Record 03022026 · captured 2026-08-25
The world looked up Jeffrey Epstein. 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.
Jeffrey Edward Epstein was an American financier and child sex offender. He began his career as a math teacher at the Dalton School in New York City, before entering the banking and finance sector. Over several decades, he made much of his fortune providing ta
The 68th Annual Grammy Awards honored the best recordings, compositions, and artists from August 31, 2024, to August 30, 2025, as chosen by the members of the Recording Academy, on February 1, 2026. In its 23rd year at Crypto.com Arena in Los Angeles and for t
The Epstein files are a partially released collection of millions of documents, images, videos, and emails related to the activities of American financier and convicted child sex offender Jeffrey Epstein, including his social circle of public figures, politici
Olivia Lauryn Dean is an English singer and songwriter. Her accolades include four Brit Awards and the Grammy Award for Best New Artist.
Benito Antonio Martínez Ocasio, known professionally as Bad Bunny, is a Puerto Rican rapper, singer and record producer. Dubbed the "King of Latin Trap", he is widely credited with helping Spanish-language rap reach mainstream global popularity and is consider
Iron Lung is a 2026 American independent science fiction horror film starring writer, editor, and director Mark Fischbach in his feature-length directorial debut. It is based on the 2022 video game by David Szymanski. It also stars Caroline Kaplan, Troy Baker,
Catherine Anne O'Hara was a Canadian and American actress and comedian, whose career spanned over 50 years. O'Hara started in sketch and improvisational comedy in film and television before taking dramatic roles to expand her career. She received various accol
Savannah Clark Guthrie is an Australian-American broadcast journalist and attorney. She is a main co-anchor of the NBC News morning show Today, a position she has held since July 2012.
Kayleigh Rose Amstutz, known professionally as Chappell Roan, is an American singer and songwriter. She is known for her camp and drag queen–influenced style.
The Grammy Awards, stylized as GRAMMY, and often referred to as the Grammys, are awards presented by the Recording Academy of the United States to recognize outstanding achievements in music. The trophy depicts a gilded gramophone, and the original idea was to
Dhurandhar is a 2025 Indian Hindi-language spy action thriller film written and directed by Aditya Dhar. It is produced by Aditya Dhar, Lokesh Dhar and Jyoti Deshpande under Jio Studios and B62 Studios. The film features an ensemble cast consisting of Ranveer
Groundhog Day is a tradition observed regionally in the United States and Canada on February 2 of every year. It derives from the Pennsylvania Dutch superstition that if a groundhog emerges from its burrow on this day and sees its shadow, it will retreat to it
Ghislaine Noelle Marion Maxwell is a British convicted child sex trafficker and former socialite. In 2021, she was convicted of child sex trafficking, and in 2022 was sentenced to 20 years in prison.
Peter Benjamin Mandelson, Baron Mandelson, is a British former Labour Party politician, lobbyist and diplomat. He was the Member of Parliament (MP) for Hartlepool from 1992 to 2004. He served in Tony Blair and Gordon Brown's cabinets as Minister without portfo
Jason Bradley DeFord, known professionally as Jelly Roll, is an American rapper, singer, and songwriter. He began his music career in 2003, and in 2022 rose to mainstream prominence following the release of his singles "Son of a Sinner" and "Need a Favor".
Spain, officially the Kingdom of Spain, is a country in Southern and Western Europe with territories in North Africa. Featuring the southernmost point of continental Europe, it is the largest country in Southern Europe and the fourth-most populous European Uni
Carlos Alcaraz Garfia is a Spanish professional tennis player. He has been ranked world No. 1 in men's singles by the Association of Tennis Professionals (ATP) for 66 weeks, and finished as the year-end No. 1 in 2022 and 2025. Alcaraz has won 26 ATP Tour–level
A Knight of the Seven Kingdoms (TV series)
A Knight of the Seven Kingdoms is an American fantasy drama television series created by Ira Parker and George R. R. Martin. A prequel to Game of Thrones (2011–2019), it is the third television series in Martin's A Song of Ice and Fire franchise and is an adap
Michael Eugene Archer, better known by his stage name D'Angelo, was an American singer, songwriter, multi-instrumentalist, and record producer. Widely regarded as a pioneer of the neo-soul movement, Billboard named him one of the greatest R&B artists, while Ro
Billie Eilish Pirate Baird O'Connell is an American singer-songwriter. Known for her distinctive musical sound and vocal style, Eilish is a prominent figure in 2020s pop culture. She first gained public attention in 2015 with her debut single "Ocean Eyes" whic
Cher is an American singer and actress. Dubbed the "Goddess of Pop", she is known for her androgynous, contralto voice, bold fashion, elaborate stagecraft and multifaceted career. Her screen roles often reflect her public image as a strong-willed, outspoken wo
Send Help is a 2026 American survival horror film directed and co-produced by Sam Raimi and written by Damian Shannon and Mark Swift. The film stars Rachel McAdams and Dylan O'Brien as an employee and her boss, respectively, who become stranded on a desert isl
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
Border 2 is a 2026 Indian Hindi-language epic war film co-written and directed by Anurag Singh. A sequel to J. P. Dutta's 1997 film Border, it was produced by Bhushan Kumar, Krishan Kumar, J. P. Dutta, and Nidhi Dutta under the banners of T-Series Films and J.
Dollar is the name of more than 25 currencies and their base units. The United States dollar, named after the international currency known as the Spanish dollar, was established in 1792 and is the first so named that still survives. Others include the Australi
Katseye is a girl group based in Los Angeles. The group is composed of six members: Daniela Avanzini, Lara Raj, Manon Bannerman, Megan Skiendiel, Sophia Laforteza, and Yoonchae Jeung. With members from the Philippines, South Korea, Switzerland, and the United
Peter Gene Hernandez, known professionally as Bruno Mars, is an American singer-songwriter, record producer and dancer. Regarded as a pop icon, he is known for his three-octave tenor vocal range, live performances, retro showmanship, and musical versatility. H
Punxsutawney Phil is a groundhog residing in Young Township near Punxsutawney, Pennsylvania, United States, who is the central figure in Punxsutawney's annual Groundhog Day celebration.
Melania is a 2026 American film directed and produced by Brett Ratner. It revolves around the experiences of Melania Trump, the first lady of the United States, in the 20 days before her husband Donald's second presidential inauguration. It was released in the
Pharrell Lanscilo Williams is an American musician, songwriter, record producer and fashion designer. He initially became known as one half of the music production duo the Neptunes, which he established alongside Chad Hugo in 1992. Fifteen of their productions
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
The Function Representation of Artificial Neural Network
This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be recognized that the current ANN can be placed in a more reasonable framework. Perhaps all questions
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
Machine learning (ML) can help fight pandemics like COVID-19 by enabling rapid screening of large volumes of images. To perform data analysis while maintaining patient privacy, we create ML models that satisfy Differential Privacy (DP). Previous works exploring private COVID-19 models are in part based on small datasets, provide weaker or unclear privacy guarantees, and do not investigate practical privacy. We sugges
Safe Control and Learning Using Generalized Action Governor
This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a generalized AG theory for discrete-time systems under bounded uncertainties, and relax the usual requirement of positive invariance to returnability of a safe set. Based on the theory, we pr
Revolutionizing Genomics with Reinforcement Learning Techniques
In recent years, Reinforcement Learning (RL) has emerged as a powerful tool for solving a wide range of problems, including decision-making and genomics. The exponential growth of raw genomic data over the past two decades has exceeded the capacity of manual analysis, leading to a growing interest in automatic data analysis and processing. RL algorithms are capable of learning from experience with minimal human super
The Principle of Uncertain Maximum Entropy
The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the available information be provided error-free (Jaynes, 1982). We relax this requirement using a memoryless communication channel as a framework to derive a new, more general principle. We
MiniLLM: On-Policy Distillation of Large Language Models
Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models to imitate black-box model APIs like ChatGPT. How to effectively distill the knowledge of white-box LLMs into small models is still under-explored, which becomes more important wit
Wikibio: a Semantic Resource for the Intersectional Analysis of Biographical Events
Biographical event detection is a relevant task for the exploration and comparison of the ways in which people's lives are told and represented. In this sense, it may support several applications in digital humanities and in works aimed at exploring bias about minoritized groups. Despite that, there are no corpora and models specifically designed for this task. In this paper we fill this gap by presenting a new c
To address the interpretability challenge in machine learning (ML) systems, counterfactual explanations (CEs) have emerged as a promising solution. CEs are unique as they provide workable suggestions to users, instead of explaining why a certain outcome was predicted. The application of CEs encounters two main challenges: general user preferences and variable ML systems. On one hand, user preferences for specific val
Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks
Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The primary challenge and opportunity lie in leveraging shared information across these tasks and domains to enhance the efficiency of the unified network. The efficiency can be in terms of accuracy, storage cost, computation, or sample complexity. In this paper, we introduc
From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentences
Long sentences have been a persistent issue in written communication for many years since they make it challenging for readers to grasp the main points or follow the initial intention of the writer. This survey, conducted using the PRISMA guidelines, systematically reviews two main strategies for addressing the issue of long sentences: a) sentence compression and b) sentence splitting. An increased trend of interest
Brain-inspired Computing Based on Deep Learning for Human-computer Interaction: A Review
The continuous development of artificial intelligence has a profound impact on biomedicine and other fields, providing new research ideas and technical methods. Brain-inspired computing is an important intersection between multimodal technology and biomedical field. Focusing on the application scenarios of decoding text and speech from brain signals in human-computer interaction, this paper presents a comprehensive r
Operator learning for hyperbolic partial differential equations
We construct the first rigorously justified probabilistic algorithm for recovering the solution operator of a hyperbolic partial differential equation (PDE) in two variables from input-output training pairs. The primary challenge of recovering the solution operator of hyperbolic PDEs is the presence of characteristics, along which the associated Green's function is discontinuous. Therefore, a central component of
Unified Task and Motion Planning using Object-centric Abstractions of Motion Constraints
In task and motion planning (TAMP), the ambiguity and underdetermination of abstract descriptions used by task planning methods make it difficult to characterize physical constraints needed to successfully execute a task. The usual approach is to overlook such constraints at task planning level and to implement expensive sub-symbolic geometric reasoning techniques that perform multiple calls on unfeasible actions, pl
Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
Smartwatch health sensor data are increasingly utilized in smart health applications and patient monitoring, including stress detection. However, such medical data often comprise sensitive personal information and are resource-intensive to acquire for research purposes. In response to this challenge, we introduce the privacy-aware synthetization of multi-sensor smartwatch health readings related to moments of stress,
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of fine-tuned neural networks both empirically and theoretically, the latter using a simplified model of fine-tuning. We show that the vulnerability of non-DP models when measured as the
Towards Artwork Explanation in Large-scale Vision Language Models
Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs possess the ability to understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. T
Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era
Trajectory computing is a pivotal domain encompassing trajectory data management and mining, garnering widespread attention due to its crucial role in various practical applications such as location services, urban traffic, and public safety. Traditional methods, focusing on simplistic spatio-temporal features, face challenges of complex calculations, limited scalability, and inadequate adaptability to real-world com
LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer features in the CLIP visual encoder, as the prefix content. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which further increases th
Deformable image registration plays a crucial role in medical imaging, aiding in disease diagnosis and image-guided interventions. Traditional iterative methods are slow, while deep learning (DL) accelerates solutions but faces usability and precision challenges. This study introduces a pyramid network with the enhanced motion decomposition Transformer (ModeTv2) operator, showcasing superior pairwise optimization (PO
InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, primarily due to the lack of large-scale interaction data and comprehensive descriptions that align with these interaction
VC Theory for Inventory Policies
There has been growing interest in applying reinforcement learning (RL) to inventory management, either by optimizing over temporal transitions or by learning directly from full historical demand trajectories. This contrasts sharply with classical data-driven approaches, which first estimate demand distributions from past data and then compute well-structured optimal policies via dynamic programming. This paper consi
Deep Transformer Network for Monocular Pose Estimation of Shipborne Unmanned Aerial Vehicle
This paper introduces a deep transformer network for estimating the relative 6D pose of a Unmanned Aerial Vehicle (UAV) with respect to a ship using monocular images. A synthetic dataset of ship images is created and annotated with 2D keypoints of multiple ship parts. A Transformer Neural Network model is trained to detect these keypoints and estimate the 6D pose of each part. The estimates are integrated using Bayes
Dual-Phase Continual Learning: Supervised Adaptation Meets Unsupervised Retention
Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to learn sequentially from new data while mitigating the forgetting of prior information, typically under supervised settings involving label shift. Nonetheless, abrupt distribution s
Retrospective Feature Estimation for Continual Learning
The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches often retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigate
Instance Temperature Knowledge Distillation
Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student network to adapt to the varying learning difficulties at different learning stages of KD. KD is a continuous process, but when adjusting the temperature, these methods consider only th
Notable events recorded on this day and month across all years.