez: Offense's success hinges on the guys in the trenches https://www.raiders.com/news/raiders-offense-success-hinges-on-offensive-line-kolton-miller-jackson-powers-johnson

Systemd is one of the best things in moving Linux forward in a long time.
(Original title: systemd has been a complete, utter, unmitigated success)
https://blog.tjll.net/the-systemd-revolution-has-been-a-success/

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Young-Jin Park, Kristjan Greenewald, Kaveh Alim, Hao Wang, Navid Azizan
https://arxiv.org/abs/2506.09338

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated and often overestimate success probabilities. To address this, we present a calibration approach, performed via quantile regression, that adjusts PRM outputs to better align with true success probabilities. Leveraging these calibrated success estimates and their associated confidence bounds, w…

Nick Chubb to Texans: Can former All-Pro rusher continue success of RBs going to new teams post-ACL injury?

https://www.cbssports.com/nfl/news/n…

LLM Robustness Leaderboard v1 --Technical report
Pierre Peign\'e - Lefebvre, Quentin Feuillade-Montixi, Tom David, Nicolas Miailhe
https://arxiv.org/abs/2508.06296 https://

LLM Robustness Leaderboard v1 --Technical report
This technical report accompanies the LLM robustness leaderboard published by PRISM Eval for the Paris AI Action Summit. We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic Adversarial Optimization that achieves 100% Attack Success Rate (ASR) against 37 of 41 state-of-the-art LLMs. Beyond binary success metrics, we propose a fine-grained robustness metric estimating the average number of attempts required to elicit harmful behav…

now i really want to try Cheddar Bay biscuits https://mas.to/@carnage4life/114830335171951140

Learning to Optimize Package Picking for Large-Scale, Real-World Robot Induction
Shuai Li, Azarakhsh Keipour, Sicong Zhao, Srinath Rajagopalan, Charles Swan, Kostas E. Bekris
https://arxiv.org/abs/2506.09765

Learning to Optimize Package Picking for Large-Scale, Real-World Robot Induction
Warehouse automation plays a pivotal role in enhancing operational efficiency, minimizing costs, and improving resilience to workforce variability. While prior research has demonstrated the potential of machine learning (ML) models to increase picking success rates in large-scale robotic fleets by prioritizing high-probability picks and packages, these efforts primarily focused on predicting success probabilities for picks sampled using heuristic methods. Limited attention has been given, howev…

Balkonkraftwerk is the German success story of plug-in solar energy (one or two solar panels, inverter with 🔌), which can be self-installed by apartment dwellers and has democratised solar energy. There are now officially over one million of these installations in Germany.
(cartoon ©️ Til Mette)
https://www.…

Trump is frustrated by his own success on immigration (Eric Levitz/Vox)
https://www.vox.com/politics/416526/la-protests-trump-ice-deportations-border-crossings
http://www.memeorandum.com/250612/p15#a250612p15

Wahey! Success on my Javastation Krups, this is a Debian Sarge debootstrapped userspace running over NFS.
#retrocomputing

YouTube releases its 2024 US Impact Report, which says YouTube's creative ecosystem contributed $55B to US GDP in 2024 and supported 490K full-time jobs (Alexandra Veitch/YouTube Official Blog)
https://blog.youtube/news-and-events/2024-us-youtube-impact-re…

2024 U.S. YouTube Impact Report
Learn how YouTube empowers creators and fuels the US economy. Our new report highlights a $55B US GDP contribution and 490K jobs supported, showcasing two decades of shared growth and creator success.

The Julie Parker Practice Success Podcast
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/the-julie-parker-practice-success-podcast/

This is what midi hell looks like... but I'm having success getting it sorted 🥵

#generativeAI experiment : for the page of software package, I am trying to generate a woman computer vision scientist in a superman costume...
I tried different ways to force the generated images to depict a woman, but with no success : I only get the same male scientist!

Some statistics about all robotic #LunarLanding attempts so far from 1965 to 2025 compiled from https://en.wikipedia.org/wiki/List_of_missions_to_the_Moon and https://scicomm.xyz/@AkaSci@fosstodon.org/114636519291241321 in which I only count those for which descent to the surface had been initiated, not missions lost at launch or on the way - in a nutshell ~70% of all landings by government agencies went well (essentially the same rate 60 years ago and now!) but only ~30% by private companies. Here goes ...
There have been two separate periods of soft lunar landing attempts of ca. a dozen years each, from 1965 to 1976 and 2013 to 2025 (ongoing) with a huge gap between them.
In the first interval there were 20 attempts with 13 successes (Luna 9, 13, 16, 17, 19, 20, 21 and 24 and Surveyor 1, 3, 5, 6 and 7), one partial success (Luna 23, counting as 50%) and 6 failures (Luna 5, 7, 8, 15 and 18 and Surveyor 4), so the success rate was 13.5/20 = 68 %. All missions were by - the Soviet and U.S. - governments.
In the second interval there were so far 14 attempts with 6 full successes (Chang'e-3, 4, 5 and 6, Vikram 2 and Blue Ghost), three partial successes (SLIM, IM-1 and 2, counting as 75%, 50% and 25%, respectively) and 5 failures (Beresheet, Vikram 1, Hakuto-R 1 and 2 and Luna 25) so the success rate was 7.5 / 14 = 54%.
But looking only at the government missions it was 72%, slighly up from 50 years ago. While for the commercial attempts it was only 29%. In total the success rate was 19 (18 government-run) missions out of 34 (28) attempts or 62% but 69% for governments only. And if you throw in the 6 Apollo landings, the total success rate rises to 68% and the government-only rate goes even up to 75%.

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
Mattia Litrico, Mario Valerio Giuffrida, Sebastiano Battiato, Devis Tuia
https://arxiv.org/abs/2508.06452 ht…

TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background and object appearances differ significantly across domains. Prior works showed that the language modality can help in the adaptation process, exhibiting more robustness to such complex shifts. In this paper, we introduce TRUST, a novel UDA approach that exploit…

This https://arxiv.org/abs/2505.01997 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated, LLMs tend to become poorly calibrated after alignment with human preferences. In this paper, we investigate why preference alignment affects calibration and how to address this issue. For the first question, we observe that the preference collapse issue in align…

This https://arxiv.org/abs/2506.02878 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the …

This https://arxiv.org/abs/2504.15585 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys…

Nexus of Team Collaboration Stability on Mega Construction Project Success in Electric Vehicle Manufacturing Enterprises: The Moderating Role of Human-AI Integration
Jun Cui
https://arxiv.org/abs/2506.06375

Nexus of Team Collaboration Stability on Mega Construction Project Success in Electric Vehicle Manufacturing Enterprises: The Moderating Role of Human-AI Integration
This study investigates how team collaboration stability influences the success of mega construction projects in electric vehicle manufacturing enterprises, with human-AI integration as a moderating variable. Using structural equation modeling (SEM) with data from 187 project teams across China's electric vehicle sector, results indicate that team collaboration stability significantly enhances project success. The moderating effect of human-AI integration strengthens this relationship, suggesti…

Unambiguous discrimination of the change point for quantum channels
Kenji Nakahira
https://arxiv.org/abs/2508.06785 https://arxiv.org/pdf/2508.06785…

Unambiguous discrimination of the change point for quantum channels
Identifying the precise moment when a quantum channel undergoes a change is a fundamental problem in quantum information theory. We study how accurately one can determine the time at which a channel transitions to another. We investigate the quantum limit of the average success probability in unambiguous discrimination, in which errors are completely avoided by allowing inconclusive results with a certain probability. This problem can be viewed as a quantum process discrimination task, where th…

Mapping NVD Records to Their VFCs: How Hard is it?
Huu Hung Nguyen, Duc Manh Tran, Yiran Cheng, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari, Shar Lwin Khin, Ouh Eng Lieh, Ting Zhang, David Lo
https://arxiv.org/abs/2506.09702

Mapping NVD Records to Their VFCs: How Hard is it?
Mapping National Vulnerability Database (NVD) records to vulnerability-fixing commits (VFCs) is crucial for vulnerability analysis but challenging due to sparse explicit links in NVD references.This study explores this mapping's feasibility through an empirical approach. Manual analysis of NVD references showed Git references enable over 86% success, while non-Git references achieve under 14%. Using these findings, we built an automated pipeline extracting 31,942 VFCs from 20,360 NVD records (8…

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

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

I've heard unhoused folks say they don't want tents because it makes them a target. A lot more people sleeping rough with just a sleeping bag, blanket, or merely a piece of cardboard. And of course the much-sensationalized open-air drug use at 16th & Mission is partly a result of taking tents away. This is a sign of degradation and further cruelty, not success.

San Francisco homeless tent tally hits new low
The number of homeless tents on the streets of San Francisco has reached its lowest point since before the COVID-19 pandemic, data shows.

Armed and ready for takeoff: Cowboys backup QB Joe Milton hoping to ride his 'rocket' to NFL success

https://www.cbssports.com/nfl/news/armed-a

This https://arxiv.org/abs/2502.12096 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Token Communications: A Unified Framework for Cross-modal Context-aware Semantic Communications
In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in generative semantic communications (GenSC). TokCom is a new paradigm, motivated by the recent success of generative foundation models and multimodal large language models (GFM/MLLMs), where the communication units are tokens, enabling efficient transformer-based token processing at the transmitter and receiver. In this paper, we introduce the potential opportu…

Sources: Apple is in talks to acquire US streaming rights for Formula 1 following the success of F1 the Movie, which has grossed ~$300M at the box office (Financial Times)
https://www.ft.com/content/ef6bbb12-1ef5-4fc7-bff5-77d000c36bff

A United Framework for Planning Electric Vehicle Charging Accessibility
Tony Kinchen, Panagiotis Typaldos, Andreas A. Malikopoulos
https://arxiv.org/abs/2508.05827 https://

A United Framework for Planning Electric Vehicle Charging Accessibility
The shift towards electric vehicles (EVs) is crucial for establishing sustainable and low-emission urban transportation systems. However, the success of this transition depends on the strategic placement of the charging infrastructure. This paper addresses the challenge of optimizing charging station locations in dense urban environments while balancing efficiency with spatial accessibility. We propose an optimization framework that integrates traffic simulation, energy consumption modeling, an…

Image-Based Biospeckle Contrast Analysis for Rapid Antimicrobial Susceptibility Testing
M. A. Gameiro, R. F. Pinto, N. V. Lopes
https://arxiv.org/abs/2506.09604

Image-Based Biospeckle Contrast Analysis for Rapid Antimicrobial Susceptibility Testing
Purpose: Antimicrobial resistance is a major global health concern, affecting hospital admissions and treatment success. This study aims to introduce an experimental setup for monitoring bacterial activity over time using image-based contrast as a key biomarker. Methods: The proposed method captures changes in bacterial activity by analyzing variations in image contrast. The approach is evaluated for its ability to detect antimicrobial effects over shorter time intervals compared to conventiona…

The secret to Dak Prescott’s success in 2025 https://insidethestar.com/the-secret-to-dak-prescotts-success-in-2025

Improved error bounds for Koopman operator and reconstructed trajectories approximations with kernel-based methods
Diego Olgu\'in, Axel Osses, H\'ector Ram\'irez
https://arxiv.org/abs/2506.09266

Improved error bounds for Koopman operator and reconstructed trajectories approximations with kernel-based methods
In this article, we propose a new error bound for Koopman operator approximation using Kernel Extended Dynamic Mode Decomposition. The new estimate is $O(N^{-1/2})$, with a constant related to the probability of success of the bound, given by Hoeffding's inequality, similar to other methodologies, such as Philipp et al. Furthermore, we propose a \textit{lifting back} operator to obtain trajectories generated by embedding the initial state and iterating a linear system in a higher dimension. Thi…

A look at UK radio news agency Radio News Hub, which served bulletins to seven radio stations 10 years ago and now serves 400, reaching a 2.3M weekly audience (Rob Waugh/Press Gazette)
https://pressgazette.co.uk/publishers/

Radio News Hub: From Huddersfield basement to global success in ten years
The growing radio news agency supplies bulletins to 400 stations.

Study of Venera Spacecraft Trajectories and Wider Implications
Adam Hibberd
https://arxiv.org/abs/2506.09478 https://arxiv.org/pdf/25…

Study of Venera Spacecraft Trajectories and Wider Implications
Historically, there is no doubt that the early years of the USSR space program put them way ahead of the competition (the USA). Nonetheless, although this was not what the Russians wished to present to the world, the interplanetary campaign, centred around missions to the planet Venus (the Venera program) was also beset with difficulties. Many of the early Venera probes failed, despite making it to a heliocentric orbit, but naturally the success rate improved with time. The result is that there…

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
Michael Amir, Matteo Bettini, Amanda Prorok
https://arxiv.org/abs/2506.09434 https://

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
The success of teams in robotics, nature, and society often depends on the division of labor among diverse specialists; however, a principled explanation for when such diversity surpasses a homogeneous team is still missing. Focusing on multi-agent task allocation problems, our goal is to study this question from the perspective of reward design: what kinds of objectives are best suited for heterogeneous teams? We first consider an instantaneous, non-spatial setting where the global reward is b…

Multimodal Framework for Explainable Autonomous Driving: Integrating Video, Sensor, and Textual Data for Enhanced Decision-Making and Transparency
Abolfazl Zarghani, Amirhossein Ebrahimi, Amir Malekesfandiari
https://arxiv.org/abs/2507.07938

Multimodal Framework for Explainable Autonomous Driving: Integrating Video, Sensor, and Textual Data for Enhanced Decision-Making and Transparency
Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments through diverse data sources, including video streams, sensor measurements, and contextual textual information. However, seamlessly integrating these multimodal inputs and ensuring transparency in AI-driven decisions remain formidable challenges. This study intro…

“They (the government) are fanatic. They are doing things against the interests of the country,” said Rami Dar, 69-year-old retiree, who travelled from a nearby suburb outside Tel Aviv, echoing calls for Trump to force a deal for the hostages.
“Frankly, I’m not an expert or anything, but I feel that after two years of fighting there has been no success,” said Yana, 45, who attended the rally with her husband and two children. “I wonder whether additional lives for both sides, not just …

Imposing the Fundamental Dynamical Constraint of Hydrostatic Balance to Improve Global ML Weather Prediction
Akshay Subramaniam, Dale Durran, David Pruitt, Nathaniel Cresswell-Clay, William Yik
https://arxiv.org/abs/2506.08285

Imposing the Fundamental Dynamical Constraint of Hydrostatic Balance to Improve Global ML Weather Prediction
Forecasting weather accurately and efficiently is a critical capability in our ability to adapt to climate change. Data driven approaches to this problem have enjoyed much success recently providing forecasts with accuracy comparable to physics based numerical prediction models but at significantly reduced computational expense. However, these models typically do not incorporate any physics priors. In this work, we demonstrate improved skill of data driven weather prediction approaches by incor…

Brillouin-Mandelstam scattering in telecommunications optical fiber at millikelvin temperatures
E. A. Cryer-Jenkins, A. C. Leung, H. Rathee, A. K. C. Tan, K. D. Major, M. R. Vanner
https://arxiv.org/abs/2506.09654

Brillouin-Mandelstam scattering in telecommunications optical fiber at millikelvin temperatures
Brillouin-Mandelstam scattering is a strong and readily accessible optical nonlinearity enabling a wide array of applications and research directions. For instance, the three-wave mixing process has been employed to great success for narrow-linewidth lasers, sensing applications, microscopy, and signal processing. While most of these avenues focus on room temperature operation, there is now increasing interest in cryogenic operation owing to the scattering mechanism's significant potential for …

Text-Aware Image Restoration with Diffusion Models
Jaewon Min, Jin Hyeon Kim, Paul Hyunbin Cho, Jaeeun Lee, Jihye Park, Minkyu Park, Sangpil Kim, Hyunhee Park, Seungryong Kim
https://arxiv.org/abs/2506.09993

Text-Aware Image Restoration with Diffusion Models
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those methods frequently generate plausible but incorrect text-like patterns, a phenomenon we refer to as text-image hallucination. In this paper, we introduce Text-Aware Image Restoration (TAIR), a novel restoration task that requires the simultaneous recovery of…

This https://arxiv.org/abs/2505.18344 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Complexity of Diffusion Model Training Without Empirical Risk Minimizer Access
Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the sample complexity suffer from poor scaling with input data dimension or rely on unrealistic assumptions such as access to exact empirical risk minimizers. In this work, we provide a principled analysis of score estimation, establishing a sample complexity bound of $\widetilde{\mathcal{O}}(ε^{-6})$. Our approach lever…

This https://arxiv.org/abs/2505.06711 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Efficient Parallelization of Message Passing Neural Network Potentials for Large-scale Molecular Dynamics
Machine learning potentials have achieved great success in accelerating atomistic simulations. Many of them relying on atom-centered local descriptors are natural for parallelization. More recent message passing neural network (MPNN) models have demonstrated their superior accuracy and become increasingly popular. However, efficiently parallelizing MPNN models across multiple nodes remains challenging, limiting their practical applications in large-scale simulations. Here, we propose an efficie…

Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization
Chengtao Jian, Kai Yang, Ye Ouyang, Xiaozhou Ye
https://arxiv.org/abs/2507.07723 …

Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization
Direct Preference Optimization (DPO) has emerged as a popular and efficient alternative to reward modeling and reinforcement learning for aligning language models with human preferences. Despite its empirical success, the theoretical properties and intrinsic limitations of DPO remain underexplored. In this work, we first present a comprehensive analysis of DPO's dynamics from a probability evolution perspective. Our analysis reveals that DPO is highly sensitive to initialization. It also tends …

This https://arxiv.org/abs/2506.03780 has been replaced.
link: https://scholar.google.com/scholar?q=a

High-Dimensional Learning in Finance
Recent advances in machine learning have shown promising results for financial prediction using large, over-parameterized models. This paper provides theoretical foundations and empirical validation for understanding when and how these methods achieve predictive success. I examine three key aspects of high-dimensional learning in finance. First, I prove that within-sample standardization in Random Fourier Features implementations fundamentally alters the underlying Gaussian kernel approximation…

"Study highlights dangers of declaring conservation success too soon"
#Animals #Conservation

Study highlights dangers of declaring conservation success too soon
The IUCN Red List has long been the globally recognized gauge for assessing how close to extinction a given species is. An improvement in the species’ conservation status from a higher to a lower threat category, known as downlisting, can signal conservation success. But a recent study says this must be done cautiously to avoid […]

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving
Zhenwen Liang, Linfeng Song, Yang Li, Tao Yang, Feng Zhang, Haitao Mi, Dong Yu
https://arxiv.org/abs/2507.06804

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving
Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and their weak formal proving performance. Recent studies show that the informal accuracy exceeds 80% while formal success remains below 8% on benchmarks like PutnamBench. We argue this gap persists because current state-of-the-art provers, by tightly coupling r…

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Songze Li, Mingxuan Zhang, Oubo Ma, Kang Wei, Shouling Ji
https://arxiv.org/abs/2506.09562

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to execute backdoor attacks, producing malicious actions when specific trigger patterns are present in the state observations. However, most existing backdoor attacks rely primarily on simplistic and heu…

SAFE: Multitask Failure Detection for Vision-Language-Action Models
Qiao Gu, Yuanliang Ju, Shengxiang Sun, Igor Gilitschenski, Haruki Nishimura, Masha Itkina, Florian Shkurti
https://arxiv.org/abs/2506.09937

SAFE: Multitask Failure Detection for Vision-Language-Action Models
While vision-language-action models (VLAs) have shown promising robotic behaviors across a diverse set of manipulation tasks, they achieve limited success rates when deployed on novel tasks out-of-the-box. To allow these policies to safely interact with their environments, we need a failure detector that gives a timely alert such that the robot can stop, backtrack, or ask for help. However, existing failure detectors are trained and tested only on one or a few specific tasks, while VLAs require…

Tailoring deep learning for real-time brain-computer interfaces: From offline models to calibration-free online decoding
Martin Wimpff, Jan Zerfowski, Bin Yang
https://arxiv.org/abs/2507.06779

Tailoring deep learning for real-time brain-computer interfaces: From offline models to calibration-free online decoding
Despite the growing success of deep learning (DL) in offline brain-computer interfaces (BCIs), its adoption in real-time applications remains limited due to three primary challenges. First, most DL solutions are designed for offline decoding, making the transition to online decoding unclear. Second, the use of sliding windows in online decoding substantially increases computational complexity. Third, DL models typically require large amounts of training data, which are often scarce in BCI appli…

X-ray transferable polyrepresentation learning
Weronika Hryniewska-Guzik, Przemyslaw Biecek
https://arxiv.org/abs/2507.06264 https://…

X-ray transferable polyrepresentation learning
The success of machine learning algorithms is inherently related to the extraction of meaningful features, as they play a pivotal role in the performance of these algorithms. Central to this challenge is the quality of data representation. However, the ability to generalize and extract these features effectively from unseen datasets is also crucial. In light of this, we introduce a novel concept: the polyrepresentation. Polyrepresentation integrates multiple representations of the same modality…

Superposed Parameterised Quantum Circuits
Viktoria Patapovich, Mo Kordzanganeh, Alexey Melnikov
https://arxiv.org/abs/2506.08749 https://

Superposed Parameterised Quantum Circuits
Quantum machine learning has shown promise for high-dimensional data analysis, yet many existing approaches rely on linear unitary operations and shared trainable parameters across outputs. These constraints limit expressivity and scalability relative to the multi-layered, non-linear architectures of classical deep networks. We introduce superposed parameterised quantum circuits to overcome these limitations. By combining flip-flop quantum random-access memory with repeat-until-success protocol…

I will try to use "Demon Copperhead" in my book club next spring here in Wiesbaden, Germany.
#books #acitivism

A weaponized AI chatbot is flooding Canadian city councils with climate misinformation, and already having some 'success'.
https://www.nationalobserver.com/2025/05/28/investigations/weaponized-ai-chatbot-…

A weaponized AI chatbot is flooding city councils with climate misinformation
Internal instructions accessed by Canada’s National Observer show that the chatbot produces tailored scripts, petitions, reports and even speeches for council chambers. The messaging is all framed to resonate with municipal officials’ duty to represent local interests. The chatbot drops the cost of misinformation to "close to zero."

Falcons' Michael Penix Jr. aims to end Atlanta's seven-year playoff drought, 'have the city turnt'

https://www.cbssports.com/nfl/news/falcons

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Anastasia Ananeva, Anton Tomilov, Marina Volkova
https://arxiv.org/abs/2507.06794

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Self-supervised learning (SSL) models such as Wav2Vec 2.0 and HuBERT have shown remarkable success in extracting phonetic information from raw audio without labelled data. While prior work has demonstrated that SSL embeddings encode phonetic features at the frame level, it remains unclear whether these models preserve temporal structure, specifically, whether embeddings at phoneme boundaries reflect the identity and order of adjacent phonemes. This study investigates the extent to which boundar…

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation
Zhiyou Xiao, Qinhan Yu, Binghui Li, Geng Chen, Chong Chen, Wentao Zhang
https://arxiv.org/abs/2508.06328

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation
Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world applications often demand both multimodal inputs and multimodal outputs for effective communication and grounded reasoning. Motivated by the recent success of Reinforcement Learning (RL) in complex reasoning tasks for Large Language Models (LLMs), we adopt RL as a prin…

The full formula for the probability of "success" is:
p = {
1/(2^(-n 1)) if n is negative, or
1 - (1/(2^(n 1))) if n is zero or positive
}
(Both branches have the same value when n is 0, so the behavior is smooth around the origin.)
How can we tweak this?
First, we can introduce fixed success and/or failure chances unaffected by level, with this formula only taking effect if those don't apply. For example, you could do 10% failure, 80% by formula, and 10% success to keep things from being too sure either way even when levels are very high or low. On the other hand, this flattening makes the benefit of extra advantage levels even less exciting.
Second, we could allow for gradations of success/failure, and treat the coin pools I used to explain that math like dice pools a bit. An in-between could require linearly more success flips to achieve the next higher grade of success at each grade. For example, simple success on a crit role might mean dealing 1.5x damage, but if you succeed on 2 of your flips, you get 9/4 damage, or on 4 flips 27/8, or on 7 flips 81/16. In this world, stacking crit levels might be a viable build, and just giving up on armor would be super dangerous. In the particular case I was using this for just now, I can't easily do gradations of success (that's the reason I turned to probabilities in the first place) but I think I'd favor this approach when feasible.
The main innovation here over simple dice pools is how to handle situations where the number of dice should be negative. I'm almost certain it's not a truly novel innovation though, and some RPG fan can point out which system already does this (please actually do this, I'm an RPG nerd too at heart).
I'll leave this with one more tweak we could do: what if the number 2 in the probability equation were 3, or 2/3? I think this has a similar effect to just scaling all the modifiers a bit, but the algebra escapes me in this moment and I'm a bit lazy. In any case, reducing the base of the probability exponent should let you get a few more gradations near 50%, which is probably a good thing, since the default goes from 25% straight to 50% and then to 75% with no integer stops in between.

This https://arxiv.org/abs/2505.16784 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and adapt them to video understanding tasks via few-shot learning and model ensemble strategies. Specifically, diversified prompt styles and process paradigms are systematically explored and evaluated to effectively guide the attention of large models, fully unleas…

What Drives Team Success? Large-Scale Evidence on the Role of the Team Player Effect
Nico Elbert, Alicia von Schenk, Fabian Kosse, Victor Klockmann, Nikolai Stein, Christoph Flath
https://arxiv.org/abs/2506.04475

What Drives Team Success? Large-Scale Evidence on the Role of the Team Player Effect
Effective teamwork is essential in structured, performance-driven environments, from professional organizations to high-stakes competitive settings. As tasks grow more complex, achieving high performance requires not only technical proficiency but also strong interpersonal skills that allow individuals to coordinate effectively within teams. While prior research has identified social skills and familiarity as key drivers of team success, their joint effects -- particularly in temporary teams --…

Dark monopoles
Vicente Vento
https://arxiv.org/abs/2507.06697 https://arxiv.org/pdf/2507.06697

Dark monopoles
Monopoles have been a subject of much theoretical and experimental research since they were proposed to symmetrize Maxwells equations. However, no experimental signature of their existence has been detected. Many mechanisms have been proposed to explain this lack of success. In here we generalize QED to a two photon theory where the magnetic photon and the monopole belong to dark matter. A naive mixing interaction produces duality and generates experimental consequences for indirect monopole de…

probing gpt5 (free)
- image of a toaster lying on its side - complete fail
- image of a cereal box fully obscuring a toaster - partial success (no toaster, but no toaster shadow)
- list sci-fi novels with furries - 2/10, the rest hallucinated, or not sci-fi, or not novels, or not furry
- refine to sci-fi only, novels only - 3/10, the rest hallucinated
- remove hallucinations from list - "✅ Verified Sci-Fi Novels with Furry Characters or Species" list is 4/6…

This https://arxiv.org/abs/2505.00347 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics
The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of even 2x the model size in order to achieve optimal convergence. We therefore present SOLO in this work to spawn a novel type of optimizer that requires an extremely light memory footprint. While previous efforts have achieved certain success in 8-bit or 4-bit c…

Personal and Professional Success Are Equally Important for Raiders' Crosby https://www.si.com/nfl/raiders/las-vegas-maxx-crosby-pete-carroll-mark-davis

The Dallas Cowboys Have Hope for the Future https://heavy.com/sports/nfl/dallas-cowboys/dallas-cowboys-have-hope-for-future/?adt_ei=[email]

Collaborative Human-Robot Surgery for Mandibular Angle Split Osteotomy: Optical Tracking based Approach
Zhe Han, Huanyu Tian, Tom Vercauteren, Da Liu, Changsheng Li, Xingguang Duan
https://arxiv.org/abs/2507.07794

Collaborative Human-Robot Surgery for Mandibular Angle Split Osteotomy: Optical Tracking based Approach
Mandibular Angle Split Osteotomy (MASO) is a significant procedure in oral and maxillofacial surgery. Despite advances in technique and instrumentation, its success still relies heavily on the surgeon's experience. In this work, a human-robot collaborative system is proposed to perform MASO according to a preoperative plan and under guidance of a surgeon. A task decomposition methodology is used to divide the collaborative surgical procedure into three subtasks: (1) positional control and (2) o…

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
Minghao Shao, Nanda Rani, Kimberly Milner, Haoran Xi, Meet Udeshi, Saksham Aggarwal, Venkata Sai Charan Putrevu, Sandeep Kumar Shukla, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Muhammad Shafique
https://arx…

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate the key factors that drive agent success and provide a detailed recipe for building effective LLM-based offensive security agents. First, we present CTFJudge, a framework leveraging LLM as a judge to analyze agent trajectories and provide granular evaluation across CTF solving steps. Second, we propose a novel metric, …

Exploring the feasibility of probabilistic and deterministic quantum gates between T centers in silicon
Shahrzad Taherizadegan, Faezeh Kimiaee Asadi, Jia-Wei Ji, Daniel Higginbottom, Christoph Simon
https://arxiv.org/abs/2508.06474

Exploring the feasibility of probabilistic and deterministic quantum gates between T centers in silicon
T center defects in silicon provide an attractive platform for quantum technologies due to their unique spin properties and compatibility with mature silicon technologies. We investigate several gate protocols between single T centers, including two probabilistic photon interference-based schemes, a near-deterministic photon scattering gate, and a deterministic magnetic dipole-based scheme. In particular, we study a photon interference-based scheme with feedback which can achieve success probab…

Sources: Instagram and TikTok are working on versions of their apps customized to run on TV screens, following YouTube's success in attracting a TV audience (The Information)
https://www.theinformation.com/articles/tiktok-instag…

TikTok, Instagram Plot TV Apps Following YouTube’s Success
Rejoice, couch potatoes. TikTok and Instagram, following YouTube’s lead, are working on ways to make it easier for viewers to watch videos from their apps on TV screens. The social media giants see an opportunity to grab some of the ad dollars flowing to the streaming TV market. Meta Platforms’ ...

16 players to trade for or trade away in dynasty leagues https://www.espn.com/fantasy/football/story/_/id/45478615/2025-fantasy-football-trade-targets-dynasty

FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation
Boshko Koloski, Senja Pollak, Roberto Navigli, Bla\v{z} \v{S}krlj
https://arxiv.org/abs/2507.06622

FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation
Building on the success of Large Language Models (LLMs), LLM-based representations have dominated the document representation landscape, achieving great performance on the document embedding benchmarks. However, the high-dimensional, computationally expensive embeddings from LLMs tend to be either too generic or inefficient for domain-specific applications. To address these limitations, we introduce FuDoBa a Bayesian optimisation-based method that integrates LLM-based embeddings with domain-spe…

Effective Training Data Synthesis for Improving MLLM Chart Understanding
Yuwei Yang, Zeyu Zhang, Yunzhong Hou, Zhuowan Li, Gaowen Liu, Ali Payani, Yuan-Sen Ting, Liang Zheng
https://arxiv.org/abs/2508.06492

Effective Training Data Synthesis for Improving MLLM Chart Understanding
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still falling behind with a typical success rate of 30%-50% on challenging benchmarks. Previous studies on fine-tuning MLLMs with synthetic charts are often restricted by their inadequate similarity to the real charts, which could compromise model training and performa…

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Yuhan Zhi, Longtian Wang, Xiaofei Xie, Chao Shen, Qiang Hu, Xiaohong Guan
https://arxiv.org/abs/2508.05681

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for identifying the most important data to label. Despite this success, one question remains unanswered: is AL safe? In this work, we introduce ALA, a practical and the first framework to utilize the acquisition function as the poisoning attack surface to reveal the w…

Today: five Starship songs.
Goal: play through each one the way I want cleanly, theoretically able to record a track in one take
It's important to realize that mistakes are also success, in the sense that they provide negative knowledge—it's important to know where you want to go, but also to have a clear idea of where you don't

This https://arxiv.org/abs/2506.01933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emer…

Sources: Apple is in talks to acquire US streaming rights for Formula 1 following the success of F1 the Movie, which has grossed ~$300M at the box office (Financial Times)
https://www.ft.com/content/ef6bbb12-1ef5-4fc7-bff5-77d000c36bff

Russell Wilson says Giants drafting Jaxson Dart 'doesn't change anything at all,' veteran focused on 'success'

https://www.cb…

Rethinking Verification for LLM Code Generation: From Generation to Testing
Zihan Ma, Taolin Zhang, Maosong Cao, Wenwei Zhang, Minnan Luo, Songyang Zhang, Kai Chen
https://arxiv.org/abs/2507.06920

Rethinking Verification for LLM Code Generation: From Generation to Testing
Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number of homogeneous test cases, resulting in subtle faults going undetected. This not only artificially inflates measured performance but also compromises accurate reward estimation in reinforcement learning frameworks utilizing verifiable rewards (RLVR). To addr…

One of the Keys to the Raiders' Success This Season https://www.si.com/nfl/raiders/las-vegas-pete-carroll-marcus-robertson-eric-stokes-jakorian-bennett

Sydney-based Lorikeet, which provides AI agents as "customer concierges", raised a AU$54M Series A led by QED Investors at a AU$200M valuation (Paul Smith/Australian Financial Review)
https://www.afr.com/technology/ai-agent-bo

Lorikeet AI: Canva founders invest in Sydney start-up amid rapid growth
The success of Lorikeet’s AI agent technology has attracted investors including Canva founders Melanie Perkins and Cliff Obrecht.

Why Dak Prescott can dominate during 2025 NFL season https://www.si.com/nfl/cowboys/news/why-dak-prescott-can-dominate-during-2025-nfl-season

Las Vegas Raiders celebrate success of 5th annual INSPIRE event held at Intermountain Health Performance Center, presented by Allegiant https://www.raiders.com/news/las-vegas-rai

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Amanuel Anteneh L\'eandre Brunel, Carlos Gonz\'alez-Arciniegas, Olivier Pfister
https://arxiv.org/abs/2506.07859

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Cubic-phase states are a sufficient resource for universal quantum computing over continuous variables. We present results from numerical experiments in which deep neural networks are trained via reinforcement learning to control a quantum optical circuit for generating cubic-phase states, with an average success rate of 96%. The only non-Gaussian resource required is photon-number-resolving measurements. We also show that the exact same resources enable the direct generation of a quartic-phase…

Sources: Instagram and TikTok are working on versions of their apps customized to run on TV screens, following YouTube's success in attracting a TV audience (The Information)
https://www.theinformation.com/articles/tiktok-instag…

TikTok, Instagram Plot TV Apps Following YouTube’s Success
Rejoice, couch potatoes. TikTok and Instagram, following YouTube’s lead, are working on ways to make it easier for viewers to watch videos from their apps on TV screens. The social media giants see an opportunity to grab some of the ad dollars flowing to the streaming TV market. Meta Platforms’ ...

Diffusion Dataset Condensation: Training Your Diffusion Model Faster with Less Data
Rui Huang, Shitong Shao, Zikai Zhou, Pukun Zhao, Hangyu Guo, Tian Ye, Lichen Bai, Shuo Yang, Zeke Xie
https://arxiv.org/abs/2507.05914

Diffusion Dataset Condensation: Training Your Diffusion Model Faster with Less Data
Diffusion models have achieved remarkable success in various generative tasks, but training them remains highly resource-intensive, often requiring millions of images and many days of GPU computation. From a data-centric perspective addressing this limitation, we study diffusion dataset condensation as a new and challenging problem setting. The goal is to construct a "synthetic" sub-dataset with significantly fewer samples than the original dataset, enabling high-quality diffusion model trainin…

Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization
Hayat Ullah, Arslan Munir, Oliver Nina
https://arxiv.org/abs/2507.06411

Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization
Inspired by the recent success of transformers and multi-stage architectures in video recognition and object detection domains. We thoroughly explore the rich spatio-temporal properties of transformers within a multi-stage architecture paradigm for the temporal action localization (TAL) task. This exploration led to the development of a hierarchical multi-stage transformer architecture called PCL-Former, where each subtask is handled by a dedicated transformer module with a specialized loss fun…

Las Vegas Raiders celebrate success of 5th annual INSPIRE event held at Intermountain Health Performance Center, presented by Allegiant https://www.raiders.com/news/las-vegas-rai

Cowboys' defensive success relies heavily on health at one position https://www.si.com/nfl/cowboys/news/dallas-cowboys-defensive-success-relies-heavily-health-secondary

Justin Simmons has 'no bad blood' with Sean Payton; Free-agent safety hopes to join contender https://www.nfl.com/news/justin-simmons-has-no-bad-blood-with-sean-payton-free-agent-safety-hopes-to-join-contender…

An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques
Walid Mohamed Aly, Taysir Hassan A. Soliman, Amr Mohamed AbdelAziz
https://arxiv.org/abs/2507.05123

An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques
Large Language Models (LLMs) continue to advance natural language processing with their ability to generate human-like text across a range of tasks. Despite the remarkable success of LLMs in Natural Language Processing (NLP), their performance in text summarization across various domains and datasets has not been comprehensively evaluated. At the same time, the ability to summarize text effectively without relying on extensive training data has become a crucial bottleneck. To address these issu…

Is Diversity All You Need for Scalable Robotic Manipulation?
Modi Shi, Li Chen, Jin Chen, Yuxiang Lu, Chiming Liu, Guanghui Ren, Ping Luo, Di Huang, Maoqing Yao, Hongyang Li
https://arxiv.org/abs/2507.06219

Is Diversity All You Need for Scalable Robotic Manipulation?
Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood. In this work, we investigate the nuanced role of data diversity in robot learning by examining three critical dimensions-task (what to do), embodiment (which robot to use), and expert (who demonstrates)-challenging the conventional intuition of "more diverse is better…

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Hui Li, Pengfei Yang, Juanyang Chen, Le Dong, Yanxin Chen, Quan Wang
https://arxiv.org/abs/2507.07015

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and statistical heterogeneities, failing to leverage the complementary prior knowledge embedded in cross-modal teacher models. This paper empirically reveals two critical issues in existing approaches: distillation path selection and knowledge drift. To address …

8) Does the new culture translate to the field? https://www.dallascowboys.com/news/8-does-the-new-culture-translate-to-the-field

Simple Convergence Proof of Adam From a Sign-like Descent Perspective
Hanyang Peng, Shuang Qin, Yue Yu, Fangqing Jiang, Hui Wang, Zhouchen Lin
https://arxiv.org/abs/2507.05966

Simple Convergence Proof of Adam From a Sign-like Descent Perspective
Adam is widely recognized as one of the most effective optimizers for training deep neural networks (DNNs). Despite its remarkable empirical success, its theoretical convergence analysis remains unsatisfactory. Existing works predominantly interpret Adam as a preconditioned stochastic gradient descent with momentum (SGDM), formulated as $\bm{x}_{t+1} = \bm{x}_t - \frac{γ_t}{{\sqrt{\bm{v}_t}+ε}} \circ \bm{m}_t$. This perspective necessitates strong assumptions and intricate techniques, resulti…

Quantum Advantage in Identifying the Parity of Permutations with Certainty
Arnau Diebra, Santiago Llorens, David Gonz\'alez-Lociga, Albert Rico, John Calsamiglia, Mark Hillery, Emili Bagan
https://arxiv.org/abs/2508.04310

Quantum Advantage in Identifying the Parity of Permutations with Certainty
We establish a sharp quantum advantage in determining the parity (even/odd) of an unknown permutation applied to any number $n \ge 3$ of particles. Classically, this is impossible with fewer than~$n$ labels, being the success limited to random guessing. Quantum mechanics does it with certainty with as few as $\lceil \sqrt{n}\, \rceil$ distinguishable states per particle, thanks to entanglement. Below this threshold, not even quantum mechanics helps: both classical and quantum success are limite…

This https://arxiv.org/abs/2309.01754 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the success probability of the quantum algorithm for the short DLP
Ekerå and Håstad have introduced a variation of Shor's algorithm for the discrete logarithm problem (DLP). Unlike Shor's original algorithm, Ekerå-Håstad's algorithm solves the short DLP in groups of unknown order. In this work, we prove a lower bound on the probability of Ekerå-Håstad's algorithm recovering the short logarithm $d$ in a single run. By our bound, the success probability can easily be pushed as high as $1 - 10^{-10}$ for any short $d$. A key to achieving such a high success…

8) Does the new culture translate to the field? https://www.dallascowboys.com/news/8-does-the-new-culture-translate-to-the-field

Peyton Manning tempers expectations for Aaron Rodgers with Steelers, explains biggest success factor

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

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
Jiawei Sun, Hongkang Li, Meng Wang
https://arxiv.org/abs/2507.05533

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
Jumping connections enable Graph Convolutional Networks (GCNs) to overcome over-smoothing, while graph sparsification reduces computational demands by selecting a sub-matrix of the graph adjacency matrix during neighborhood aggregation. Learning GCNs with graph sparsification has shown empirical success across various applications, but a theoretical understanding of the generalization guarantees remains limited, with existing analyses ignoring either graph sparsification or jumping connections.…

GenIR: Generative Visual Feedback for Mental Image Retrieval
Diji Yang, Minghao Liu, Chung-Hsiang Lo, Yi Zhang, James Davis
https://arxiv.org/abs/2506.06220

GenIR: Generative Visual Feedback for Mental Image Retrieval
Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot action. Instead, it is often a multi-round process guided by clues in mind, that is, a mental image ranging from vague recollections to vivid mental representations of the target image. Motivated by this gap, we study the task of Mental Image Retrieval (MIR), which…

Texans guard Laken Tomlinson: 'I believe offensive line could be the strength of a team' https://www.nfl.com/news/texans-guard-laken-tomlinson-offensive-line-strength-team