Record 04052026 · captured 2026-08-25
The world looked up Michael Jackson. 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.
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
The Devil Wears Prada 2 is a 2026 American comedy drama film directed by David Frankel and written by Aline Brosh McKenna. A sequel to the 2006 film The Devil Wears Prada, it sees Meryl Streep, Anne Hathaway, Emily Blunt, and Stanley Tucci reprising their role
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
Spirit Airlines was an American ultra-low-cost airline, headquartered in Dania Beach, Florida. It operated scheduled flights throughout the United States, the Caribbean, and Latin America. In 2023, it was the seventh-largest passenger carrier in North America
2026 West Bengal Legislative Assembly election
Legislative Assembly elections were held in West Bengal to elect all 294 members of the West Bengal Legislative Assembly in two phases on 23 and 29 April 2026, with the votes counted and results for 293 seats released on 4 May 2026. The election saw the defeat
Shipping ethics controversy in fanfiction
Beginning in the mid-2010s and continuing into the 2020s, significant discourse emerged in online fandom spaces around the ethical implications of taboo and abusive content within shipping, the depiction of romantic or sexual relationships between characters i
Jaafar Jeremiah Jackson is an American actor and singer. A member of the Jackson family, he released his debut single "Got Me Singing" in 2019 but gained popularity for portraying his uncle Michael Jackson in the record-breaking biographical film Michael (2026
Olivia Isabel Rodrigo is an American singer-songwriter and actress. She began her career as a child actress, appearing in commercials and the direct-to-video film An American Girl: Grace Stirs Up Success (2015). She rose to prominence with her leading roles in
Neatsville is an unincorporated community in Adair County, in the U.S. state of Kentucky. It is located at the junction of Kentucky Route 206 and Kentucky Route 76. Its elevation is 705 feet (215 m). For unknown reasons, the town's name was spelled as Neetsvil
Alessandro Leone Zanardi was an Italian racing driver and para-cyclist who competed in Formula One between 1991 and 1999, in CART between 1996 and 2001, in the World Touring Car Championship from 2005 to 2009, and at two editions of the Summer Paralympics in 2
The Devil Wears Prada is a 2006 American comedy-drama film directed by David Frankel and produced by Wendy Finerman. The screenplay, written by Aline Brosh McKenna, is based on the 2003 novel by Lauren Weisberger. The film stars Meryl Streep, Anne Hathaway, St
Real Club Celta de Vigo, commonly known as Celta Vigo or just Celta, is a Spanish professional football club based in Vigo, Galicia, that competes in La Liga, the top tier of Spanish football. Nicknamed Os Celestes, the club was founded in August 1923 as Club
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
Apex is a 2026 survival thriller film directed by Baltasar Kormákur, written by Jeremy Robbins, and starring Charlize Theron and Taron Egerton. It tells the story of a rock climber and kayaker who finds herself being hunted in the wilds of Australia.
KFIM-LP, known on the air as REAL 102.1, was a low-power FM Christian Music radio station located in Carroll, IA. The station was a music intensive format and carried the Today's Christian Music offering from the Salem Radio Network until it was purchased by E
Limonene is a slightly yellow-green liquid aliphatic hydrocarbon classified as a cyclic monoterpene, and is the major component in the fragrance and essential oil of citrus fruit peels, taking its name from Italian limone ("lemon").
Raja Shivaji is a 2026 Indian historical action drama film co-written and directed by Riteish Deshmukh, based on the life of Shivaji, the founder of the Maratha Empire. The film was produced by Genelia D'Souza and Jyoti Deshpande under Mumbai Film Company and
Jermaine LaJuane Jacksun is an American musician. A member of the Jackson family, he was second vocalist after his brother Michael of the Jackson 5 from 1964 to 1975, and played bass guitar. In 1983, he rejoined the group, which had been renamed the Jacksons;
2026 Tamil Nadu Legislative Assembly election
Elections to appoint the 234 members of the 17th Tamil Nadu Legislative Assembly, the highest body of the Government of Tamil Nadu, were held on 23 April 2026. The results were declared on 4 May 2026 by the Election Commission of India. It recorded the highest
Cherie DeVaux is an American thoroughbred racehorse trainer. In 2026, she won the Kentucky Derby and the Belmont Stakes as the trainer of Golden Tempo, becoming the first woman to train a Derby winner and the second to train a Belmont winner, after Jena Antonu
Richard H. Simpson was an American politician. He served as a Democratic member of the Florida House of Representatives.
Sir David Frederick Attenborough is an English broadcaster, natural historian, and writer. His presenting career began as host of Zoo Quest in 1954, and has spanned seven decades; it includes the nine documentary series forming The Life Collection, Natural Wor
Anthony David Benavidez is an American professional boxer who has held world championships in three weight classes. He has held the unified World Boxing Association (WBA) and World Boxing Organization (WBO) cruiserweight titles since May 2026, the WBA light he
Katherine Esther Jackson is the matriarch of the Jackson family of entertainers that includes her children Michael and Janet Jackson. Michael dedicated his sixth studio album Thriller (1982) to her. Janet did the same with her fourth studio album Rhythm Nation
Joel Hans Embiid is a Cameroonian American professional basketball player for the Philadelphia 76ers of the National Basketball Association (NBA). After one year of college basketball with the Kansas Jayhawks, he was drafted third overall by the 76ers in the 2
Anne Jacqueline Hathaway is an American actress. Her accolades include an Academy Award, a British Academy Film Award, a Golden Globe Award, and a Primetime Emmy Award. Her films have grossed over $6.8 billion worldwide.
Golden Tempo is an American thoroughbred racehorse best known for winning the 2026 Kentucky Derby and Belmont Stakes.
Deborah Jeanne Rowe is an American woman who was the second wife of pop musician Michael Jackson, with whom she had two children.
Andrea Kimi Antonelli is an Italian racing driver who competes in Formula One for Mercedes. Antonelli has won six Formula One Grands Prix since his debut in 2025.
Dhurandhar: The Revenge is a 2026 Indian Hindi-language spy action-thriller film written and directed by Aditya Dhar. It is produced by Dhar, Lokesh Dhar, and Jyoti Deshpande under Jio Studios and B62 Studios. It is a sequel to the 2025 film Dhurandhar and the
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, sev
We present two algorithms to initialize layers of tensorized neural networks and general tensor network algorithms using partial computations of their Frobenius norms and positive lineal entrywise sums, depending on the type of tensor network involved. The core of this method is the use of the norm of subnetworks of the tensor network in an iterative way, so that we normalize by the finite values of the norms that le
Value Explicit Pretraining for Learning Transferable Representations
Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations for transfer reinforcement learning. VEP enables efficient learning of new tasks that share similar objectives as previously learned tasks, by learning an encoder that trains represe
Koopman-Assisted Reinforcement Learning
The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theory. However, these equations become intractable for high-dimensional or nonlinear systems. This paper develops two new reinforcement learning algorithms based on the data-driven Koopman operator, which lifts a nonlinear system into new coordinates where the dynamics become appro
AI Consciousness is Inevitable: A Theoretical Computer Science Perspective
We look at consciousness through the lens of Theoretical Computer Science, a branch of mathematics that studies computation under resource limitations, distinguishing functions that are efficiently computable from those that are not. From this perspective, we develop a formal machine model for consciousness. The model is inspired by Alan Turing's simple yet powerful model of computation and Bernard Baars' the
Laissez-Faire Harms: Algorithmic Biases in Generative Language Models
The rapid deployment of generative language models (LMs) has raised concerns about social biases affecting the well-being of diverse consumers. The extant literature on generative LMs has primarily examined bias via explicit identity prompting. However, prior research on bias in earlier language-based technology platforms, including search engines, has shown that discrimination can occur even when identity terms are
Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications
Tiny machine learning (TinyML) co-locates models with sensors on microcontrollers, where small models (which are disproportionately sensitive to label noise) and bespoke binary tasks (which lack standard benchmarks) make general-purpose dataset practices a poor fit. Visual Wake Words (VWW), the prior standard TinyML person detection benchmark, contains roughly 123K images and has an estimated label error rate of 7.8%
A Survey on Vision-Language-Action Models for Embodied AI
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language models (VLMs), a new category of multimodal models -- referred to as vision-language-action (VLA) models -- has emerged to address language-conditioned robotic tasks
Image Score: Learning and Evaluating Human Preferences for Mercari Search
Mercari is the largest C2C e-commerce marketplace in Japan, having more than 20 million active monthly users. Search being the fundamental way to discover desired items, we have always had a substantial amount of data with implicit feedback. Although we actively take advantage of that to provide the best service for our users, the correlation of implicit feedback for such tasks as image quality assessment is not triv
Last-Iterate Convergence of General Parameterized Policies in Constrained MDPs
This paper focuses on learning a Constrained Markov Decision Process (CMDP) via general parameterized policies. We propose a Primal-Dual based Regularized Accelerated Natural Policy Gradient (PDR-ANPG) algorithm that uses entropy and quadratic regularizers to reach this goal. For parameterized policy classes with a transferred compatibility approximation error, $ε_{\mathrm{bias}}$, PDR-ANPG achieves a last-iterate $ε
A Unified Deep Learning Framework for Motion Correction in Medical Imaging
Deep learning has shown significant value in medical image registration for motion correction, however, current techniques are either limited by the type and range of motion they can handle, or require iterative inference and/or retraining for new imaging data. To address these limitations, we introduce UniMo, a Unified Motion Correction framework that leverages deep neural networks to correct for various types of mo
Machine Learning Toric Duality in Brane Tilings
We apply a variety of machine learning methods to the study of Seiberg duality within 4d $\mathcal{N}=1$ quantum field theories arising on the worldvolumes of D3-branes probing toric Calabi-Yau 3-folds. Such theories admit an elegant description in terms of bipartite tessellations of the torus known as brane tilings or dimer models. An intricate network of infrared dualities interconnects the space of such theories a
Dynamics-Encoded Deep Learning for Robust System Identification and Parameter Estimation
Incorporating a priori physics knowledge into machine learning leads to more robust and interpretable algorithms. In this work, we combine deep learning techniques and classic numerical methods for differential equations to address two challenging missing physics problems in dynamical systems theory: dynamics discovery and parameter estimation. The presented methods encode available information relating to the system
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long videos through extremely extended context lengths. However, this comes at the cost of significantly increased computational overhead due to the massive number of visual tokens, making efficiency a major bottleneck. In this paper, we identify the root of this inefficiency as
Bias in Large Language Models: Origin, Evaluation, and Mitigation
Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and over-smoothing, where repeated propagation makes node representations indistinguishable. Both phenomena stem from the interaction between message passing and the input topology, ultima
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of discrete text prompts, we formulate post-training adaptation as a latent control problem, where the goal embedding serves as a continuous control variable to modulate the behavior
TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems
Efficient real-time solvers for forward and inverse problems are essential in engineering and science applications. Machine learning surrogate models have emerged as promising alternatives to traditional methods, offering substantially reduced computational time. Nevertheless, these models typically demand extensive training datasets to achieve robust generalization across diverse scenarios. While physics-based appro
Representation in large language models
The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over fundamental theoretical issues has led to stalemate, with entrenched camps of LLM optimists and pessimists often committed to very different views of how these systems work. Overcom
Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty
We develop a new class of distance-aware error bounds that tightly characterize the approximation error of spline neural networks. Our bottom-up approach analyzes the error bound of each neuron (a spline) and then extends it to the full network. We begin with error bounds for Newton's polynomial, generalize them to arbitrary splines under higher-order Lipschitz continuity, and extend the result to function compos
Copula-enhanced Vision Transformer for high myopia diagnosis through OU UWF fundus images
The advancement of AI-assisted myopia screening necessitates the joint diagnosis of both-eye (OU) high myopia (HM) status and the prediction of axial length (AL). This clinical requirement introduces a complex mixed-type (binary-continuous) multitask learning task with bi-domain (OU) image covariates, giving rise to two key challenges: i) capture the inter-ocular asymmetry of OU images within a cutting-edge foundatio
Mean-field limit from general mixtures of experts to quantum neural networks
In this work, we study the asymptotic behavior of Mixture of Experts (MoE) trained via gradient flow on supervised learning problems. Our main result establishes the propagation of chaos for a MoE as the number of experts diverges. We demonstrate that the corresponding empirical measure of their parameters is close to a probability measure that solves a nonlinear continuity equation, and we provide an explicit conver
Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learners
We analyze the performance of heterogeneous learning agents in asset markets with stochastic payoffs. Our main focus is on comparing Bayesian learners and no-regret learners who compete in markets and identifying the conditions under which each approach is more effective. We formally relate the notions of survival and market dominance studied in economics and the framework of regret minimization, thereby bridging the
Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers
Gaussian Splatting has become a popular technique for various 3D Computer Vision tasks, including novel view synthesis, scene reconstruction, and dynamic scene rendering. However, the challenge of natural-looking object insertion, where the object's appearance seamlessly matches the scene, remains unsolved. In this work, we propose a method, dubbed D3DR, for inserting a 3DGS-parametrized object into a 3DGS scene
Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental statistical limits concerning aligning LLMs with human preferences, with a focus on the probabilistic representation of human preferences and the preservation of diverse preferences in aligned LLMs. W
Notable events recorded on this day and month across all years.