Record 18052026 · captured 2026-08-25
The world looked up Aaron Rai. 30 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the most people looked up, ranked by Wikipedia pageviews for that day.
Aaron Rai is an English professional golfer who plays on the PGA Tour and the European Tour. He has won one major championship, the 2026 PGA Championship.
The Eurovision Song Contest 2026 was the 70th edition of the Eurovision Song Contest. It consisted of two semi-finals on 12 and 14 May and a final on 16 May 2026, held at Wiener Stadthalle in Vienna, Austria, and presented by Victoria Swarovski and Michael Ost
Gina Joy Carano is an American actress and mixed martial artist. She competed in Elite Xtreme Combat and Strikeforce from 2006 to 2009, where she compiled a 7–1 record. Her popularity led to her being called the "face of women's MMA", although Carano rejected
Ronda Jean Rousey is an American actress, retired professional wrestler, former judoka, and former mixed martial artist. She is best known for her tenures in the Ultimate Fighting Championship (UFC) and WWE.
Darina Nikolaeva Yotova, professionally known as Dara, is a Bulgarian singer and songwriter. She first rose to prominence in 2015 after reaching the final in the Bulgarian edition of The X Factor. In 2016, she released her debut single "K'vo ne chu", and in 20
Obsession is a 2025 American supernatural horror film written, directed, and edited by Curry Barker. The film follows Bear, a music store employee who buys a supernatural toy that grants his wish for his friend Nikki to fall in love with him, which makes her b
Murder of Dominic Russo and Davion Flanagan
The murder of Dominic Russo and Davion Flanagan occurred during the early morning hours of July 31, 2022, when Mackenzie Shirilla intentionally crashed her vehicle into a brick wall in Strongsville, Ohio, United States, killing two passengers: her boyfriend, D
MVP MMA: Rousey vs. Carano was a mixed martial arts event produced by Most Valuable Promotions that took place on May 16, 2026, at the Intuit Dome in Inglewood, California, United States.
Karuppu (transl. Black) is a 2026 Indian Tamil-language fantasy action drama film directed by RJ Balaji from a screenplay he co-wrote with Ashwin Ravichandran, Rahul Raj, T. S. Gopi Krishnan and Karan Aravind Kumar. Produced by Dream Warrior Pictures, the film
Michael Joseph Jackson was an American singer, songwriter, dancer, and philanthropist. Dubbed the "King of Pop", he is widely regarded as one of the most culturally significant figures of the 20th century. His musical achievements broke American racial barrier
Off Campus is an American romantic drama television series created by Louisa Levy for Amazon Prime Video. It is based on the Off-Campus book series by Elle Kennedy. The series premiered on May 13, 2026 and received positive reviews. In February 2026, ahead of
Francis Zavier Ngannou is a Cameroonian and French professional mixed martial artist and professional boxer who currently competes in the Heavyweight division. He previously competed in the heavyweight division in the Ultimate Fighting Championship (UFC) from
Scott Hastings was a Scottish and British and Irish Lions rugby union player and sports summariser. He gained 65 full international caps between 1986 and 1997 and at his retirement he was Scotland's most-capped player ever. He went on two British Lions tours.
Michael Joseph Perry is an American professional mixed martial artist and bare-knuckle boxer currently competing in the Middleweight division of the Bare Knuckle Fighting Championship (BKFC), where he is the current "King of Violence" champion. Perry also comp
Nathan Donald Diaz is an American mixed martial artist and professional boxer who is currently a free agent. Diaz is most known for his time spent fighting in the Ultimate Fighting Championship (UFC), where he fought for over 15 years after winning The Ultimat
The following notable deaths occurred in 2026. Names are reported under the date of death, in alphabetical order. A typical entry reports information in the following sequence:Name, age, country of citizenship at birth, subsequent nationality, what subject was
Michael is a 2026 biographical film directed by Antoine Fuqua and written by John Logan. It follows the early life of the American singer Michael Jackson, from his time with the Jackson 5 in the 1960s to the Bad World Tour in the late 1980s. Jackson is portray
Xabier Alonso Olano is a Spanish professional football manager and former player who is the manager of Premier League club Chelsea. Widely regarded as one of the greatest midfielders of his generation, he was known for his passing range and long-distance shoot
Travis Kuualiialoha Browne is an American retired mixed martial artist who last competed as a Heavyweight in the Ultimate Fighting Championship (UFC).
The Eurovision Song Contest, often known simply as Eurovision, is an international song competition organised annually by the European Broadcasting Union (EBU) since 1956. Each participating broadcaster submits an original song representing its country to be p
Chaska brick is a distinctive brick known for its unique cream color, high clay content, and quality, originating in Chaska, Minnesota, United States. The Chaska brick industry flourished from 1857 until 1950. First called "Chaska brick" in an 1894 Chaska Hera
"Bangaranga" is a song by Bulgarian singer Dara, released on 2 March 2026 and produced by Monoir and Dimitris Kontopoulos. It represented Bulgaria in the Eurovision Song Contest 2026, winning the contest with 516 points. It was the first entry since 2017 to to
List of Eurovision Song Contest winners
73 songs written by 154 songwriters have won the Eurovision Song Contest, an international song competition organised annually by the European Broadcasting Union (EBU). The contest, which has been broadcast every year since its debut in 1956, is one of the lon
Dutton Ranch is an American television series created by Chad Feehan. The series serves as both a spin-off and sequel to Yellowstone (2018–2024) and is the fifth television series in the Yellowstone franchise. It stars Kelly Reilly and Cole Hauser reprising th
Sir James Paul McCartney is an English musician and songwriter. He gained global fame with the Beatles, for whom he was the bassist and keyboardist, and shared primary songwriting and lead vocal duties with John Lennon. McCartney is known for his melodic appro
Alex Anthony Smalley is an American professional golfer who plays on the PGA Tour.
The Eurovision Song Contest 2027 is the upcoming 71st edition of the Eurovision Song Contest. It will consist of two semi-finals on 11 and 13 May and a final on 15 May 2027, held at Arena Burgas in Burgas, Bulgaria. It is being organised by the European Broadc
Swamp Seed is the fifth album by the saxophonist Jimmy Heath of performances recorded in 1963, originally released on the Riverside label.
Legends is a British crime thriller television series written and created by Neil Forsyth and produced by his Tannadice Pictures production company. It is a dramatisation of the true story of undercover British customs investigators who infiltrated the drug wo
Project Hail Mary is a 2026 American science fiction film produced and directed by Phil Lord and Christopher Miller and written by Drew Goddard, based on the 2021 novel of the same name by Andy Weir. It stars Ryan Gosling, who also produced the film, as Ryland
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
In a previous study [B. Li, S. Tang and H. Yu, Commun. Comput. Phy. 27(2):379-411, 2020], it is shown that deep neural networks built with rectified power units (RePU) as activation functions can give better approximation for sufficient smooth functions than those built with rectified linear units, by converting polynomial approximations using power series into deep neural networks with optimal complexity and no appr
Epistemic Monte Carlo Tree Search
The AlphaZero/MuZero (A/MZ) family of algorithms has achieved remarkable success across various challenging domains by integrating Monte Carlo Tree Search (MCTS) with learned models. Learned models introduce epistemic uncertainty, which is caused by learning from limited data and is useful for exploration in sparse reward environments. MCTS does not account for the propagation of this uncertainty however. To address
Learning to Detect and Segment for Open Vocabulary Object Detection
Open vocabulary object detection has been greatly advanced by the recent development of vision-language pretrained model, which helps recognize novel objects with only semantic categories. The prior works mainly focus on knowledge transferring to the object proposal classification and employ class-agnostic box and mask prediction. In this work, we propose CondHead, a principled dynamic network design to better genera
Generative Semantic Communication: Diffusion Models Beyond Bit Recovery
Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos semantically equivalent to the transmitted ones, without necessarily recovering the transmitted sequence of bits. The current solutions still lack the ability to build complex scenes f
Approximate and Weighted Data Reconstruction Attack in Federated Learning
Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data. Although FL is considered privacy-preserved by design, recent data reconstruction attacks demonstrate that an attacker can recover clients' training data based on the parameters shared in FL. However, most existing methods fail to attack t
The Linear Representation Hypothesis and the Geometry of Large Language Models
Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear representation" actually mean? And, how do we make sense of geometric notions (e.g., cosine similarity or projection) in the representation space? To answer these, we use t
FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision
Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network (CNN) models. Existing methods for explaining CNN predictions are largely based on Gradient-weighted Class Activation Maps (Grad-CAM) and focus solely on a single target class; thi
Subgraph-level Universal Prompt Tuning
In the evolving landscape of machine learning, the adaptation of pre-trained models through prompt tuning has become increasingly prominent. This trend is particularly observable in the graph domain, where diverse pre-training strategies present unique challenges in developing effective prompt-based tuning methods for graph neural networks. Previous approaches have been limited, focusing on specialized prompting func
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle differences among fine-grained items. Conversely, Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories, thanks to their substantial knowledge from pre-
Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks
Operator learning is a rising field of scientific computing where inputs or outputs of a machine learning model are functions defined in infinite-dimensional spaces. In this paper, we introduce NEON (Neural Epistemic Operator Networks), an architecture for generating predictions with uncertainty using a single operator network backbone, which presents orders of magnitude less trainable parameters than deep ensembles
An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification
Predictive models may generate biased predictions when classifying imbalanced datasets. This happens when the model favors the majority class, leading to low performance in accurately predicting the minority class. To address this issue, balancing or resampling methods are critical data-centric AI approaches in the modeling process to improve prediction performance. However, there have been debates and questions abou
Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers
Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two complementary methods that leverage the Discrete Cosine Transform (DCT) to enhance the efficiency and performance of Vision Transformers. First, we address the initialization problem by
Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models
Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations, leading to significant degradation when fine-tuned on corrupted datasets. These vulnerabilities are exploited to create protective perturbations that prevent unauthorized image gen
Prompt Stability Scoring for Text Annotation with Large Language Models
Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The reproducibility of LM outputs may nonetheless be vulnerable to small changes in the prompt design. This calls into question the replicability of classification routines. To tackle this problem, researchers have typically
Density Estimation via Binless Multidimensional Integration
We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonparametric, robust, and data-efficient density estimation. BMTI estimates the logarithm of the density by initially computing log-density differences between neighbouring data points. Subsequently, such differences are integrated, weighted by their associated uncertainties, using a maximum-likelihood formulation. This procedure c
Social and Ethical Risks Posed by General-Purpose LLMs for Settling Newcomers in Canada
The non-profit settlement sector in Canada supports newcomers in achieving successful integration. This sector faces increasing operational pressures amidst rising immigration targets, which highlights a need for enhanced efficiency and innovation, potentially through reliable AI solutions. The ad-hoc use of general-purpose generative AI, such as ChatGPT, might become a common practice among newcomers and service pro
RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in learning from multi-view graph data. In the framework of multi-view graph neural networks, a critical challenge lies in effectively combining diverse views, where each view has distinct graph structure features (GSFs). Existing approaches to this challenge primarily focus on two aspects: 1) prioritizing the most important GSFs, 2) utilizing GNNs for f
On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments
Large-scale multi-agent systems are often deployed across wide geographic areas, where agents interact with heterogeneous environments. There is an emerging interest in understanding the role of heterogeneity in the performance of the federated versions of classic reinforcement learning algorithms. In this paper, we study synchronous federated Q-learning, which aims to learn an optimal Q-function by having $K$ agents
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
The advancements of Large Language Models (LLMs) have spurred a growing interest in their application to Named Entity Recognition (NER) methods. However, existing datasets are primarily designed for traditional machine learning methods and are inadequate for LLM-based methods, in terms of corpus selection and overall dataset design logic. Moreover, the prevalent fixed and relatively coarse-grained entity categorizati
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original KST formulation, while mathematically elegant, presents practical challenges due to its limited insight into the structure of inner and outer functions and the large number of unknown variables it introduces. Kolmogorov-Arnold Networks (KANs) leverage KST for function appr
FlipAttack: Jailbreak LLMs via Flipping
This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to comprehend the text when noise is added to the left side. Motivated by these insights, we propose to disguise the harmful prompt by constructing left-side noise merely based on the p
The MediaSpin Dataset: Post-Publication News Headline Edits Annotated for Media Bias
We present MediaSpin, a large-scale language resource capturing how major news outlets modify headlines after publication, and MediaSpin-in-the-Wild, a complementary dataset linking these revised headlines to their downstream engagement on social media. The increasing editability of online news headlines offers new opportunities to study linguistic framing and bias through the lens of editorial revisions. The dataset
Tube Loss: A Novel Approach for Prediction Interval Estimation
This paper proposes a novel loss function, called 'Tube Loss', for simultaneous estimation of bounds of a Prediction Interval (PI) in the regression setup. The PIs obtained by minimizing the empirical risk based on the Tube Loss are shown to be of better quality than the PIs obtained by the existing methods in the following sense. First, it yields intervals that attain the prespecified confidence level t $\in
From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection
Predictive models often degrade in performance due to evolving data distributions, a phenomenon known as data drift. Among its forms, concept drift, where the relationship between explanatory variables and the response variable changes, is particularly challenging to detect and adapt to. Traditional drift detection methods often rely on metrics such as accuracy or marginal variable distributions, which may fail to ca
TrainMover: An Interruption-Resilient Runtime for ML Training
Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime reconfiguration suffer from long downtimes and degraded performance. We present TrainMover, a resilient LLM training runtime that leverages elastic and standby machines to handle interruptions with minimal downtime and zero memory overhead.
Notable events recorded on this day and month across all years.